Tidying

author Neil Smith <neil.git@njae.me.uk>

Thu, 22 Feb 2018 16:29:49 +0000 (16:29 +0000)

committer Neil Smith <neil.git@njae.me.uk>

Thu, 22 Feb 2018 16:29:49 +0000 (16:29 +0000)
author Neil Smith <neil.git@njae.me.uk>
Thu, 22 Feb 2018 16:29:49 +0000 (16:29 +0000)
committer Neil Smith <neil.git@njae.me.uk>
Thu, 22 Feb 2018 16:29:49 +0000 (16:29 +0000)
diff --git a/.gitignore b/.gitignore

new file mode 100644 (file)

index 0000000..06fdb0b
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,50 @@
+.directory
+
+*.py[cod]
+
+# C extensions
+*.so
+
+# Packages
+*.egg
+*.egg-info
+dist
+build
+eggs
+parts
+bin
+var
+sdist
+develop-eggs
+.installed.cfg
+lib
+lib64
+__pycache__
+
+# Installer logs
+pip-log.txt
+
+# Unit test / coverage reports
+.coverage
+.tox
+nosetests.xml
+
+# Translations
+*.mo
+
+# Mr Developer
+.mr.developer.cfg
+.project
+.pydevproject
+
+# IPython
+.ipynb*
+
+# Sublime text
+*.sublime-workspace
+
+# Logs
+*.log
+
+# Data analysis directory, as it contains personal data.
+data-analysis/*
diff --git a/.ipynb_checkpoints/accidents-regression-checkpoint.ipynb b/.ipynb_checkpoints/accidents-regression-checkpoint.ipynb

deleted file mode 100644 (file)

index 2fd6442..0000000
--- a/.ipynb_checkpoints/accidents-regression-checkpoint.ipynb
+++ /dev/null
@@ -1,6 +0,0 @@
-{
- "cells": [],
- "metadata": {},
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/.ipynb_checkpoints/section5.1-checkpoint.ipynb b/.ipynb_checkpoints/section5.1-checkpoint.ipynb

deleted file mode 100644 (file)

index dca6b94..0000000
--- a/.ipynb_checkpoints/section5.1-checkpoint.ipynb
+++ /dev/null
@@ -1,705 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Section 5.1: Using the model"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Imports and defintions"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "── Attaching packages ─────────────────────────────────────── tidyverse 1.2.1 ──\n",
-      "✔ ggplot2 2.2.1     ✔ purrr   0.2.4\n",
-      "✔ tibble  1.4.2     ✔ dplyr   0.7.4\n",
-      "✔ tidyr   0.8.0     ✔ stringr 1.2.0\n",
-      "✔ readr   1.1.1     ✔ forcats 0.2.0\n",
-      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
-      "✖ dplyr::filter() masks stats::filter()\n",
-      "✖ dplyr::lag()    masks stats::lag()\n"
-     ]
-    }
-   ],
-   "source": [
-    "library(tidyverse)\n",
-    "# library(cowplot)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Multiple plot function\n",
-    "#\n",
-    "# ggplot objects can be passed in ..., or to plotlist (as a list of ggplot objects)\n",
-    "# - cols:   Number of columns in layout\n",
-    "# - layout: A matrix specifying the layout. If present, 'cols' is ignored.\n",
-    "#\n",
-    "# If the layout is something like matrix(c(1,2,3,3), nrow=2, byrow=TRUE),\n",
-    "# then plot 1 will go in the upper left, 2 will go in the upper right, and\n",
-    "# 3 will go all the way across the bottom.\n",
-    "#\n",
-    "multiplot <- function(..., plotlist=NULL, file, cols=1, layout=NULL) {\n",
-    "  library(grid)\n",
-    "\n",
-    "  # Make a list from the ... arguments and plotlist\n",
-    "  plots <- c(list(...), plotlist)\n",
-    "\n",
-    "  numPlots = length(plots)\n",
-    "\n",
-    "  # If layout is NULL, then use 'cols' to determine layout\n",
-    "  if (is.null(layout)) {\n",
-    "    # Make the panel\n",
-    "    # ncol: Number of columns of plots\n",
-    "    # nrow: Number of rows needed, calculated from # of cols\n",
-    "    layout <- matrix(seq(1, cols * ceiling(numPlots/cols)),\n",
-    "                    ncol = cols, nrow = ceiling(numPlots/cols))\n",
-    "  }\n",
-    "\n",
-    " if (numPlots==1) {\n",
-    "    print(plots[[1]])\n",
-    "\n",
-    "  } else {\n",
-    "    # Set up the page\n",
-    "    grid.newpage()\n",
-    "    pushViewport(viewport(layout = grid.layout(nrow(layout), ncol(layout))))\n",
-    "\n",
-    "    # Make each plot, in the correct location\n",
-    "    for (i in 1:numPlots) {\n",
-    "      # Get the i,j matrix positions of the regions that contain this subplot\n",
-    "      matchidx <- as.data.frame(which(layout == i, arr.ind = TRUE))\n",
-    "\n",
-    "      print(plots[[i]], vp = viewport(layout.pos.row = matchidx$row,\n",
-    "                                      layout.pos.col = matchidx$col))\n",
-    "    }\n",
-    "  }\n",
-    "}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Modelling abrasion loss\n",
-    "\n",
-    "This example concerns the dataset `rubber`, which you first met in Exercise 3.1. The experiment introduced in that exercise concerned an investigation of the resistance of rubber to abrasion (the abrasion loss) and how that resistance depended on various attributes of the rubber. In Exercise 3.1, the only explanatory variable we analysed was hardness; but in Exercise 3.19, a second explanatory variable, tensile strength, was taken into account too. There are 30 datapoints."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th scope=col>loss</th><th scope=col>hardness</th><th scope=col>strength</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><td>372</td><td>45 </td><td>162</td></tr>\n",
-       "\t<tr><td>206</td><td>55 </td><td>233</td></tr>\n",
-       "\t<tr><td>175</td><td>61 </td><td>232</td></tr>\n",
-       "\t<tr><td>154</td><td>66 </td><td>231</td></tr>\n",
-       "\t<tr><td>136</td><td>71 </td><td>231</td></tr>\n",
-       "\t<tr><td>112</td><td>71 </td><td>237</td></tr>\n",
-       "\t<tr><td> 55</td><td>81 </td><td>224</td></tr>\n",
-       "\t<tr><td> 45</td><td>86 </td><td>219</td></tr>\n",
-       "\t<tr><td>221</td><td>53 </td><td>203</td></tr>\n",
-       "\t<tr><td>166</td><td>60 </td><td>189</td></tr>\n",
-       "\t<tr><td>164</td><td>64 </td><td>210</td></tr>\n",
-       "\t<tr><td>113</td><td>68 </td><td>210</td></tr>\n",
-       "\t<tr><td> 82</td><td>79 </td><td>196</td></tr>\n",
-       "\t<tr><td> 32</td><td>81 </td><td>180</td></tr>\n",
-       "\t<tr><td>228</td><td>56 </td><td>200</td></tr>\n",
-       "\t<tr><td>196</td><td>68 </td><td>173</td></tr>\n",
-       "\t<tr><td>128</td><td>75 </td><td>188</td></tr>\n",
-       "\t<tr><td> 97</td><td>83 </td><td>161</td></tr>\n",
-       "\t<tr><td> 64</td><td>88 </td><td>119</td></tr>\n",
-       "\t<tr><td>249</td><td>59 </td><td>161</td></tr>\n",
-       "\t<tr><td>219</td><td>71 </td><td>151</td></tr>\n",
-       "\t<tr><td>186</td><td>80 </td><td>165</td></tr>\n",
-       "\t<tr><td>155</td><td>82 </td><td>151</td></tr>\n",
-       "\t<tr><td>114</td><td>89 </td><td>128</td></tr>\n",
-       "\t<tr><td>341</td><td>51 </td><td>161</td></tr>\n",
-       "\t<tr><td>340</td><td>59 </td><td>146</td></tr>\n",
-       "\t<tr><td>283</td><td>65 </td><td>148</td></tr>\n",
-       "\t<tr><td>267</td><td>74 </td><td>144</td></tr>\n",
-       "\t<tr><td>215</td><td>81 </td><td>134</td></tr>\n",
-       "\t<tr><td>148</td><td>86 </td><td>127</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lll}\n",
-       " loss & hardness & strength\\\\\n",
-       "\\hline\n",
-       "\t 372 & 45  & 162\\\\\n",
-       "\t 206 & 55  & 233\\\\\n",
-       "\t 175 & 61  & 232\\\\\n",
-       "\t 154 & 66  & 231\\\\\n",
-       "\t 136 & 71  & 231\\\\\n",
-       "\t 112 & 71  & 237\\\\\n",
-       "\t  55 & 81  & 224\\\\\n",
-       "\t  45 & 86  & 219\\\\\n",
-       "\t 221 & 53  & 203\\\\\n",
-       "\t 166 & 60  & 189\\\\\n",
-       "\t 164 & 64  & 210\\\\\n",
-       "\t 113 & 68  & 210\\\\\n",
-       "\t  82 & 79  & 196\\\\\n",
-       "\t  32 & 81  & 180\\\\\n",
-       "\t 228 & 56  & 200\\\\\n",
-       "\t 196 & 68  & 173\\\\\n",
-       "\t 128 & 75  & 188\\\\\n",
-       "\t  97 & 83  & 161\\\\\n",
-       "\t  64 & 88  & 119\\\\\n",
-       "\t 249 & 59  & 161\\\\\n",
-       "\t 219 & 71  & 151\\\\\n",
-       "\t 186 & 80  & 165\\\\\n",
-       "\t 155 & 82  & 151\\\\\n",
-       "\t 114 & 89  & 128\\\\\n",
-       "\t 341 & 51  & 161\\\\\n",
-       "\t 340 & 59  & 146\\\\\n",
-       "\t 283 & 65  & 148\\\\\n",
-       "\t 267 & 74  & 144\\\\\n",
-       "\t 215 & 81  & 134\\\\\n",
-       "\t 148 & 86  & 127\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "loss | hardness | strength | \n",
-       "|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|\n",
-       "| 372 | 45  | 162 | \n",
-       "| 206 | 55  | 233 | \n",
-       "| 175 | 61  | 232 | \n",
-       "| 154 | 66  | 231 | \n",
-       "| 136 | 71  | 231 | \n",
-       "| 112 | 71  | 237 | \n",
-       "|  55 | 81  | 224 | \n",
-       "|  45 | 86  | 219 | \n",
-       "| 221 | 53  | 203 | \n",
-       "| 166 | 60  | 189 | \n",
-       "| 164 | 64  | 210 | \n",
-       "| 113 | 68  | 210 | \n",
-       "|  82 | 79  | 196 | \n",
-       "|  32 | 81  | 180 | \n",
-       "| 228 | 56  | 200 | \n",
-       "| 196 | 68  | 173 | \n",
-       "| 128 | 75  | 188 | \n",
-       "|  97 | 83  | 161 | \n",
-       "|  64 | 88  | 119 | \n",
-       "| 249 | 59  | 161 | \n",
-       "| 219 | 71  | 151 | \n",
-       "| 186 | 80  | 165 | \n",
-       "| 155 | 82  | 151 | \n",
-       "| 114 | 89  | 128 | \n",
-       "| 341 | 51  | 161 | \n",
-       "| 340 | 59  | 146 | \n",
-       "| 283 | 65  | 148 | \n",
-       "| 267 | 74  | 144 | \n",
-       "| 215 | 81  | 134 | \n",
-       "| 148 | 86  | 127 | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "   loss hardness strength\n",
-       "1  372  45       162     \n",
-       "2  206  55       233     \n",
-       "3  175  61       232     \n",
-       "4  154  66       231     \n",
-       "5  136  71       231     \n",
-       "6  112  71       237     \n",
-       "7   55  81       224     \n",
-       "8   45  86       219     \n",
-       "9  221  53       203     \n",
-       "10 166  60       189     \n",
-       "11 164  64       210     \n",
-       "12 113  68       210     \n",
-       "13  82  79       196     \n",
-       "14  32  81       180     \n",
-       "15 228  56       200     \n",
-       "16 196  68       173     \n",
-       "17 128  75       188     \n",
-       "18  97  83       161     \n",
-       "19  64  88       119     \n",
-       "20 249  59       161     \n",
-       "21 219  71       151     \n",
-       "22 186  80       165     \n",
-       "23 155  82       151     \n",
-       "24 114  89       128     \n",
-       "25 341  51       161     \n",
-       "26 340  59       146     \n",
-       "27 283  65       148     \n",
-       "28 267  74       144     \n",
-       "29 215  81       134     \n",
-       "30 148  86       127     "
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "# Load the data from the file.\n",
-    "rubber <- read.csv('rubber.csv')\n",
-    "rubber"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The figures below show scatterplots of abrasion loss against hardness and of abrasion loss against strength. (A scatterplot of abrasion loss against hardness also appeared in Solution 3.1.) Figure (a) suggests a strong decreasing linear relationship of abrasion loss with hardness. Figure (b) is much less indicative of any strong dependence of abrasion loss on tensile strength."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# ggplot(rubber, aes(x=hardness, y=loss)) + geom_point()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA0gAAANICAMAAADKOT/pAAADAFBMVEUAAAABAQECAgIDAwME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\nrULxyAmRBSMAAAAASUVORK5CYII=",
-      "text/plain": [
-       "plot without title"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "hardloss <- ggplot(rubber, aes(x=hardness, y=loss)) + geom_point()\n",
-    "strloss <-  ggplot(rubber, aes(x=strength, y=loss)) + geom_point()\n",
-    "\n",
-    "# plot_grid(hardloss, strloss, labels = \"AUTO\")\n",
-    "\n",
-    "multiplot(hardloss, strloss)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In exercise 3.5(a) you obtained the following output for the regression of abrasion loss on hardness."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\n",
-       "Call:\n",
-       "lm(formula = loss ~ hardness, data = rubber)\n",
-       "\n",
-       "Residuals:\n",
-       "   Min     1Q Median     3Q    Max \n",
-       "-86.15 -46.77 -19.49  54.27 111.49 \n",
-       "\n",
-       "Coefficients:\n",
-       "            Estimate Std. Error t value Pr(>|t|)    \n",
-       "(Intercept) 550.4151    65.7867   8.367 4.22e-09 ***\n",
-       "hardness     -5.3366     0.9229  -5.782 3.29e-06 ***\n",
-       "---\n",
-       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
-       "\n",
-       "Residual standard error: 60.52 on 28 degrees of freedom\n",
-       "Multiple R-squared:  0.5442,\tAdjusted R-squared:  0.5279 \n",
-       "F-statistic: 33.43 on 1 and 28 DF,  p-value: 3.294e-06\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th></th><th scope=col>Df</th><th scope=col>Sum Sq</th><th scope=col>Mean Sq</th><th scope=col>F value</th><th scope=col>Pr(&gt;F)</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><th scope=row>hardness</th><td> 1          </td><td>122455.0    </td><td>122455.037  </td><td>33.43276    </td><td>3.294489e-06</td></tr>\n",
-       "\t<tr><th scope=row>Residuals</th><td>28          </td><td>102556.3    </td><td>  3662.726  </td><td>      NA    </td><td>          NA</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lllll}\n",
-       "  & Df & Sum Sq & Mean Sq & F value & Pr(>F)\\\\\n",
-       "\\hline\n",
-       "\thardness &  1           & 122455.0     & 122455.037   & 33.43276     & 3.294489e-06\\\\\n",
-       "\tResiduals & 28           & 102556.3     &   3662.726   &       NA     &           NA\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "| <!--/--> | Df | Sum Sq | Mean Sq | F value | Pr(>F) | \n",
-       "|---|---|\n",
-       "| hardness |  1           | 122455.0     | 122455.037   | 33.43276     | 3.294489e-06 | \n",
-       "| Residuals | 28           | 102556.3     |   3662.726   |       NA     |           NA | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "          Df Sum Sq   Mean Sq    F value  Pr(>F)      \n",
-       "hardness   1 122455.0 122455.037 33.43276 3.294489e-06\n",
-       "Residuals 28 102556.3   3662.726       NA           NA"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "          Df   Sum Sq    Mean Sq  F value       Pr(>F)   PctExp\n",
-      "hardness   1 122455.0 122455.037 33.43276 3.294489e-06 54.42171\n",
-      "Residuals 28 102556.3   3662.726       NA           NA 45.57829\n"
-     ]
-    }
-   ],
-   "source": [
-    "fit <- lm(loss ~ hardness, data = rubber)\n",
-    "summary(fit)\n",
-    "anova(fit)\n",
-    "af <- anova(fit)\n",
-    "afss <- af$\"Sum Sq\"\n",
-    "print(cbind(af,PctExp=afss/sum(afss)*100))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "solution": "shown",
-    "solution2": "hidden",
-    "solution2_first": true,
-    "solution_first": true
-   },
-   "source": [
-    "## Exercise\n",
-    "Now repeat the for the regression of abrasion loss on tensile strength."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Solution"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {
-    "solution2": "hidden"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\n",
-       "Call:\n",
-       "lm(formula = loss ~ strength, data = rubber)\n",
-       "\n",
-       "Residuals:\n",
-       "     Min       1Q   Median       3Q      Max \n",
-       "-155.640  -59.919    2.795   61.221  183.285 \n",
-       "\n",
-       "Coefficients:\n",
-       "            Estimate Std. Error t value Pr(>|t|)    \n",
-       "(Intercept) 305.2248    79.9962   3.815 0.000688 ***\n",
-       "strength     -0.7192     0.4347  -1.654 0.109232    \n",
-       "---\n",
-       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
-       "\n",
-       "Residual standard error: 85.56 on 28 degrees of freedom\n",
-       "Multiple R-squared:  0.08904,\tAdjusted R-squared:  0.0565 \n",
-       "F-statistic: 2.737 on 1 and 28 DF,  p-value: 0.1092\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th></th><th scope=col>Df</th><th scope=col>Sum Sq</th><th scope=col>Mean Sq</th><th scope=col>F value</th><th scope=col>Pr(&gt;F)</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><th scope=row>strength</th><td> 1       </td><td> 20034.77</td><td>20034.772</td><td>2.736769 </td><td>0.1092317</td></tr>\n",
-       "\t<tr><th scope=row>Residuals</th><td>28       </td><td>204976.59</td><td> 7320.593</td><td>      NA </td><td>       NA</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lllll}\n",
-       "  & Df & Sum Sq & Mean Sq & F value & Pr(>F)\\\\\n",
-       "\\hline\n",
-       "\tstrength &  1        &  20034.77 & 20034.772 & 2.736769  & 0.1092317\\\\\n",
-       "\tResiduals & 28        & 204976.59 &  7320.593 &       NA  &        NA\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "| <!--/--> | Df | Sum Sq | Mean Sq | F value | Pr(>F) | \n",
-       "|---|---|\n",
-       "| strength |  1        |  20034.77 | 20034.772 | 2.736769  | 0.1092317 | \n",
-       "| Residuals | 28        | 204976.59 |  7320.593 |       NA  |        NA | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "          Df Sum Sq    Mean Sq   F value  Pr(>F)   \n",
-       "strength   1  20034.77 20034.772 2.736769 0.1092317\n",
-       "Residuals 28 204976.59  7320.593       NA        NA"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "          Df    Sum Sq   Mean Sq  F value    Pr(>F)    PctExp\n",
-      "strength   1  20034.77 20034.772 2.736769 0.1092317  8.903893\n",
-      "Residuals 28 204976.59  7320.593       NA        NA 91.096107\n"
-     ]
-    }
-   ],
-   "source": [
-    "fit <- lm(loss ~ strength, data = rubber)\n",
-    "summary(fit)\n",
-    "anova(fit)\n",
-    "af <- anova(fit)\n",
-    "afss <- af$\"Sum Sq\"\n",
-    "print(cbind(af,PctExp=afss/sum(afss)*100))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "solution2": "hidden"
-   },
-   "source": [
-    "Individually, then, regression of abrasion loss on hardness seems satisfactory, albeit accounting for a disappointingly small percentage of the variance in the response; regression of abrasion loss on tensile strength,  on the other hand, seems to have very little explanatory power. "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "solution": "hidden"
-   },
-   "source": [
-    "However, back in Exercise 3.19 it was shown that the residuals from the former regression showed a clear relationship with the tensile strength values, and this suggested that a regression model involving both variables is necessary. \n",
-    "\n",
-    "Let us try it. The only change is to include `strength` in the equations being fitted in the `lm()` function."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\n",
-       "Call:\n",
-       "lm(formula = loss ~ hardness + strength, data = rubber)\n",
-       "\n",
-       "Residuals:\n",
-       "    Min      1Q  Median      3Q     Max \n",
-       "-79.385 -14.608   3.816  19.755  65.981 \n",
-       "\n",
-       "Coefficients:\n",
-       "            Estimate Std. Error t value Pr(>|t|)    \n",
-       "(Intercept) 885.1611    61.7516  14.334 3.84e-14 ***\n",
-       "hardness     -6.5708     0.5832 -11.267 1.03e-11 ***\n",
-       "strength     -1.3743     0.1943  -7.073 1.32e-07 ***\n",
-       "---\n",
-       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
-       "\n",
-       "Residual standard error: 36.49 on 27 degrees of freedom\n",
-       "Multiple R-squared:  0.8402,\tAdjusted R-squared:  0.8284 \n",
-       "F-statistic:    71 on 2 and 27 DF,  p-value: 1.767e-11\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th></th><th scope=col>Df</th><th scope=col>Sum Sq</th><th scope=col>Mean Sq</th><th scope=col>F value</th><th scope=col>Pr(&gt;F)</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><th scope=row>hardness</th><td> 1          </td><td>122455.04   </td><td>122455.037  </td><td>91.96967    </td><td>3.458255e-10</td></tr>\n",
-       "\t<tr><th scope=row>strength</th><td> 1          </td><td> 66606.59   </td><td> 66606.586  </td><td>50.02477    </td><td>1.324645e-07</td></tr>\n",
-       "\t<tr><th scope=row>Residuals</th><td>27          </td><td> 35949.74   </td><td>  1331.472  </td><td>      NA    </td><td>          NA</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lllll}\n",
-       "  & Df & Sum Sq & Mean Sq & F value & Pr(>F)\\\\\n",
-       "\\hline\n",
-       "\thardness &  1           & 122455.04    & 122455.037   & 91.96967     & 3.458255e-10\\\\\n",
-       "\tstrength &  1           &  66606.59    &  66606.586   & 50.02477     & 1.324645e-07\\\\\n",
-       "\tResiduals & 27           &  35949.74    &   1331.472   &       NA     &           NA\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "| <!--/--> | Df | Sum Sq | Mean Sq | F value | Pr(>F) | \n",
-       "|---|---|---|\n",
-       "| hardness |  1           | 122455.04    | 122455.037   | 91.96967     | 3.458255e-10 | \n",
-       "| strength |  1           |  66606.59    |  66606.586   | 50.02477     | 1.324645e-07 | \n",
-       "| Residuals | 27           |  35949.74    |   1331.472   |       NA     |           NA | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "          Df Sum Sq    Mean Sq    F value  Pr(>F)      \n",
-       "hardness   1 122455.04 122455.037 91.96967 3.458255e-10\n",
-       "strength   1  66606.59  66606.586 50.02477 1.324645e-07\n",
-       "Residuals 27  35949.74   1331.472       NA           NA"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "          Df    Sum Sq    Mean Sq  F value       Pr(>F)   PctExp\n",
-      "hardness   1 122455.04 122455.037 91.96967 3.458255e-10 54.42171\n",
-      "strength   1  66606.59  66606.586 50.02477 1.324645e-07 29.60143\n",
-      "Residuals 27  35949.74   1331.472       NA           NA 15.97686\n"
-     ]
-    }
-   ],
-   "source": [
-    "fit <- lm(loss ~ hardness + strength, data = rubber)\n",
-    "summary(fit)\n",
-    "anova(fit)\n",
-    "af <- anova(fit)\n",
-    "afss <- af$\"Sum Sq\"\n",
-    "print(cbind(af,PctExp=afss/sum(afss)*100))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Looking at the regression coefficient output next, the estimated model for the mean response is\n",
-    "\n",
-    "$$ \\hat{y} = \\hat{\\alpha} + \\hat{\\beta}_1 x_1 + \\hat{\\beta}_2 x_2 = 885.2 − 6.571 x_1 − 1.374 x_2 $$ \n",
-    "\n",
-    "where $x_1$ and $x_2$ stand for values of hardness and tensile strength, respectively. \n",
-    "\n",
-    "Associated with each estimated parameter, GenStat gives a standard error (details of the calculation of which need not concern us now) and hence a _t_-statistic (estimate divided by standard error) to be compared with the distribution on `d.f. (Residual)`=27 degrees of freedom. GenStat makes the comparison and gives _p_ values, which in this case are all very small, suggesting strong evidence for the non-zeroness (and hence presence) of each parameter, $\\alpha$, $\\beta_1$ and $\\beta_2$, individually."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "So, even though the single regression of abrasion loss on tensile strength did not suggest a close relationship, when taken in conjunction with the effect of hardness the effect of tensile strength is also a considerable one. A key idea here is that $\\beta_1$ and $\\beta_2$ (and more generally $\\beta_1, \\beta_2, \\ldots , \\beta_k$ in model (5.1)) are partial regression coefficients. That is, $\\beta_1$ measures the effect of an increase of one unit in $x_1$ treating the value of the other variable $x_2$ as fixed. Contrast this with the single regression model $E(Y) = \\alpha + \\beta_1 x_1$ in which $\\beta_1$ represents an increase of one unit in $x_1$ treating $x_2$ as zero. The meaning of $\\beta_1$ in the regression models with one and two explanatory variables is not the same.\n",
-    "\n",
-    "You will notice that the percentage of variance accounted for has increased dramatically in the two-explanatory-variable model to a much more respectable 82.8%. This statistic has the same interpretation — or difficulty of interpretation — as for the case of one explanatory variable (see [Unit 3](unit3.ipynb)).\n",
-    "\n",
-    "Other items in the GenStat output are as for the case of one explanatory variable: the `Standard error of observations` is $\\hat{\\sigma}$, and is the square root of `m.s. (Residual)`; the message about standardised residuals will be clarified below; and the message about leverage will be ignored until [Unit 10](unit10.ipynb).\n",
-    "\n",
-    "The simple residuals are, again, defined as the differences between the observed and predicted responses:\n",
-    "\n",
-    "$$ r_i = y_i - \\left( \\hat{\\alpha} + \\sum_{j=1}^{k} \\hat{\\beta}_j x_{i, j} \\right) , i = 1, 2, \\ldots, n. $$\n",
-    "\n",
-    "GenStat can obtain these for you and produce a plot of residuals against fitted values. The fitted values are simply $\\hat{Y}_i = \\hat{\\alpha} + \\sum_{j=1}^{k} \\hat{\\beta}_j x_{i, j}$. As in the regression models in [Unit 3](unit3.ipynb), the default in GenStat is to use deviance residuals which, in this context, are equivalent to standardised residuals (simple residuals divided by their estimated standard errors)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Example 5.2"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "R",
-   "language": "R",
-   "name": "ir"
-  },
-  "language_info": {
-   "codemirror_mode": "r",
-   "file_extension": ".r",
-   "mimetype": "text/x-r-source",
-   "name": "R",
-   "pygments_lexer": "r",
-   "version": "3.4.2"
-  },
-  "toc": {
-   "nav_menu": {},
-   "number_sections": true,
-   "sideBar": true,
-   "skip_h1_title": false,
-   "title_cell": "Table of Contents",
-   "title_sidebar": "Contents",
-   "toc_cell": false,
-   "toc_position": {
-    "height": "calc(100% - 180px)",
-    "left": "10px",
-    "top": "150px",
-    "width": "342px"
-   },
-   "toc_section_display": true,
-   "toc_window_display": true
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/.ipynb_checkpoints/section5.1solutions-checkpoint.ipynb b/.ipynb_checkpoints/section5.1solutions-checkpoint.ipynb

deleted file mode 100644 (file)

index 9e446d1..0000000
--- a/.ipynb_checkpoints/section5.1solutions-checkpoint.ipynb
+++ /dev/null
@@ -1,1557 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Section 5.1: Using the model"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "heading_collapsed": true
-   },
-   "source": [
-    "## Imports and defintions"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "hidden": true
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "── Attaching packages ─────────────────────────────────────── tidyverse 1.2.1 ──\n",
-      "✔ ggplot2 2.2.1     ✔ purrr   0.2.4\n",
-      "✔ tibble  1.4.2     ✔ dplyr   0.7.4\n",
-      "✔ tidyr   0.8.0     ✔ stringr 1.2.0\n",
-      "✔ readr   1.1.1     ✔ forcats 0.2.0\n",
-      "── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──\n",
-      "✖ dplyr::filter() masks stats::filter()\n",
-      "✖ dplyr::lag()    masks stats::lag()\n"
-     ]
-    }
-   ],
-   "source": [
-    "library(tidyverse)\n",
-    "# library(cowplot)\n",
-    "library(repr)\n",
-    "library(ggfortify)\n",
-    "\n",
-    "# Change plot size to 4 x 3\n",
-    "options(repr.plot.width=6, repr.plot.height=4)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "hidden": true
-   },
-   "outputs": [],
-   "source": [
-    "# Multiple plot function\n",
-    "#\n",
-    "# ggplot objects can be passed in ..., or to plotlist (as a list of ggplot objects)\n",
-    "# - cols:   Number of columns in layout\n",
-    "# - layout: A matrix specifying the layout. If present, 'cols' is ignored.\n",
-    "#\n",
-    "# If the layout is something like matrix(c(1,2,3,3), nrow=2, byrow=TRUE),\n",
-    "# then plot 1 will go in the upper left, 2 will go in the upper right, and\n",
-    "# 3 will go all the way across the bottom.\n",
-    "#\n",
-    "multiplot <- function(..., plotlist=NULL, file, cols=1, layout=NULL) {\n",
-    "  library(grid)\n",
-    "\n",
-    "  # Make a list from the ... arguments and plotlist\n",
-    "  plots <- c(list(...), plotlist)\n",
-    "\n",
-    "  numPlots = length(plots)\n",
-    "\n",
-    "  # If layout is NULL, then use 'cols' to determine layout\n",
-    "  if (is.null(layout)) {\n",
-    "    # Make the panel\n",
-    "    # ncol: Number of columns of plots\n",
-    "    # nrow: Number of rows needed, calculated from # of cols\n",
-    "    layout <- matrix(seq(1, cols * ceiling(numPlots/cols)),\n",
-    "                    ncol = cols, nrow = ceiling(numPlots/cols))\n",
-    "  }\n",
-    "\n",
-    " if (numPlots==1) {\n",
-    "    print(plots[[1]])\n",
-    "\n",
-    "  } else {\n",
-    "    # Set up the page\n",
-    "    grid.newpage()\n",
-    "    pushViewport(viewport(layout = grid.layout(nrow(layout), ncol(layout))))\n",
-    "\n",
-    "    # Make each plot, in the correct location\n",
-    "    for (i in 1:numPlots) {\n",
-    "      # Get the i,j matrix positions of the regions that contain this subplot\n",
-    "      matchidx <- as.data.frame(which(layout == i, arr.ind = TRUE))\n",
-    "\n",
-    "      print(plots[[i]], vp = viewport(layout.pos.row = matchidx$row,\n",
-    "                                      layout.pos.col = matchidx$col))\n",
-    "    }\n",
-    "  }\n",
-    "}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Modelling abrasion loss\n",
-    "\n",
-    "This example concerns the dataset `rubber`, which you first met in Exercise 3.1. The experiment introduced in that exercise concerned an investigation of the resistance of rubber to abrasion (the abrasion loss) and how that resistance depended on various attributes of the rubber. In Exercise 3.1, the only explanatory variable we analysed was hardness; but in Exercise 3.19, a second explanatory variable, tensile strength, was taken into account too. There are 30 datapoints."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th scope=col>loss</th><th scope=col>hardness</th><th scope=col>strength</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><td>372</td><td>45 </td><td>162</td></tr>\n",
-       "\t<tr><td>206</td><td>55 </td><td>233</td></tr>\n",
-       "\t<tr><td>175</td><td>61 </td><td>232</td></tr>\n",
-       "\t<tr><td>154</td><td>66 </td><td>231</td></tr>\n",
-       "\t<tr><td>136</td><td>71 </td><td>231</td></tr>\n",
-       "\t<tr><td>112</td><td>71 </td><td>237</td></tr>\n",
-       "\t<tr><td> 55</td><td>81 </td><td>224</td></tr>\n",
-       "\t<tr><td> 45</td><td>86 </td><td>219</td></tr>\n",
-       "\t<tr><td>221</td><td>53 </td><td>203</td></tr>\n",
-       "\t<tr><td>166</td><td>60 </td><td>189</td></tr>\n",
-       "\t<tr><td>164</td><td>64 </td><td>210</td></tr>\n",
-       "\t<tr><td>113</td><td>68 </td><td>210</td></tr>\n",
-       "\t<tr><td> 82</td><td>79 </td><td>196</td></tr>\n",
-       "\t<tr><td> 32</td><td>81 </td><td>180</td></tr>\n",
-       "\t<tr><td>228</td><td>56 </td><td>200</td></tr>\n",
-       "\t<tr><td>196</td><td>68 </td><td>173</td></tr>\n",
-       "\t<tr><td>128</td><td>75 </td><td>188</td></tr>\n",
-       "\t<tr><td> 97</td><td>83 </td><td>161</td></tr>\n",
-       "\t<tr><td> 64</td><td>88 </td><td>119</td></tr>\n",
-       "\t<tr><td>249</td><td>59 </td><td>161</td></tr>\n",
-       "\t<tr><td>219</td><td>71 </td><td>151</td></tr>\n",
-       "\t<tr><td>186</td><td>80 </td><td>165</td></tr>\n",
-       "\t<tr><td>155</td><td>82 </td><td>151</td></tr>\n",
-       "\t<tr><td>114</td><td>89 </td><td>128</td></tr>\n",
-       "\t<tr><td>341</td><td>51 </td><td>161</td></tr>\n",
-       "\t<tr><td>340</td><td>59 </td><td>146</td></tr>\n",
-       "\t<tr><td>283</td><td>65 </td><td>148</td></tr>\n",
-       "\t<tr><td>267</td><td>74 </td><td>144</td></tr>\n",
-       "\t<tr><td>215</td><td>81 </td><td>134</td></tr>\n",
-       "\t<tr><td>148</td><td>86 </td><td>127</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lll}\n",
-       " loss & hardness & strength\\\\\n",
-       "\\hline\n",
-       "\t 372 & 45  & 162\\\\\n",
-       "\t 206 & 55  & 233\\\\\n",
-       "\t 175 & 61  & 232\\\\\n",
-       "\t 154 & 66  & 231\\\\\n",
-       "\t 136 & 71  & 231\\\\\n",
-       "\t 112 & 71  & 237\\\\\n",
-       "\t  55 & 81  & 224\\\\\n",
-       "\t  45 & 86  & 219\\\\\n",
-       "\t 221 & 53  & 203\\\\\n",
-       "\t 166 & 60  & 189\\\\\n",
-       "\t 164 & 64  & 210\\\\\n",
-       "\t 113 & 68  & 210\\\\\n",
-       "\t  82 & 79  & 196\\\\\n",
-       "\t  32 & 81  & 180\\\\\n",
-       "\t 228 & 56  & 200\\\\\n",
-       "\t 196 & 68  & 173\\\\\n",
-       "\t 128 & 75  & 188\\\\\n",
-       "\t  97 & 83  & 161\\\\\n",
-       "\t  64 & 88  & 119\\\\\n",
-       "\t 249 & 59  & 161\\\\\n",
-       "\t 219 & 71  & 151\\\\\n",
-       "\t 186 & 80  & 165\\\\\n",
-       "\t 155 & 82  & 151\\\\\n",
-       "\t 114 & 89  & 128\\\\\n",
-       "\t 341 & 51  & 161\\\\\n",
-       "\t 340 & 59  & 146\\\\\n",
-       "\t 283 & 65  & 148\\\\\n",
-       "\t 267 & 74  & 144\\\\\n",
-       "\t 215 & 81  & 134\\\\\n",
-       "\t 148 & 86  & 127\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "loss | hardness | strength | \n",
-       "|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|\n",
-       "| 372 | 45  | 162 | \n",
-       "| 206 | 55  | 233 | \n",
-       "| 175 | 61  | 232 | \n",
-       "| 154 | 66  | 231 | \n",
-       "| 136 | 71  | 231 | \n",
-       "| 112 | 71  | 237 | \n",
-       "|  55 | 81  | 224 | \n",
-       "|  45 | 86  | 219 | \n",
-       "| 221 | 53  | 203 | \n",
-       "| 166 | 60  | 189 | \n",
-       "| 164 | 64  | 210 | \n",
-       "| 113 | 68  | 210 | \n",
-       "|  82 | 79  | 196 | \n",
-       "|  32 | 81  | 180 | \n",
-       "| 228 | 56  | 200 | \n",
-       "| 196 | 68  | 173 | \n",
-       "| 128 | 75  | 188 | \n",
-       "|  97 | 83  | 161 | \n",
-       "|  64 | 88  | 119 | \n",
-       "| 249 | 59  | 161 | \n",
-       "| 219 | 71  | 151 | \n",
-       "| 186 | 80  | 165 | \n",
-       "| 155 | 82  | 151 | \n",
-       "| 114 | 89  | 128 | \n",
-       "| 341 | 51  | 161 | \n",
-       "| 340 | 59  | 146 | \n",
-       "| 283 | 65  | 148 | \n",
-       "| 267 | 74  | 144 | \n",
-       "| 215 | 81  | 134 | \n",
-       "| 148 | 86  | 127 | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "   loss hardness strength\n",
-       "1  372  45       162     \n",
-       "2  206  55       233     \n",
-       "3  175  61       232     \n",
-       "4  154  66       231     \n",
-       "5  136  71       231     \n",
-       "6  112  71       237     \n",
-       "7   55  81       224     \n",
-       "8   45  86       219     \n",
-       "9  221  53       203     \n",
-       "10 166  60       189     \n",
-       "11 164  64       210     \n",
-       "12 113  68       210     \n",
-       "13  82  79       196     \n",
-       "14  32  81       180     \n",
-       "15 228  56       200     \n",
-       "16 196  68       173     \n",
-       "17 128  75       188     \n",
-       "18  97  83       161     \n",
-       "19  64  88       119     \n",
-       "20 249  59       161     \n",
-       "21 219  71       151     \n",
-       "22 186  80       165     \n",
-       "23 155  82       151     \n",
-       "24 114  89       128     \n",
-       "25 341  51       161     \n",
-       "26 340  59       146     \n",
-       "27 283  65       148     \n",
-       "28 267  74       144     \n",
-       "29 215  81       134     \n",
-       "30 148  86       127     "
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "# Load the data from the file.\n",
-    "rubber <- read.csv('rubber.csv')\n",
-    "rubber"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The figures below show scatterplots of abrasion loss against hardness and of abrasion loss against strength. (A scatterplot of abrasion loss against hardness also appeared in Solution 3.1.) Figure (a) suggests a strong decreasing linear relationship of abrasion loss with hardness. Figure (b) is much less indicative of any strong dependence of abrasion loss on tensile strength."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# ggplot(rubber, aes(x=hardness, y=loss)) + geom_point()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtAAAAHgCAMAAAC7G6qeAAADAFBMVEUAAAABAQECAgIDAwME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\nGvgKCA18BYQGvuL/Ad6D8+SrqQ5UAAAAAElFTkSuQmCC",
-      "text/plain": [
-       "plot without title"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "hardloss <- ggplot(rubber, aes(x=hardness, y=loss)) + geom_point()\n",
-    "strloss <-  ggplot(rubber, aes(x=strength, y=loss)) + geom_point()\n",
-    "\n",
-    "# plot_grid(hardloss, strloss, labels = \"AUTO\")\n",
-    "\n",
-    "multiplot(hardloss, strloss, cols=2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "In exercise 3.5(a) you obtained the following output for the regression of abrasion loss on hardness."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\n",
-       "Call:\n",
-       "lm(formula = loss ~ hardness, data = rubber)\n",
-       "\n",
-       "Residuals:\n",
-       "   Min     1Q Median     3Q    Max \n",
-       "-86.15 -46.77 -19.49  54.27 111.49 \n",
-       "\n",
-       "Coefficients:\n",
-       "            Estimate Std. Error t value Pr(>|t|)    \n",
-       "(Intercept) 550.4151    65.7867   8.367 4.22e-09 ***\n",
-       "hardness     -5.3366     0.9229  -5.782 3.29e-06 ***\n",
-       "---\n",
-       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
-       "\n",
-       "Residual standard error: 60.52 on 28 degrees of freedom\n",
-       "Multiple R-squared:  0.5442,\tAdjusted R-squared:  0.5279 \n",
-       "F-statistic: 33.43 on 1 and 28 DF,  p-value: 3.294e-06\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th></th><th scope=col>Df</th><th scope=col>Sum Sq</th><th scope=col>Mean Sq</th><th scope=col>F value</th><th scope=col>Pr(&gt;F)</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><th scope=row>hardness</th><td> 1          </td><td>122455.0    </td><td>122455.037  </td><td>33.43276    </td><td>3.294489e-06</td></tr>\n",
-       "\t<tr><th scope=row>Residuals</th><td>28          </td><td>102556.3    </td><td>  3662.726  </td><td>      NA    </td><td>          NA</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lllll}\n",
-       "  & Df & Sum Sq & Mean Sq & F value & Pr(>F)\\\\\n",
-       "\\hline\n",
-       "\thardness &  1           & 122455.0     & 122455.037   & 33.43276     & 3.294489e-06\\\\\n",
-       "\tResiduals & 28           & 102556.3     &   3662.726   &       NA     &           NA\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "| <!--/--> | Df | Sum Sq | Mean Sq | F value | Pr(>F) | \n",
-       "|---|---|\n",
-       "| hardness |  1           | 122455.0     | 122455.037   | 33.43276     | 3.294489e-06 | \n",
-       "| Residuals | 28           | 102556.3     |   3662.726   |       NA     |           NA | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "          Df Sum Sq   Mean Sq    F value  Pr(>F)      \n",
-       "hardness   1 122455.0 122455.037 33.43276 3.294489e-06\n",
-       "Residuals 28 102556.3   3662.726       NA           NA"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "          Df   Sum Sq    Mean Sq  F value       Pr(>F)   PctExp\n",
-      "hardness   1 122455.0 122455.037 33.43276 3.294489e-06 54.42171\n",
-      "Residuals 28 102556.3   3662.726       NA           NA 45.57829\n"
-     ]
-    }
-   ],
-   "source": [
-    "fit <- lm(loss ~ hardness, data = rubber)\n",
-    "summary(fit)\n",
-    "anova(fit)\n",
-    "af <- anova(fit)\n",
-    "afss <- af$\"Sum Sq\"\n",
-    "print(cbind(af,PctExp=afss/sum(afss)*100))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "solution": "shown",
-    "solution2": "hidden",
-    "solution2_first": true,
-    "solution_first": true
-   },
-   "source": [
-    "### Exercise 5.1\n",
-    "Now repeat the for the regression of abrasion loss on tensile strength.\n",
-    "\n",
-    "Enter your solution in the cell below."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Your solution here"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "heading_collapsed": true
-   },
-   "source": [
-    "### Solution"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "hidden": true,
-    "solution2": "hidden"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\n",
-       "Call:\n",
-       "lm(formula = loss ~ strength, data = rubber)\n",
-       "\n",
-       "Residuals:\n",
-       "     Min       1Q   Median       3Q      Max \n",
-       "-155.640  -59.919    2.795   61.221  183.285 \n",
-       "\n",
-       "Coefficients:\n",
-       "            Estimate Std. Error t value Pr(>|t|)    \n",
-       "(Intercept) 305.2248    79.9962   3.815 0.000688 ***\n",
-       "strength     -0.7192     0.4347  -1.654 0.109232    \n",
-       "---\n",
-       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
-       "\n",
-       "Residual standard error: 85.56 on 28 degrees of freedom\n",
-       "Multiple R-squared:  0.08904,\tAdjusted R-squared:  0.0565 \n",
-       "F-statistic: 2.737 on 1 and 28 DF,  p-value: 0.1092\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th></th><th scope=col>Df</th><th scope=col>Sum Sq</th><th scope=col>Mean Sq</th><th scope=col>F value</th><th scope=col>Pr(&gt;F)</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><th scope=row>strength</th><td> 1       </td><td> 20034.77</td><td>20034.772</td><td>2.736769 </td><td>0.1092317</td></tr>\n",
-       "\t<tr><th scope=row>Residuals</th><td>28       </td><td>204976.59</td><td> 7320.593</td><td>      NA </td><td>       NA</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lllll}\n",
-       "  & Df & Sum Sq & Mean Sq & F value & Pr(>F)\\\\\n",
-       "\\hline\n",
-       "\tstrength &  1        &  20034.77 & 20034.772 & 2.736769  & 0.1092317\\\\\n",
-       "\tResiduals & 28        & 204976.59 &  7320.593 &       NA  &        NA\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "| <!--/--> | Df | Sum Sq | Mean Sq | F value | Pr(>F) | \n",
-       "|---|---|\n",
-       "| strength |  1        |  20034.77 | 20034.772 | 2.736769  | 0.1092317 | \n",
-       "| Residuals | 28        | 204976.59 |  7320.593 |       NA  |        NA | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "          Df Sum Sq    Mean Sq   F value  Pr(>F)   \n",
-       "strength   1  20034.77 20034.772 2.736769 0.1092317\n",
-       "Residuals 28 204976.59  7320.593       NA        NA"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "          Df    Sum Sq   Mean Sq  F value    Pr(>F)    PctExp\n",
-      "strength   1  20034.77 20034.772 2.736769 0.1092317  8.903893\n",
-      "Residuals 28 204976.59  7320.593       NA        NA 91.096107\n"
-     ]
-    }
-   ],
-   "source": [
-    "fit <- lm(loss ~ strength, data = rubber)\n",
-    "summary(fit)\n",
-    "anova(fit)\n",
-    "af <- anova(fit)\n",
-    "afss <- af$\"Sum Sq\"\n",
-    "print(cbind(af,PctExp=afss/sum(afss)*100))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "hidden": true,
-    "solution2": "hidden"
-   },
-   "source": [
-    "Individually, then, regression of abrasion loss on hardness seems satisfactory, albeit accounting for a disappointingly small percentage of the variance in the response; regression of abrasion loss on tensile strength,  on the other hand, seems to have very little explanatory power. "
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "solution": "hidden"
-   },
-   "source": [
-    "### Multiple regression\n",
-    "However, back in Exercise 3.19 it was shown that the residuals from the former regression showed a clear relationship with the tensile strength values, and this suggested that a regression model involving both variables is necessary. \n",
-    "\n",
-    "Let us try it. The only change is to include `strength` in the equations being fitted in the `lm()` function. Instead of \n",
-    "\n",
-    "```\n",
-    "lm(loss ~ hardness, data = rubber)\n",
-    "```\n",
-    "use \n",
-    "```\n",
-    "lm(loss ~ hardness + strength, data = rubber)\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\n",
-       "Call:\n",
-       "lm(formula = loss ~ hardness + strength, data = rubber)\n",
-       "\n",
-       "Residuals:\n",
-       "    Min      1Q  Median      3Q     Max \n",
-       "-79.385 -14.608   3.816  19.755  65.981 \n",
-       "\n",
-       "Coefficients:\n",
-       "            Estimate Std. Error t value Pr(>|t|)    \n",
-       "(Intercept) 885.1611    61.7516  14.334 3.84e-14 ***\n",
-       "hardness     -6.5708     0.5832 -11.267 1.03e-11 ***\n",
-       "strength     -1.3743     0.1943  -7.073 1.32e-07 ***\n",
-       "---\n",
-       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
-       "\n",
-       "Residual standard error: 36.49 on 27 degrees of freedom\n",
-       "Multiple R-squared:  0.8402,\tAdjusted R-squared:  0.8284 \n",
-       "F-statistic:    71 on 2 and 27 DF,  p-value: 1.767e-11\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th></th><th scope=col>Df</th><th scope=col>Sum Sq</th><th scope=col>Mean Sq</th><th scope=col>F value</th><th scope=col>Pr(&gt;F)</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><th scope=row>hardness</th><td> 1          </td><td>122455.04   </td><td>122455.037  </td><td>91.96967    </td><td>3.458255e-10</td></tr>\n",
-       "\t<tr><th scope=row>strength</th><td> 1          </td><td> 66606.59   </td><td> 66606.586  </td><td>50.02477    </td><td>1.324645e-07</td></tr>\n",
-       "\t<tr><th scope=row>Residuals</th><td>27          </td><td> 35949.74   </td><td>  1331.472  </td><td>      NA    </td><td>          NA</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lllll}\n",
-       "  & Df & Sum Sq & Mean Sq & F value & Pr(>F)\\\\\n",
-       "\\hline\n",
-       "\thardness &  1           & 122455.04    & 122455.037   & 91.96967     & 3.458255e-10\\\\\n",
-       "\tstrength &  1           &  66606.59    &  66606.586   & 50.02477     & 1.324645e-07\\\\\n",
-       "\tResiduals & 27           &  35949.74    &   1331.472   &       NA     &           NA\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "| <!--/--> | Df | Sum Sq | Mean Sq | F value | Pr(>F) | \n",
-       "|---|---|---|\n",
-       "| hardness |  1           | 122455.04    | 122455.037   | 91.96967     | 3.458255e-10 | \n",
-       "| strength |  1           |  66606.59    |  66606.586   | 50.02477     | 1.324645e-07 | \n",
-       "| Residuals | 27           |  35949.74    |   1331.472   |       NA     |           NA | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "          Df Sum Sq    Mean Sq    F value  Pr(>F)      \n",
-       "hardness   1 122455.04 122455.037 91.96967 3.458255e-10\n",
-       "strength   1  66606.59  66606.586 50.02477 1.324645e-07\n",
-       "Residuals 27  35949.74   1331.472       NA           NA"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "          Df    Sum Sq    Mean Sq  F value       Pr(>F)   PctExp\n",
-      "hardness   1 122455.04 122455.037 91.96967 3.458255e-10 54.42171\n",
-      "strength   1  66606.59  66606.586 50.02477 1.324645e-07 29.60143\n",
-      "Residuals 27  35949.74   1331.472       NA           NA 15.97686\n"
-     ]
-    }
-   ],
-   "source": [
-    "fit <- lm(loss ~ hardness + strength, data = rubber)\n",
-    "summary(fit)\n",
-    "anova(fit)\n",
-    "af <- anova(fit)\n",
-    "afss <- af$\"Sum Sq\"\n",
-    "print(cbind(af,PctExp=afss/sum(afss)*100))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Looking at the regression coefficient output next, the estimated model for the mean response is\n",
-    "\n",
-    "$$ \\hat{y} = \\hat{\\alpha} + \\hat{\\beta}_1 x_1 + \\hat{\\beta}_2 x_2 = 885.2 − 6.571 x_1 − 1.374 x_2 $$ \n",
-    "\n",
-    "where $x_1$ and $x_2$ stand for values of hardness and tensile strength, respectively. \n",
-    "\n",
-    "Associated with each estimated parameter, GenStat gives a standard error (details of the calculation of which need not concern us now) and hence a _t_-statistic (estimate divided by standard error) to be compared with the distribution on `d.f. (Residual)`=27 degrees of freedom. GenStat makes the comparison and gives _p_ values, which in this case are all very small, suggesting strong evidence for the non-zeroness (and hence presence) of each parameter, $\\alpha$, $\\beta_1$ and $\\beta_2$, individually."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "So, even though the single regression of abrasion loss on tensile strength did not suggest a close relationship, when taken in conjunction with the effect of hardness the effect of tensile strength is also a considerable one. A key idea here is that $\\beta_1$ and $\\beta_2$ (and more generally $\\beta_1, \\beta_2, \\ldots , \\beta_k$ in model (5.1)) are partial regression coefficients. That is, $\\beta_1$ measures the effect of an increase of one unit in $x_1$ treating the value of the other variable $x_2$ as fixed. Contrast this with the single regression model $E(Y) = \\alpha + \\beta_1 x_1$ in which $\\beta_1$ represents an increase of one unit in $x_1$ treating $x_2$ as zero. The meaning of $\\beta_1$ in the regression models with one and two explanatory variables is not the same.\n",
-    "\n",
-    "You will notice that the percentage of variance accounted for has increased dramatically in the two-explanatory-variable model to a much more respectable 82.8%. This statistic has the same interpretation — or difficulty of interpretation — as for the case of one explanatory variable (see [Unit 3](unit3.ipynb)).\n",
-    "\n",
-    "Other items in the GenStat output are as for the case of one explanatory variable: the `Standard error of observations` is $\\hat{\\sigma}$, and is the square root of `m.s. (Residual)`; the message about standardised residuals will be clarified below; and the message about leverage will be ignored until [Unit 10](unit10.ipynb).\n",
-    "\n",
-    "The simple residuals are, again, defined as the differences between the observed and predicted responses:\n",
-    "\n",
-    "$$ r_i = y_i - \\left( \\hat{\\alpha} + \\sum_{j=1}^{k} \\hat{\\beta}_j x_{i, j} \\right) ,\\ i = 1, 2, \\ldots, n. $$\n",
-    "\n",
-    "GenStat can obtain these for you and produce a plot of residuals against fitted values. The fitted values are simply $\\hat{Y}_i = \\hat{\\alpha} + \\sum_{j=1}^{k} \\hat{\\beta}_j x_{i, j}$. As in the regression models in [Unit 3](unit3.ipynb), the default in GenStat is to use deviance residuals which, in this context, are equivalent to standardised residuals (simple residuals divided by their estimated standard errors)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Gratuitous example of more complex maths markup\n",
-    "If \n",
-    "\n",
-    "$$ \\rho(z) = \\rho_c \\exp \\left( - \\frac{z^2}{2H^2} \\right) $$\n",
-    "\n",
-    "then\n",
-    "\n",
-    "\\begin{eqnarray*}\n",
-    "\\frac{\\partial \\rho(z)}{\\partial z} & = & \\rho_c \\frac{\\partial}{\\partial z}\\exp \n",
-    "                 \\left( - \\frac{z^2}{2H^2} \\right) \\\\\n",
-    "\t& = & \\rho_c \\exp \\left( - \\frac{z^2}{2H^2} \\right) \\cdot \n",
-    "\t             \\frac{\\partial}{\\partial z}  \\left( - \\frac{z^2}{2H^2} \\right) \\\\\n",
-    "\t& = &  \\rho_c \\exp \\left( - \\frac{z^2}{2H^2} \\right) \\cdot \n",
-    "\t             - \\frac{z}{H^2} \\\\\n",
-    "\t& = & - \\frac{z}{H^2} \\rho(z) \n",
-    "\\end{eqnarray*}"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Example 5.2\n",
-    "Something about plots of residuals..."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {},
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtAAAALQCAIAAAA2NdDLAAAACXBIWXMAABJ0AAASdAHeZh94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\nRK5CYII=",
-      "text/plain": [
-       "plot without title"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "fit <- lm(loss ~ hardness + strength, data = rubber)\n",
-    "autoplot(fit, label.size = 3)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "These plots are of just the same sort as those in [Unit 3](unit3.ipynb), and are interpreted in the same way. In this case, the normal plot and histogram show some slight suggestion of skewness in the residuals, but there is no obvious cause to doubt the model. In the regression output, GenStat flagged one of the points (number 19) as having a large standardised (i.e. deviance) residual. To decide which points to flag in this way, GenStat uses the same rules as described in [Units 3](unit3.ipynb) and [4](unit4.ipynb). In this case, it warned us about the most negative residual. However, the value of this standardised residual is not very large (at −2.38), and the plot of residuals against fitted values in Figure 5.2 makes it clear that this particular residual is not exceptionally large relative to some of the others, which are almost as large."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Exercise 5.2\n",
-    "The table below shows values for the first five datapoints, of 13, of a dataset concerned with predicting the heat evolved when cement sets via knowledge of its constituents. There are two explanatory variables, tricalcium aluminate (TA) and tricalcium silicate (TS), and the response variable is the heat generated in calories per gram (heat).\n",
-    "\n",
-    "heat | TA |  TS\n",
-    "-----|----|-----\n",
-    "78.5 |  7 | 26\n",
-    "74.3 |  1 | 29\n",
-    "104.3 |  11 |  56\n",
-    "87.6 |  11 |  31\n",
-    "95.9 |  7 | 52\n",
-    " $\\vdots$ | $\\vdots$ | $\\vdots$\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "a. Load the `cemheat` dataset.\n",
-    "\n",
-    "b. Make scatterplots of heat against each of TA and TS in turn, and comment on what you see.\n",
-    "\n",
-    "c. Use GenStat to fit each individual regression equation (of heat on TA and of heat on TS) in turn, and then to fit the regression equation with two explanatory variables. Does the latter regression equation give you a better model than either of the individual ones?\n",
-    "\n",
-    "d. According to the regression equation with two explanatory variables fitted in part (b), what is the predicted value of heat when TA = 15 and TS = 55?\n",
-    "\n",
-    "e. By looking at the (default) composite residual plots, comment on the appropriateness of the fitted regression model."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th scope=col>heat</th><th scope=col>TA</th><th scope=col>TS</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><td> 78.5</td><td> 7   </td><td>26   </td></tr>\n",
-       "\t<tr><td> 74.3</td><td> 1   </td><td>29   </td></tr>\n",
-       "\t<tr><td>104.3</td><td>11   </td><td>56   </td></tr>\n",
-       "\t<tr><td> 87.6</td><td>11   </td><td>31   </td></tr>\n",
-       "\t<tr><td> 95.9</td><td> 7   </td><td>52   </td></tr>\n",
-       "\t<tr><td>109.2</td><td>11   </td><td>55   </td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lll}\n",
-       " heat & TA & TS\\\\\n",
-       "\\hline\n",
-       "\t  78.5 &  7    & 26   \\\\\n",
-       "\t  74.3 &  1    & 29   \\\\\n",
-       "\t 104.3 & 11    & 56   \\\\\n",
-       "\t  87.6 & 11    & 31   \\\\\n",
-       "\t  95.9 &  7    & 52   \\\\\n",
-       "\t 109.2 & 11    & 55   \\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "heat | TA | TS | \n",
-       "|---|---|---|---|---|---|\n",
-       "|  78.5 |  7    | 26    | \n",
-       "|  74.3 |  1    | 29    | \n",
-       "| 104.3 | 11    | 56    | \n",
-       "|  87.6 | 11    | 31    | \n",
-       "|  95.9 |  7    | 52    | \n",
-       "| 109.2 | 11    | 55    | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "  heat  TA TS\n",
-       "1  78.5  7 26\n",
-       "2  74.3  1 29\n",
-       "3 104.3 11 56\n",
-       "4  87.6 11 31\n",
-       "5  95.9  7 52\n",
-       "6 109.2 11 55"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "cemheat <- read.csv('cemheat.csv')\n",
-    "head(cemheat)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtAAAAHgCAMAAAC7G6qeAAAC+lBMVEUAAAABAQECAgIDAwME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\nEBqEiv8H6pHUZe6MJNUAAAAASUVORK5CYII=",
-      "text/plain": [
-       "plot without title"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "taheat <- ggplot(cemheat, aes(x=TA, y=heat)) + geom_point()\n",
-    "tsheat <-  ggplot(cemheat, aes(x=TS, y=heat)) + geom_point()\n",
-    "\n",
-    "# plot_grid(hardloss, strloss, labels = \"AUTO\")\n",
-    "\n",
-    "options(repr.plot.width=6, repr.plot.height=4)\n",
-    "multiplot(taheat, tsheat, cols=2)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\n",
-       "Call:\n",
-       "lm(formula = heat ~ TA, data = cemheat)\n",
-       "\n",
-       "Residuals:\n",
-       "    Min      1Q  Median      3Q     Max \n",
-       "-16.061  -9.048   1.339   7.883  15.614 \n",
-       "\n",
-       "Coefficients:\n",
-       "            Estimate Std. Error t value Pr(>|t|)    \n",
-       "(Intercept)  81.4793     4.9273   16.54 4.07e-09 ***\n",
-       "TA            1.8687     0.5264    3.55  0.00455 ** \n",
-       "---\n",
-       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
-       "\n",
-       "Residual standard error: 10.73 on 11 degrees of freedom\n",
-       "Multiple R-squared:  0.5339,\tAdjusted R-squared:  0.4916 \n",
-       "F-statistic:  12.6 on 1 and 11 DF,  p-value: 0.004552\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th></th><th scope=col>Df</th><th scope=col>Sum Sq</th><th scope=col>Mean Sq</th><th scope=col>F value</th><th scope=col>Pr(&gt;F)</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><th scope=row>TA</th><td> 1         </td><td>1450.076   </td><td>1450.0763  </td><td>12.60252   </td><td>0.004552045</td></tr>\n",
-       "\t<tr><th scope=row>Residuals</th><td>11         </td><td>1265.687   </td><td> 115.0624  </td><td>      NA   </td><td>         NA</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lllll}\n",
-       "  & Df & Sum Sq & Mean Sq & F value & Pr(>F)\\\\\n",
-       "\\hline\n",
-       "\tTA &  1          & 1450.076    & 1450.0763   & 12.60252    & 0.004552045\\\\\n",
-       "\tResiduals & 11          & 1265.687    &  115.0624   &       NA    &          NA\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "| <!--/--> | Df | Sum Sq | Mean Sq | F value | Pr(>F) | \n",
-       "|---|---|\n",
-       "| TA |  1          | 1450.076    | 1450.0763   | 12.60252    | 0.004552045 | \n",
-       "| Residuals | 11          | 1265.687    |  115.0624   |       NA    |          NA | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "          Df Sum Sq   Mean Sq   F value  Pr(>F)     \n",
-       "TA         1 1450.076 1450.0763 12.60252 0.004552045\n",
-       "Residuals 11 1265.687  115.0624       NA          NA"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "          Df   Sum Sq   Mean Sq  F value      Pr(>F)  PctExp\n",
-      "TA         1 1450.076 1450.0763 12.60252 0.004552045 53.3948\n",
-      "Residuals 11 1265.687  115.0624       NA          NA 46.6052\n"
-     ]
-    }
-   ],
-   "source": [
-    "fit <- lm(heat ~ TA, data = cemheat)\n",
-    "summary(fit)\n",
-    "anova(fit)\n",
-    "af <- anova(fit)\n",
-    "afss <- af$\"Sum Sq\"\n",
-    "print(cbind(af,PctExp=afss/sum(afss)*100))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\n",
-       "Call:\n",
-       "lm(formula = heat ~ TS, data = cemheat)\n",
-       "\n",
-       "Residuals:\n",
-       "    Min      1Q  Median      3Q     Max \n",
-       "-10.752  -6.008  -1.684   3.794  21.387 \n",
-       "\n",
-       "Coefficients:\n",
-       "            Estimate Std. Error t value Pr(>|t|)    \n",
-       "(Intercept)  57.4237     8.4906   6.763  3.1e-05 ***\n",
-       "TS            0.7891     0.1684   4.686 0.000665 ***\n",
-       "---\n",
-       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
-       "\n",
-       "Residual standard error: 9.077 on 11 degrees of freedom\n",
-       "Multiple R-squared:  0.6663,\tAdjusted R-squared:  0.6359 \n",
-       "F-statistic: 21.96 on 1 and 11 DF,  p-value: 0.0006648\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th></th><th scope=col>Df</th><th scope=col>Sum Sq</th><th scope=col>Mean Sq</th><th scope=col>F value</th><th scope=col>Pr(&gt;F)</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><th scope=row>TS</th><td> 1          </td><td>1809.4267   </td><td>1809.42673  </td><td>21.9606     </td><td>0.0006648249</td></tr>\n",
-       "\t<tr><th scope=row>Residuals</th><td>11          </td><td> 906.3363   </td><td>  82.39421  </td><td>     NA     </td><td>          NA</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lllll}\n",
-       "  & Df & Sum Sq & Mean Sq & F value & Pr(>F)\\\\\n",
-       "\\hline\n",
-       "\tTS &  1           & 1809.4267    & 1809.42673   & 21.9606      & 0.0006648249\\\\\n",
-       "\tResiduals & 11           &  906.3363    &   82.39421   &      NA      &           NA\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "| <!--/--> | Df | Sum Sq | Mean Sq | F value | Pr(>F) | \n",
-       "|---|---|\n",
-       "| TS |  1           | 1809.4267    | 1809.42673   | 21.9606      | 0.0006648249 | \n",
-       "| Residuals | 11           |  906.3363    |   82.39421   |      NA      |           NA | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "          Df Sum Sq    Mean Sq    F value Pr(>F)      \n",
-       "TS         1 1809.4267 1809.42673 21.9606 0.0006648249\n",
-       "Residuals 11  906.3363   82.39421      NA           NA"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "          Df    Sum Sq    Mean Sq F value       Pr(>F)   PctExp\n",
-      "TS         1 1809.4267 1809.42673 21.9606 0.0006648249 66.62683\n",
-      "Residuals 11  906.3363   82.39421      NA           NA 33.37317\n"
-     ]
-    }
-   ],
-   "source": [
-    "fit <- lm(heat ~ TS, data = cemheat)\n",
-    "summary(fit)\n",
-    "anova(fit)\n",
-    "af <- anova(fit)\n",
-    "afss <- af$\"Sum Sq\"\n",
-    "print(cbind(af,PctExp=afss/sum(afss)*100))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\n",
-       "Call:\n",
-       "lm(formula = heat ~ TA + TS, data = cemheat)\n",
-       "\n",
-       "Residuals:\n",
-       "   Min     1Q Median     3Q    Max \n",
-       "-2.893 -1.574 -1.302  1.363  4.048 \n",
-       "\n",
-       "Coefficients:\n",
-       "            Estimate Std. Error t value Pr(>|t|)    \n",
-       "(Intercept) 52.57735    2.28617   23.00 5.46e-10 ***\n",
-       "TA           1.46831    0.12130   12.11 2.69e-07 ***\n",
-       "TS           0.66225    0.04585   14.44 5.03e-08 ***\n",
-       "---\n",
-       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
-       "\n",
-       "Residual standard error: 2.406 on 10 degrees of freedom\n",
-       "Multiple R-squared:  0.9787,\tAdjusted R-squared:  0.9744 \n",
-       "F-statistic: 229.5 on 2 and 10 DF,  p-value: 4.407e-09\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th></th><th scope=col>Df</th><th scope=col>Sum Sq</th><th scope=col>Mean Sq</th><th scope=col>F value</th><th scope=col>Pr(&gt;F)</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><th scope=row>TA</th><td> 1          </td><td>1450.07633  </td><td>1450.076328 </td><td>250.4256    </td><td>2.088092e-08</td></tr>\n",
-       "\t<tr><th scope=row>TS</th><td> 1          </td><td>1207.78227  </td><td>1207.782266 </td><td>208.5818    </td><td>5.028960e-08</td></tr>\n",
-       "\t<tr><th scope=row>Residuals</th><td>10          </td><td>  57.90448  </td><td>   5.790448 </td><td>      NA    </td><td>          NA</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lllll}\n",
-       "  & Df & Sum Sq & Mean Sq & F value & Pr(>F)\\\\\n",
-       "\\hline\n",
-       "\tTA &  1           & 1450.07633   & 1450.076328  & 250.4256     & 2.088092e-08\\\\\n",
-       "\tTS &  1           & 1207.78227   & 1207.782266  & 208.5818     & 5.028960e-08\\\\\n",
-       "\tResiduals & 10           &   57.90448   &    5.790448  &       NA     &           NA\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "| <!--/--> | Df | Sum Sq | Mean Sq | F value | Pr(>F) | \n",
-       "|---|---|---|\n",
-       "| TA |  1           | 1450.07633   | 1450.076328  | 250.4256     | 2.088092e-08 | \n",
-       "| TS |  1           | 1207.78227   | 1207.782266  | 208.5818     | 5.028960e-08 | \n",
-       "| Residuals | 10           |   57.90448   |    5.790448  |       NA     |           NA | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "          Df Sum Sq     Mean Sq     F value  Pr(>F)      \n",
-       "TA         1 1450.07633 1450.076328 250.4256 2.088092e-08\n",
-       "TS         1 1207.78227 1207.782266 208.5818 5.028960e-08\n",
-       "Residuals 10   57.90448    5.790448       NA           NA"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "          Df     Sum Sq     Mean Sq  F value       Pr(>F)    PctExp\n",
-      "TA         1 1450.07633 1450.076328 250.4256 2.088092e-08 53.394802\n",
-      "TS         1 1207.78227 1207.782266 208.5818 5.028960e-08 44.473035\n",
-      "Residuals 10   57.90448    5.790448       NA           NA  2.132163\n"
-     ]
-    }
-   ],
-   "source": [
-    "fit <- lm(heat ~ TA + TS, data = cemheat)\n",
-    "summary(fit)\n",
-    "anova(fit)\n",
-    "af <- anova(fit)\n",
-    "afss <- af$\"Sum Sq\"\n",
-    "print(cbind(af,PctExp=afss/sum(afss)*100))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<strong>1:</strong> 111.025712035428"
-      ],
-      "text/latex": [
-       "\\textbf{1:} 111.025712035428"
-      ],
-      "text/markdown": [
-       "**1:** 111.025712035428"
-      ],
-      "text/plain": [
-       "       1 \n",
-       "111.0257 "
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "predict(fit, data.frame(\"TA\" = 15, \"TS\" = 55))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Exercise 5.3: Fitting a quadratic regression model\n",
-    "In Unit 3, the dataset `anaerob` was briefly considered (Example 3.1) and swiftly dismissed as a candidate for simple linear regression modelling. The reason is clear from the figure below, in which the response variable, expired ventilation ($y$), is plotted against the single explanatory variable, oxygen uptake ($x$). (The same plot appeared as Figure 3.1 in Example 3.1.) A model quadratic in $x$, i.e. $E(Y) = \\alpha + \\beta x + \\gamma x^2$, was suggested instead."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {},
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtAAAAHgCAMAAAC7G6qeAAADAFBMVEUAAAABAQECAgIDAwME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\nzC8txQAAAABJRU5ErkJggg==",
-      "text/plain": [
-       "plot without title"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "anaerobic <- read.csv('anaerob.csv')\n",
-    "ggplot(anaerobic, aes(x=oxygen, y=ventil)) + geom_point()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Since this quadratic model is nonetheless linear in its parameters, we can fit it using multiple regression of $y$ on $x$ plus the new variable $x^2$. Even though $x_1 = x$ and $x_2 = x^2$ are closely related, there is no immediate impediment to forgetting this and regressing on them in the usual way. A variable such as $x_2$ is sometimes called a derived variable.\n",
-    "\n",
-    "a. Using GenStat, perform the regression of expired ventilation (`ventil`) on oxygen uptake (`oxygen`). Are you at all surprised by how good this regression model seems?\n",
-    "\n",
-    "b. Now form a new variable `oxy2`, say, by squaring oxygen. (Create a new column in the `anearobic` dataframe which is `anaerobic$oxygen ^ 2`.) Perform the regression of ventil on `oxygen` and `oxy2`. Comment on the fit of this model according to the printed output (and with recourse to Figure 3.2 in Example 3.1).\n",
-    "\n",
-    "c. Make the usual residual plots and comment on the fit of the model again."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\n",
-       "Call:\n",
-       "lm(formula = ventil ~ oxygen, data = anaerobic)\n",
-       "\n",
-       "Residuals:\n",
-       "    Min      1Q  Median      3Q     Max \n",
-       "-15.502  -9.716  -3.391   7.881  26.446 \n",
-       "\n",
-       "Coefficients:\n",
-       "              Estimate Std. Error t value Pr(>|t|)    \n",
-       "(Intercept) -18.448734   3.815196  -4.836 1.26e-05 ***\n",
-       "oxygen        0.031141   0.001355  22.987  < 2e-16 ***\n",
-       "---\n",
-       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
-       "\n",
-       "Residual standard error: 11.96 on 51 degrees of freedom\n",
-       "Multiple R-squared:  0.912,\tAdjusted R-squared:  0.9103 \n",
-       "F-statistic: 528.4 on 1 and 51 DF,  p-value: < 2.2e-16\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th></th><th scope=col>Df</th><th scope=col>Sum Sq</th><th scope=col>Mean Sq</th><th scope=col>F value</th><th scope=col>Pr(&gt;F)</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><th scope=row>oxygen</th><td> 1          </td><td>75555.216   </td><td>75555.2158  </td><td>528.403     </td><td>1.419964e-28</td></tr>\n",
-       "\t<tr><th scope=row>Residuals</th><td>51          </td><td> 7292.381   </td><td>  142.9879  </td><td>     NA     </td><td>          NA</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lllll}\n",
-       "  & Df & Sum Sq & Mean Sq & F value & Pr(>F)\\\\\n",
-       "\\hline\n",
-       "\toxygen &  1           & 75555.216    & 75555.2158   & 528.403      & 1.419964e-28\\\\\n",
-       "\tResiduals & 51           &  7292.381    &   142.9879   &      NA      &           NA\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "| <!--/--> | Df | Sum Sq | Mean Sq | F value | Pr(>F) | \n",
-       "|---|---|\n",
-       "| oxygen |  1           | 75555.216    | 75555.2158   | 528.403      | 1.419964e-28 | \n",
-       "| Residuals | 51           |  7292.381    |   142.9879   |      NA      |           NA | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "          Df Sum Sq    Mean Sq    F value Pr(>F)      \n",
-       "oxygen     1 75555.216 75555.2158 528.403 1.419964e-28\n",
-       "Residuals 51  7292.381   142.9879      NA           NA"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "          Df    Sum Sq    Mean Sq F value       Pr(>F)    PctExp\n",
-      "oxygen     1 75555.216 75555.2158 528.403 1.419964e-28 91.197836\n",
-      "Residuals 51  7292.381   142.9879      NA           NA  8.802164\n"
-     ]
-    }
-   ],
-   "source": [
-    "fit <- lm(ventil ~ oxygen, data = anaerobic)\n",
-    "summary(fit)\n",
-    "anova(fit)\n",
-    "af <- anova(fit)\n",
-    "afss <- af$\"Sum Sq\"\n",
-    "print(cbind(af,PctExp=afss/sum(afss)*100))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {},
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtAAAAHgCAIAAAADp837AAAACXBIWXMAABJ0AAASdAHeZh94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\nYII=",
-      "text/plain": [
-       "plot without title"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "layout(matrix(1:4,2,2)) \n",
-    "autoplot(fit)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th scope=col>ventil</th><th scope=col>oxygen</th><th scope=col>oxy2</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><td>21.9  </td><td>574   </td><td>329476</td></tr>\n",
-       "\t<tr><td>18.6  </td><td>592   </td><td>350464</td></tr>\n",
-       "\t<tr><td>18.6  </td><td>664   </td><td>440896</td></tr>\n",
-       "\t<tr><td>19.1  </td><td>667   </td><td>444889</td></tr>\n",
-       "\t<tr><td>19.2  </td><td>718   </td><td>515524</td></tr>\n",
-       "\t<tr><td>16.9  </td><td>770   </td><td>592900</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lll}\n",
-       " ventil & oxygen & oxy2\\\\\n",
-       "\\hline\n",
-       "\t 21.9   & 574    & 329476\\\\\n",
-       "\t 18.6   & 592    & 350464\\\\\n",
-       "\t 18.6   & 664    & 440896\\\\\n",
-       "\t 19.1   & 667    & 444889\\\\\n",
-       "\t 19.2   & 718    & 515524\\\\\n",
-       "\t 16.9   & 770    & 592900\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "ventil | oxygen | oxy2 | \n",
-       "|---|---|---|---|---|---|\n",
-       "| 21.9   | 574    | 329476 | \n",
-       "| 18.6   | 592    | 350464 | \n",
-       "| 18.6   | 664    | 440896 | \n",
-       "| 19.1   | 667    | 444889 | \n",
-       "| 19.2   | 718    | 515524 | \n",
-       "| 16.9   | 770    | 592900 | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "  ventil oxygen oxy2  \n",
-       "1 21.9   574    329476\n",
-       "2 18.6   592    350464\n",
-       "3 18.6   664    440896\n",
-       "4 19.1   667    444889\n",
-       "5 19.2   718    515524\n",
-       "6 16.9   770    592900"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "anaerobic$oxy2 <- anaerobic$oxygen^2\n",
-    "head(anaerobic)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\n",
-       "Call:\n",
-       "lm(formula = ventil ~ oxygen + oxy2, data = anaerobic)\n",
-       "\n",
-       "Residuals:\n",
-       "    Min      1Q  Median      3Q     Max \n",
-       "-9.4713 -1.3675 -0.4201  2.1925  7.7817 \n",
-       "\n",
-       "Coefficients:\n",
-       "              Estimate Std. Error t value Pr(>|t|)    \n",
-       "(Intercept)  2.427e+01  1.940e+00  12.509  < 2e-16 ***\n",
-       "oxygen      -1.344e-02  1.762e-03  -7.628 6.27e-10 ***\n",
-       "oxy2         8.902e-06  3.444e-07  25.850  < 2e-16 ***\n",
-       "---\n",
-       "Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1\n",
-       "\n",
-       "Residual standard error: 3.186 on 50 degrees of freedom\n",
-       "Multiple R-squared:  0.9939,\tAdjusted R-squared:  0.9936 \n",
-       "F-statistic:  4055 on 2 and 50 DF,  p-value: < 2.2e-16\n"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "text/html": [
-       "<table>\n",
-       "<thead><tr><th></th><th scope=col>Df</th><th scope=col>Sum Sq</th><th scope=col>Mean Sq</th><th scope=col>F value</th><th scope=col>Pr(&gt;F)</th></tr></thead>\n",
-       "<tbody>\n",
-       "\t<tr><th scope=row>oxygen</th><td> 1          </td><td>75555.2158  </td><td>75555.21580 </td><td>7441.5695   </td><td>4.587875e-56</td></tr>\n",
-       "\t<tr><th scope=row>oxy2</th><td> 1          </td><td> 6784.7247  </td><td> 6784.72473 </td><td> 668.2398   </td><td>1.357823e-30</td></tr>\n",
-       "\t<tr><th scope=row>Residuals</th><td>50          </td><td>  507.6565  </td><td>   10.15313 </td><td>       NA   </td><td>          NA</td></tr>\n",
-       "</tbody>\n",
-       "</table>\n"
-      ],
-      "text/latex": [
-       "\\begin{tabular}{r|lllll}\n",
-       "  & Df & Sum Sq & Mean Sq & F value & Pr(>F)\\\\\n",
-       "\\hline\n",
-       "\toxygen &  1           & 75555.2158   & 75555.21580  & 7441.5695    & 4.587875e-56\\\\\n",
-       "\toxy2 &  1           &  6784.7247   &  6784.72473  &  668.2398    & 1.357823e-30\\\\\n",
-       "\tResiduals & 50           &   507.6565   &    10.15313  &        NA    &           NA\\\\\n",
-       "\\end{tabular}\n"
-      ],
-      "text/markdown": [
-       "\n",
-       "| <!--/--> | Df | Sum Sq | Mean Sq | F value | Pr(>F) | \n",
-       "|---|---|---|\n",
-       "| oxygen |  1           | 75555.2158   | 75555.21580  | 7441.5695    | 4.587875e-56 | \n",
-       "| oxy2 |  1           |  6784.7247   |  6784.72473  |  668.2398    | 1.357823e-30 | \n",
-       "| Residuals | 50           |   507.6565   |    10.15313  |        NA    |           NA | \n",
-       "\n",
-       "\n"
-      ],
-      "text/plain": [
-       "          Df Sum Sq     Mean Sq     F value   Pr(>F)      \n",
-       "oxygen     1 75555.2158 75555.21580 7441.5695 4.587875e-56\n",
-       "oxy2       1  6784.7247  6784.72473  668.2398 1.357823e-30\n",
-       "Residuals 50   507.6565    10.15313        NA           NA"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "          Df     Sum Sq     Mean Sq   F value       Pr(>F)     PctExp\n",
-      "oxygen     1 75555.2158 75555.21580 7441.5695 4.587875e-56 91.1978362\n",
-      "oxy2       1  6784.7247  6784.72473  668.2398 1.357823e-30  8.1894044\n",
-      "Residuals 50   507.6565    10.15313        NA           NA  0.6127594\n"
-     ]
-    }
-   ],
-   "source": [
-    "fit <- lm(ventil ~ oxygen + oxy2, data = anaerobic)\n",
-    "summary(fit)\n",
-    "anova(fit)\n",
-    "af <- anova(fit)\n",
-    "afss <- af$\"Sum Sq\"\n",
-    "print(cbind(af,PctExp=afss/sum(afss)*100))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {},
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtAAAAHgCAIAAAADp837AAAACXBIWXMAABJ0AAASdAHeZh94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",
-      "text/plain": [
-       "plot without title"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "layout(matrix(1:4,2,2)) \n",
-    "autoplot(fit)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "R",
-   "language": "R",
-   "name": "ir"
-  },
-  "language_info": {
-   "codemirror_mode": "r",
-   "file_extension": ".r",
-   "mimetype": "text/x-r-source",
-   "name": "R",
-   "pygments_lexer": "r",
-   "version": "3.4.2"
-  },
-  "toc": {
-   "nav_menu": {},
-   "number_sections": true,
-   "sideBar": true,
-   "skip_h1_title": false,
-   "title_cell": "Table of Contents",
-   "title_sidebar": "Contents",
-   "toc_cell": false,
-   "toc_position": {
-    "height": "calc(100% - 180px)",
-    "left": "10px",
-    "top": "150px",
-    "width": "342px"
-   },
-   "toc_section_display": true,
-   "toc_window_display": true
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/.ipynb_checkpoints/unit10-checkpoint.ipynb b/.ipynb_checkpoints/unit10-checkpoint.ipynb

deleted file mode 100644 (file)

index 92dea90..0000000
--- a/.ipynb_checkpoints/unit10-checkpoint.ipynb
+++ /dev/null
@@ -1,39 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Unit 10\n",
-    "\n",
-    "Sample text for unit 10 goes here\n",
-    "\n",
-    "Back to [section 5.1](section5.1.ipynb)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "R",
-   "language": "R",
-   "name": "ir"
-  },
-  "language_info": {
-   "codemirror_mode": "r",
-   "file_extension": ".r",
-   "mimetype": "text/x-r-source",
-   "name": "R",
-   "pygments_lexer": "r",
-   "version": "3.4.2"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/.ipynb_checkpoints/unit3-checkpoint.ipynb b/.ipynb_checkpoints/unit3-checkpoint.ipynb

deleted file mode 100644 (file)

index 2fd6442..0000000
--- a/.ipynb_checkpoints/unit3-checkpoint.ipynb
+++ /dev/null
@@ -1,6 +0,0 @@
-{
- "cells": [],
- "metadata": {},
- "nbformat": 4,
- "nbformat_minor": 2
-}
author	Neil Smith <neil.git@njae.me.uk>
	Thu, 22 Feb 2018 16:29:49 +0000 (16:29 +0000)
committer	Neil Smith <neil.git@njae.me.uk>
	Thu, 22 Feb 2018 16:29:49 +0000 (16:29 +0000)
.gitignore	[new file with mode: 0644]	patch \| blob
.ipynb_checkpoints/accidents-regression-checkpoint.ipynb	[deleted file]	patch \| blob \| history
.ipynb_checkpoints/section5.1-checkpoint.ipynb	[deleted file]	patch \| blob \| history
.ipynb_checkpoints/section5.1solutions-checkpoint.ipynb	[deleted file]	patch \| blob \| history
.ipynb_checkpoints/unit10-checkpoint.ipynb	[deleted file]	patch \| blob \| history
.ipynb_checkpoints/unit3-checkpoint.ipynb	[deleted file]	patch \| blob \| history