Merge branch 'master' of https://github.com/UBC-STAT/stat-301

UBC-STAT · Jul 7, 2024 · a424534 · a424534
2 parents 5509b80 + 7fec519
commit a424534
Show file tree

Hide file tree

Showing 8 changed files with 38,606 additions and 0 deletions.
diff --git a/lectures/live-coding/data/milk-fat-train.csv b/lectures/live-coding/data/milk-fat-train.csv
@@ -0,0 +1,26 @@
+week,fat
+11,0.72
+12,0.68
+13,0.65
+14,0.64
+15,0.57
+16,0.48
+17,0.46
+18,0.45
+19,0.31
+20,0.33
+21,0.36
+22,0.3
+23,0.26
+24,0.34
+25,0.29
+26,0.31
+27,0.29
+28,0.2
+29,0.15
+30,0.18
+31,0.11
+32,0.07
+33,0.06
+34,0.01
+35,0.01
diff --git a/lectures/live-coding/data/milk-fat-true.csv b/lectures/live-coding/data/milk-fat-true.csv
@@ -0,0 +1,11 @@
+week,fat
+1,0.31
+2,0.39
+3,0.5
+4,0.58
+5,0.59
+6,0.64
+7,0.68
+8,0.66
+9,0.67
+10,0.7
diff --git a/lectures/live-coding/lecture02-demo.ipynb b/lectures/live-coding/lecture02-demo.ipynb
@@ -0,0 +1,316 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 68,
+   "id": "8e8a5403-1079-49aa-8063-cb244bb6eabb",
+   "metadata": {
+    "tags": [],
+    "vscode": {
+     "languageId": "r"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "library(tidyverse)\n",
+    "library(palmerpenguins)\n",
+    "library(broom)\n",
+    "library(modelr)\n",
+    "\n",
+    "options(repr.plot.width = 10, repr.plot.height = 5) "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f5c616aa-c4ea-4be3-916d-e4663056e601",
+   "metadata": {},
+   "source": [
+    "# Linear Regression Model\n",
+    "**Lecture 2 - Demo**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8181e27f-9fdd-4501-8227-c742f18177fd",
+   "metadata": {
+    "tags": [],
+    "vscode": {
+     "languageId": "r"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<table class=\"dataframe\">\n",
+       "<caption>A tibble: 5 × 7</caption>\n",
+       "<thead>\n",
+       "\t<tr><th scope=col>species</th><th scope=col>island</th><th scope=col>bill_length_mm</th><th scope=col>bill_depth_mm</th><th scope=col>flipper_length_mm</th><th scope=col>body_mass_g</th><th scope=col>sex</th></tr>\n",
+       "\t<tr><th scope=col>&lt;fct&gt;</th><th scope=col>&lt;fct&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;dbl&gt;</th><th scope=col>&lt;int&gt;</th><th scope=col>&lt;int&gt;</th><th scope=col>&lt;fct&gt;</th></tr>\n",
+       "</thead>\n",
+       "<tbody>\n",
+       "\t<tr><td>Adelie   </td><td>Dream </td><td>41.5</td><td>18.5</td><td>201</td><td>4000</td><td>male  </td></tr>\n",
+       "\t<tr><td>Gentoo   </td><td>Biscoe</td><td>45.0</td><td>15.4</td><td>220</td><td>5050</td><td>male  </td></tr>\n",
+       "\t<tr><td>Gentoo   </td><td>Biscoe</td><td>48.5</td><td>14.1</td><td>220</td><td>5300</td><td>male  </td></tr>\n",
+       "\t<tr><td>Chinstrap</td><td>Dream </td><td>50.3</td><td>20.0</td><td>197</td><td>3300</td><td>male  </td></tr>\n",
+       "\t<tr><td>Chinstrap</td><td>Dream </td><td>45.7</td><td>17.0</td><td>195</td><td>3650</td><td>female</td></tr>\n",
+       "</tbody>\n",
+       "</table>\n"
+      ],
+      "text/latex": [
+       "A tibble: 5 × 7\n",
+       "\\begin{tabular}{lllllll}\n",
+       " species & island & bill\\_length\\_mm & bill\\_depth\\_mm & flipper\\_length\\_mm & body\\_mass\\_g & sex\\\\\n",
+       " <fct> & <fct> & <dbl> & <dbl> & <int> & <int> & <fct>\\\\\n",
+       "\\hline\n",
+       "\t Adelie    & Dream  & 41.5 & 18.5 & 201 & 4000 & male  \\\\\n",
+       "\t Gentoo    & Biscoe & 45.0 & 15.4 & 220 & 5050 & male  \\\\\n",
+       "\t Gentoo    & Biscoe & 48.5 & 14.1 & 220 & 5300 & male  \\\\\n",
+       "\t Chinstrap & Dream  & 50.3 & 20.0 & 197 & 3300 & male  \\\\\n",
+       "\t Chinstrap & Dream  & 45.7 & 17.0 & 195 & 3650 & female\\\\\n",
+       "\\end{tabular}\n"
+      ],
+      "text/markdown": [
+       "\n",
+       "A tibble: 5 × 7\n",
+       "\n",
+       "| species &lt;fct&gt; | island &lt;fct&gt; | bill_length_mm &lt;dbl&gt; | bill_depth_mm &lt;dbl&gt; | flipper_length_mm &lt;int&gt; | body_mass_g &lt;int&gt; | sex &lt;fct&gt; |\n",
+       "|---|---|---|---|---|---|---|\n",
+       "| Adelie    | Dream  | 41.5 | 18.5 | 201 | 4000 | male   |\n",
+       "| Gentoo    | Biscoe | 45.0 | 15.4 | 220 | 5050 | male   |\n",
+       "| Gentoo    | Biscoe | 48.5 | 14.1 | 220 | 5300 | male   |\n",
+       "| Chinstrap | Dream  | 50.3 | 20.0 | 197 | 3300 | male   |\n",
+       "| Chinstrap | Dream  | 45.7 | 17.0 | 195 | 3650 | female |\n",
+       "\n"
+      ],
+      "text/plain": [
+       "  species   island bill_length_mm bill_depth_mm flipper_length_mm body_mass_g\n",
+       "1 Adelie    Dream  41.5           18.5          201               4000       \n",
+       "2 Gentoo    Biscoe 45.0           15.4          220               5050       \n",
+       "3 Gentoo    Biscoe 48.5           14.1          220               5300       \n",
+       "4 Chinstrap Dream  50.3           20.0          197               3300       \n",
+       "5 Chinstrap Dream  45.7           17.0          195               3650       \n",
+       "  sex   \n",
+       "1 male  \n",
+       "2 male  \n",
+       "3 male  \n",
+       "4 male  \n",
+       "5 female"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "penguins_clean <-\n",
+    "    penguins %>%\n",
+    "    drop_na() %>%\n",
+    "    select(-year)\n",
+    "\n",
+    "penguins_clean %>%\n",
+    "    slice_sample(n = 5)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "40a2fde9-b2db-4fcf-999b-4585c75f5f5b",
+   "metadata": {},
+   "source": [
+    "## 1. **One Binary Covariate**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c82b1db7-9a74-4976-83f8-c85169f98e35",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "### 1.1 **What the model looks like**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8a40c2ac-d389-45c8-8825-ecd80c4cab44",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "15a094ea-d0ad-421d-bcf0-113a97d638e9",
+   "metadata": {},
+   "source": [
+    "#### 1.1.1 **Dummy Variables**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f36ab118-e5b9-48df-b697-489afe2b78dc",
+   "metadata": {},
+   "source": [
+    "### 1.2 **Fitting using R**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c0fdb706-15c2-4871-9198-c3d2f2857f37",
+   "metadata": {},
+   "source": [
+    "### 1.3 **Equivalent to t-test from STAT 201**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "89b40ac1-f9f6-4728-a20c-07360837fd02",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "## 2. **Categorical covariate with more than 2 categories**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2fef3c0d-f90e-4f3c-b594-f179da1ccba5",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "### 2.1 **What the model looks like**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "97901247-9cbc-4abe-a438-da9554035c80",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e6f0eec5-f58f-42ae-9397-003536a00823",
+   "metadata": {},
+   "source": [
+    "#### 2.1.1 **Dummy Variables**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "60b7b0fe-a14a-419b-94e2-59595fc0b54d",
+   "metadata": {
+    "vscode": {
+     "languageId": "r"
+    }
+   },
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "afb602ac-8cc7-4e25-87a8-34ebc45d7278",
+   "metadata": {},
+   "source": [
+    "### 2.2 **Fitting using R**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e3b1301f-b04e-437f-a1fc-633358771e26",
+   "metadata": {},
+   "source": [
+    "### 2.3 Difference in means?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "73db7e2c-c6b4-4cca-928c-f9d3ac804ed4",
+   "metadata": {},
+   "source": [
+    "## 3. One Categorical and One Numerical "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "22b43d4e-33da-4311-9216-cb6d527f7944",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "### 3.1 **What the model looks like**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7e56be67-9118-4315-a458-a52c953dc424",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1aeee946-ce28-4cdb-8494-9da851c810de",
+   "metadata": {},
+   "source": [
+    "### 3.2 **Fitting using R**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "650a6531-7f9e-485b-a6eb-68676f0e0708",
+   "metadata": {},
+   "source": [
+    "In this model, the difference in the means between the groups do not depend on the `flipper_length_mm`."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2f2cc1c1-0538-4481-be8f-a60d4767dabc",
+   "metadata": {},
+   "source": [
+    "## 4. **MLR with interaction**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "221224d5-c144-4afb-93e9-3a9a0cc5ee39",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "### 4.1 **What the model looks like**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "81bcd409-3ebe-433a-93d5-e1e15fdb2535",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6b0371d2-0d89-4f9b-bfe0-a6c0d2357b5a",
+   "metadata": {},
+   "source": [
+    "### 4.2 **Fitting using R**"
+   ]
+  }
+ ],
+ "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": "4.2.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}