{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": false }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Warning message:\n", "“package ‘xlsx’ was built under R version 3.6.3”" ] } ], "source": [ "library(xlsx) # library to import excel spreadsheets as data to analyze" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "# Importing the dataset\n", "df.data <- read.xlsx(\"ANOVA Practice Data File.xlsx\", sheetName = 1)" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\t\n", "\t\n", "\n", "\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\n", "
A data.frame: 18 × 4
IDExperience.LevelBlurriness.LevelThroughput
<dbl><fct><fct><dbl>
1No Experience Not Blurred 1.314
2No Experience Not Blurred 1.219
3Moderate Experience Not Blurred 4.413
4Moderate Experience Not Blurred 4.612
5Extensive ExperienceNot Blurred 4.752
6Extensive ExperienceNot Blurred 4.432
7No Experience Moderately Blurred 1.114
8No Experience Moderately Blurred 1.119
9Moderate Experience Moderately Blurred 2.113
10Moderate Experience Moderately Blurred 2.235
11Extensive ExperienceModerately Blurred 4.443
12Extensive ExperienceModerately Blurred 4.512
13No Experience Extensively Blurred0.295
14No Experience Extensively Blurred0.113
15Moderate Experience Extensively Blurred0.443
16Moderate Experience Extensively Blurred0.452
17Extensive ExperienceExtensively Blurred2.113
18Extensive ExperienceExtensively Blurred2.211
\n" ], "text/latex": [ "A data.frame: 18 × 4\n", "\\begin{tabular}{llll}\n", " ID & Experience.Level & Blurriness.Level & Throughput\\\\\n", " & & & \\\\\n", "\\hline\n", "\t 1 & No Experience & Not Blurred & 1.314\\\\\n", "\t 2 & No Experience & Not Blurred & 1.219\\\\\n", "\t 3 & Moderate Experience & Not Blurred & 4.413\\\\\n", "\t 4 & Moderate Experience & Not Blurred & 4.612\\\\\n", "\t 5 & Extensive Experience & Not Blurred & 4.752\\\\\n", "\t 6 & Extensive Experience & Not Blurred & 4.432\\\\\n", "\t 7 & No Experience & Moderately Blurred & 1.114\\\\\n", "\t 8 & No Experience & Moderately Blurred & 1.119\\\\\n", "\t 9 & Moderate Experience & Moderately Blurred & 2.113\\\\\n", "\t 10 & Moderate Experience & Moderately Blurred & 2.235\\\\\n", "\t 11 & Extensive Experience & Moderately Blurred & 4.443\\\\\n", "\t 12 & Extensive Experience & Moderately Blurred & 4.512\\\\\n", "\t 13 & No Experience & Extensively Blurred & 0.295\\\\\n", "\t 14 & No Experience & Extensively Blurred & 0.113\\\\\n", "\t 15 & Moderate Experience & Extensively Blurred & 0.443\\\\\n", "\t 16 & Moderate Experience & Extensively Blurred & 0.452\\\\\n", "\t 17 & Extensive Experience & Extensively Blurred & 2.113\\\\\n", "\t 18 & Extensive Experience & Extensively Blurred & 2.211\\\\\n", "\\end{tabular}\n" ], "text/markdown": [ "\n", "A data.frame: 18 × 4\n", "\n", "| ID <dbl> | Experience.Level <fct> | Blurriness.Level <fct> | Throughput <dbl> |\n", "|---|---|---|---|\n", "| 1 | No Experience | Not Blurred | 1.314 |\n", "| 2 | No Experience | Not Blurred | 1.219 |\n", "| 3 | Moderate Experience | Not Blurred | 4.413 |\n", "| 4 | Moderate Experience | Not Blurred | 4.612 |\n", "| 5 | Extensive Experience | Not Blurred | 4.752 |\n", "| 6 | Extensive Experience | Not Blurred | 4.432 |\n", "| 7 | No Experience | Moderately Blurred | 1.114 |\n", "| 8 | No Experience | Moderately Blurred | 1.119 |\n", "| 9 | Moderate Experience | Moderately Blurred | 2.113 |\n", "| 10 | Moderate Experience | Moderately Blurred | 2.235 |\n", "| 11 | Extensive Experience | Moderately Blurred | 4.443 |\n", "| 12 | Extensive Experience | Moderately Blurred | 4.512 |\n", "| 13 | No Experience | Extensively Blurred | 0.295 |\n", "| 14 | No Experience | Extensively Blurred | 0.113 |\n", "| 15 | Moderate Experience | Extensively Blurred | 0.443 |\n", "| 16 | Moderate Experience | Extensively Blurred | 0.452 |\n", "| 17 | Extensive Experience | Extensively Blurred | 2.113 |\n", "| 18 | Extensive Experience | Extensively Blurred | 2.211 |\n", "\n" ], "text/plain": [ " ID Experience.Level Blurriness.Level Throughput\n", "1 1 No Experience Not Blurred 1.314 \n", "2 2 No Experience Not Blurred 1.219 \n", "3 3 Moderate Experience Not Blurred 4.413 \n", "4 4 Moderate Experience Not Blurred 4.612 \n", "5 5 Extensive Experience Not Blurred 4.752 \n", "6 6 Extensive Experience Not Blurred 4.432 \n", "7 7 No Experience Moderately Blurred 1.114 \n", "8 8 No Experience Moderately Blurred 1.119 \n", "9 9 Moderate Experience Moderately Blurred 2.113 \n", "10 10 Moderate Experience Moderately Blurred 2.235 \n", "11 11 Extensive Experience Moderately Blurred 4.443 \n", "12 12 Extensive Experience Moderately Blurred 4.512 \n", "13 13 No Experience Extensively Blurred 0.295 \n", "14 14 No Experience Extensively Blurred 0.113 \n", "15 15 Moderate Experience Extensively Blurred 0.443 \n", "16 16 Moderate Experience Extensively Blurred 0.452 \n", "17 17 Extensive Experience Extensively Blurred 2.113 \n", "18 18 Extensive Experience Extensively Blurred 2.211 " ] }, "execution_count": 10, "metadata": { }, "output_type": "execute_result" } ], "source": [ "# Checking whether the data frame imported correctly\n", "df.data" ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "collapsed": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "'data.frame':\t18 obs. of 4 variables:\n", " $ ID : num 1 2 3 4 5 6 7 8 9 10 ...\n", " $ Experience.Level: Factor w/ 3 levels \"Extensive Experience\",..: 3 3 2 2 1 1 3 3 2 2 ...\n", " $ Blurriness.Level: Factor w/ 3 levels \"Extensively Blurred\",..: 3 3 3 3 3 3 2 2 2 2 ...\n", " $ Throughput : Factor w/ 17 levels \"0.113\",\"0.295\",..: 8 7 12 16 17 13 5 6 9 11 ...\n" ] } ], "source": [ "# Checking the import results.'data.frame':\t18 obs. of 4 variables:\n", "str(df.data)" ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "# Throughput was recorded as a factor variable; In reality, it should be a numeric variable.\n", "# Hence, its data type needs to be changed to reflect this fact.\n", "df.data$Throughput <- as.numeric(as.character (df.data$Throughput))" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "collapsed": false }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Warning message:\n", "“package ‘ggplot2’ was built under R version 3.6.3”" ] } ], "source": [ "# Import the ggplot2 library to create graphs\n", "library(ggplot2)" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "plot without title" ] }, "execution_count": 12, "metadata": { }, "output_type": "execute_result" } ], "source": [ "# Plot the difference of means between experience levels\n", "ggplot(df.data, aes(x = Experience.Level, y = Throughput)) + geom_point()" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "collapsed": false }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "plot without title" ] }, "execution_count": 13, "metadata": { }, "output_type": "execute_result" } ], "source": [ "# Plot the difference of means between experience levels\n", "ggplot(df.data, aes(x = Blurriness.Level, y = Throughput)) + geom_point()" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "# First ANOVA, testing all factors and all interaction effects\n", "# There are three hypotheses we wish to test.\n", "# 1. Does experience affect one's annotation throughput?\n", "# 2. Does blurriness of the image being annotated affect one's annotation throughput?\n", "# 3. Does one's experience mitigate the effect of blurriness (i.e. are skilled annotators less slowed down by blurriness?)\n", "result <- aov(Throughput ~ Experience.Level + Blurriness.Level + Experience.Level*Blurriness.Level, data = df.data)" ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "result2 <- aov(Throughput ~ Experience.Level + Blurriness.Level + Experience.Level*Blurriness.Level, data = df.data)" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ " Df Sum Sq Mean Sq F value Pr(>F) \n", "Experience.Level 2 24.932 12.466 1051.0 2.16e-11 ***\n", "Blurriness.Level 2 19.653 9.826 828.4 6.26e-11 ***\n", "Experience.Level:Blurriness.Level 4 5.838 1.460 123.1 7.55e-08 ***\n", "Residuals 9 0.107 0.012 \n", "---\n", "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1" ] }, "execution_count": 15, "metadata": { }, "output_type": "execute_result" } ], "source": [ "# Check the results. What do you see?\n", "summary(result) " ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ " Df Sum Sq Mean Sq F value Pr(>F) \n", "Experience.Level 2 24.932 12.466 1051.0 2.16e-11 ***\n", "Blurriness.Level 2 19.653 9.826 828.4 6.26e-11 ***\n", "Experience.Level:Blurriness.Level 4 5.838 1.460 123.1 7.55e-08 ***\n", "Residuals 9 0.107 0.012 \n", "---\n", "Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1" ] }, "execution_count": 19, "metadata": { }, "output_type": "execute_result" } ], "source": [ "# Check the results for the new ANOVA. What do you see?\n", "summary(result2)" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ " Tukey multiple comparisons of means\n", " 95% family-wise confidence level\n", "\n", "Fit: aov(formula = Throughput ~ Experience.Level + Blurriness.Level + Experience.Level * Blurriness.Level, data = df.data)\n", "\n", "$Experience.Level\n", " diff lwr upr p adj\n", "Moderate Experience-Extensive Experience -1.365833 -1.541392 -1.190274 0\n", "No Experience-Extensive Experience -2.881500 -3.057059 -2.705941 0\n", "No Experience-Moderate Experience -1.515667 -1.691226 -1.340108 0\n", "\n", "$Blurriness.Level\n", " diff lwr upr p adj\n", "Moderately Blurred-Extensively Blurred 1.6515000 1.4759409 1.827059 0e+00\n", "Not Blurred-Extensively Blurred 2.5191667 2.3436075 2.694726 0e+00\n", "Not Blurred-Moderately Blurred 0.8676667 0.6921075 1.043226 6e-07\n", "\n", "$`Experience.Level:Blurriness.Level`\n", " diff\n", "Moderate Experience:Extensively Blurred-Extensive Experience:Extensively Blurred -1.7145\n", "No Experience:Extensively Blurred-Extensive Experience:Extensively Blurred -1.9580\n", "Extensive Experience:Moderately Blurred-Extensive Experience:Extensively Blurred 2.3155\n", "Moderate Experience:Moderately Blurred-Extensive Experience:Extensively Blurred 0.0120\n", "No Experience:Moderately Blurred-Extensive Experience:Extensively Blurred -1.0455\n", "Extensive Experience:Not Blurred-Extensive Experience:Extensively Blurred 2.4300\n", "Moderate Experience:Not Blurred-Extensive Experience:Extensively Blurred 2.3505\n", "No Experience:Not Blurred-Extensive Experience:Extensively Blurred -0.8955\n", "No Experience:Extensively Blurred-Moderate Experience:Extensively Blurred -0.2435\n", "Extensive Experience:Moderately Blurred-Moderate Experience:Extensively Blurred 4.0300\n", "Moderate Experience:Moderately Blurred-Moderate Experience:Extensively Blurred 1.7265\n", "No Experience:Moderately Blurred-Moderate Experience:Extensively Blurred 0.6690\n", "Extensive Experience:Not Blurred-Moderate Experience:Extensively Blurred 4.1445\n", "Moderate Experience:Not Blurred-Moderate Experience:Extensively Blurred 4.0650\n", "No Experience:Not Blurred-Moderate Experience:Extensively Blurred 0.8190\n", "Extensive Experience:Moderately Blurred-No Experience:Extensively Blurred 4.2735\n", "Moderate Experience:Moderately Blurred-No Experience:Extensively Blurred 1.9700\n", "No Experience:Moderately Blurred-No Experience:Extensively Blurred 0.9125\n", "Extensive Experience:Not Blurred-No Experience:Extensively Blurred 4.3880\n", "Moderate Experience:Not Blurred-No Experience:Extensively Blurred 4.3085\n", "No Experience:Not Blurred-No Experience:Extensively Blurred 1.0625\n", "Moderate Experience:Moderately Blurred-Extensive Experience:Moderately Blurred -2.3035\n", "No Experience:Moderately Blurred-Extensive Experience:Moderately Blurred -3.3610\n", "Extensive Experience:Not Blurred-Extensive Experience:Moderately Blurred 0.1145\n", "Moderate Experience:Not Blurred-Extensive Experience:Moderately Blurred 0.0350\n", "No Experience:Not Blurred-Extensive Experience:Moderately Blurred -3.2110\n", "No Experience:Moderately Blurred-Moderate Experience:Moderately Blurred -1.0575\n", "Extensive Experience:Not Blurred-Moderate Experience:Moderately Blurred 2.4180\n", "Moderate Experience:Not Blurred-Moderate Experience:Moderately Blurred 2.3385\n", "No Experience:Not Blurred-Moderate Experience:Moderately Blurred -0.9075\n", "Extensive Experience:Not Blurred-No Experience:Moderately Blurred 3.4755\n", "Moderate Experience:Not Blurred-No Experience:Moderately Blurred 3.3960\n", "No Experience:Not Blurred-No Experience:Moderately Blurred 0.1500\n", "Moderate Experience:Not Blurred-Extensive Experience:Not Blurred -0.0795\n", "No Experience:Not Blurred-Extensive Experience:Not Blurred -3.3255\n", "No Experience:Not Blurred-Moderate Experience:Not Blurred -3.2460\n", " lwr\n", "Moderate Experience:Extensively Blurred-Extensive Experience:Extensively Blurred -2.1453544\n", "No Experience:Extensively Blurred-Extensive Experience:Extensively Blurred -2.3888544\n", "Extensive Experience:Moderately Blurred-Extensive Experience:Extensively Blurred 1.8846456\n", "Moderate Experience:Moderately Blurred-Extensive Experience:Extensively Blurred -0.4188544\n", "No Experience:Moderately Blurred-Extensive Experience:Extensively Blurred -1.4763544\n", "Extensive Experience:Not Blurred-Extensive Experience:Extensively Blurred 1.9991456\n", "Moderate Experience:Not Blurred-Extensive Experience:Extensively Blurred 1.9196456\n", "No Experience:Not Blurred-Extensive Experience:Extensively Blurred -1.3263544\n", "No Experience:Extensively Blurred-Moderate Experience:Extensively Blurred -0.6743544\n", "Extensive Experience:Moderately Blurred-Moderate Experience:Extensively Blurred 3.5991456\n", "Moderate Experience:Moderately Blurred-Moderate Experience:Extensively Blurred 1.2956456\n", "No Experience:Moderately Blurred-Moderate Experience:Extensively Blurred 0.2381456\n", "Extensive Experience:Not Blurred-Moderate Experience:Extensively Blurred 3.7136456\n", "Moderate Experience:Not Blurred-Moderate Experience:Extensively Blurred 3.6341456\n", "No Experience:Not Blurred-Moderate Experience:Extensively Blurred 0.3881456\n", "Extensive Experience:Moderately Blurred-No Experience:Extensively Blurred 3.8426456\n", "Moderate Experience:Moderately Blurred-No Experience:Extensively Blurred 1.5391456\n", "No Experience:Moderately Blurred-No Experience:Extensively Blurred 0.4816456\n", "Extensive Experience:Not Blurred-No Experience:Extensively Blurred 3.9571456\n", "Moderate Experience:Not Blurred-No Experience:Extensively Blurred 3.8776456\n", "No Experience:Not Blurred-No Experience:Extensively Blurred 0.6316456\n", "Moderate Experience:Moderately Blurred-Extensive Experience:Moderately Blurred -2.7343544\n", "No Experience:Moderately Blurred-Extensive Experience:Moderately Blurred -3.7918544\n", "Extensive Experience:Not Blurred-Extensive Experience:Moderately Blurred -0.3163544\n", "Moderate Experience:Not Blurred-Extensive Experience:Moderately Blurred -0.3958544\n", "No Experience:Not Blurred-Extensive Experience:Moderately Blurred -3.6418544\n", "No Experience:Moderately Blurred-Moderate Experience:Moderately Blurred -1.4883544\n", "Extensive Experience:Not Blurred-Moderate Experience:Moderately Blurred 1.9871456\n", "Moderate Experience:Not Blurred-Moderate Experience:Moderately Blurred 1.9076456\n", "No Experience:Not Blurred-Moderate Experience:Moderately Blurred -1.3383544\n", "Extensive Experience:Not Blurred-No Experience:Moderately Blurred 3.0446456\n", "Moderate Experience:Not Blurred-No Experience:Moderately Blurred 2.9651456\n", "No Experience:Not Blurred-No Experience:Moderately Blurred -0.2808544\n", "Moderate Experience:Not Blurred-Extensive Experience:Not Blurred -0.5103544\n", "No Experience:Not Blurred-Extensive Experience:Not Blurred -3.7563544\n", "No Experience:Not Blurred-Moderate Experience:Not Blurred -3.6768544\n", " upr\n", "Moderate Experience:Extensively Blurred-Extensive Experience:Extensively Blurred -1.2836456\n", "No Experience:Extensively Blurred-Extensive Experience:Extensively Blurred -1.5271456\n", "Extensive Experience:Moderately Blurred-Extensive Experience:Extensively Blurred 2.7463544\n", "Moderate Experience:Moderately Blurred-Extensive Experience:Extensively Blurred 0.4428544\n", "No Experience:Moderately Blurred-Extensive Experience:Extensively Blurred -0.6146456\n", "Extensive Experience:Not Blurred-Extensive Experience:Extensively Blurred 2.8608544\n", "Moderate Experience:Not Blurred-Extensive Experience:Extensively Blurred 2.7813544\n", "No Experience:Not Blurred-Extensive Experience:Extensively Blurred -0.4646456\n", "No Experience:Extensively Blurred-Moderate Experience:Extensively Blurred 0.1873544\n", "Extensive Experience:Moderately Blurred-Moderate Experience:Extensively Blurred 4.4608544\n", "Moderate Experience:Moderately Blurred-Moderate Experience:Extensively Blurred 2.1573544\n", "No Experience:Moderately Blurred-Moderate Experience:Extensively Blurred 1.0998544\n", "Extensive Experience:Not Blurred-Moderate Experience:Extensively Blurred 4.5753544\n", "Moderate Experience:Not Blurred-Moderate Experience:Extensively Blurred 4.4958544\n", "No Experience:Not Blurred-Moderate Experience:Extensively Blurred 1.2498544\n", "Extensive Experience:Moderately Blurred-No Experience:Extensively Blurred 4.7043544\n", "Moderate Experience:Moderately Blurred-No Experience:Extensively Blurred 2.4008544\n", "No Experience:Moderately Blurred-No Experience:Extensively Blurred 1.3433544\n", "Extensive Experience:Not Blurred-No Experience:Extensively Blurred 4.8188544\n", "Moderate Experience:Not Blurred-No Experience:Extensively Blurred 4.7393544\n", "No Experience:Not Blurred-No Experience:Extensively Blurred 1.4933544\n", "Moderate Experience:Moderately Blurred-Extensive Experience:Moderately Blurred -1.8726456\n", "No Experience:Moderately Blurred-Extensive Experience:Moderately Blurred -2.9301456\n", "Extensive Experience:Not Blurred-Extensive Experience:Moderately Blurred 0.5453544\n", "Moderate Experience:Not Blurred-Extensive Experience:Moderately Blurred 0.4658544\n", "No Experience:Not Blurred-Extensive Experience:Moderately Blurred -2.7801456\n", "No Experience:Moderately Blurred-Moderate Experience:Moderately Blurred -0.6266456\n", "Extensive Experience:Not Blurred-Moderate Experience:Moderately Blurred 2.8488544\n", "Moderate Experience:Not Blurred-Moderate Experience:Moderately Blurred 2.7693544\n", "No Experience:Not Blurred-Moderate Experience:Moderately Blurred -0.4766456\n", "Extensive Experience:Not Blurred-No Experience:Moderately Blurred 3.9063544\n", "Moderate Experience:Not Blurred-No Experience:Moderately Blurred 3.8268544\n", "No Experience:Not Blurred-No Experience:Moderately Blurred 0.5808544\n", "Moderate Experience:Not Blurred-Extensive Experience:Not Blurred 0.3513544\n", "No Experience:Not Blurred-Extensive Experience:Not Blurred -2.8946456\n", "No Experience:Not Blurred-Moderate Experience:Not Blurred -2.8151456\n", " p adj\n", "Moderate Experience:Extensively Blurred-Extensive Experience:Extensively Blurred 0.0000016\n", "No Experience:Extensively Blurred-Extensive Experience:Extensively Blurred 0.0000005\n", "Extensive Experience:Moderately Blurred-Extensive Experience:Extensively Blurred 0.0000001\n", "Moderate Experience:Moderately Blurred-Extensive Experience:Extensively Blurred 1.0000000\n", "No Experience:Moderately Blurred-Extensive Experience:Extensively Blurred 0.0001005\n", "Extensive Experience:Not Blurred-Extensive Experience:Extensively Blurred 0.0000001\n", "Moderate Experience:Not Blurred-Extensive Experience:Extensively Blurred 0.0000001\n", "No Experience:Not Blurred-Extensive Experience:Extensively Blurred 0.0003473\n", "No Experience:Extensively Blurred-Moderate Experience:Extensively Blurred 0.4557486\n", "Extensive Experience:Moderately Blurred-Moderate Experience:Extensively Blurred 0.0000000\n", "Moderate Experience:Moderately Blurred-Moderate Experience:Extensively Blurred 0.0000015\n", "No Experience:Moderately Blurred-Moderate Experience:Extensively Blurred 0.0031144\n", "Extensive Experience:Not Blurred-Moderate Experience:Extensively Blurred 0.0000000\n", "Moderate Experience:Not Blurred-Moderate Experience:Extensively Blurred 0.0000000\n", "No Experience:Not Blurred-Moderate Experience:Extensively Blurred 0.0006952\n", "Extensive Experience:Moderately Blurred-No Experience:Extensively Blurred 0.0000000\n", "Moderate Experience:Moderately Blurred-No Experience:Extensively Blurred 0.0000005\n", "No Experience:Moderately Blurred-No Experience:Extensively Blurred 0.0002994\n", "Extensive Experience:Not Blurred-No Experience:Extensively Blurred 0.0000000\n", "Moderate Experience:Not Blurred-No Experience:Extensively Blurred 0.0000000\n", "No Experience:Not Blurred-No Experience:Extensively Blurred 0.0000881\n", "Moderate Experience:Moderately Blurred-Extensive Experience:Moderately Blurred 0.0000001\n", "No Experience:Moderately Blurred-Extensive Experience:Moderately Blurred 0.0000000\n", "Extensive Experience:Not Blurred-Extensive Experience:Moderately Blurred 0.9686083\n", "Moderate Experience:Not Blurred-Extensive Experience:Moderately Blurred 0.9999912\n", "No Experience:Not Blurred-Extensive Experience:Moderately Blurred 0.0000000\n", "No Experience:Moderately Blurred-Moderate Experience:Moderately Blurred 0.0000915\n", "Extensive Experience:Not Blurred-Moderate Experience:Moderately Blurred 0.0000001\n", "Moderate Experience:Not Blurred-Moderate Experience:Moderately Blurred 0.0000001\n", "No Experience:Not Blurred-Moderate Experience:Moderately Blurred 0.0003127\n", "Extensive Experience:Not Blurred-No Experience:Moderately Blurred 0.0000000\n", "Moderate Experience:Not Blurred-No Experience:Moderately Blurred 0.0000000\n", "No Experience:Not Blurred-No Experience:Moderately Blurred 0.8815911\n", "Moderate Experience:Not Blurred-Extensive Experience:Not Blurred 0.9965769\n", "No Experience:Not Blurred-Extensive Experience:Not Blurred 0.0000000\n", "No Experience:Not Blurred-Moderate Experience:Not Blurred 0.0000000\n" ] }, "execution_count": 20, "metadata": { }, "output_type": "execute_result" } ], "source": [ "# Remember that ANOVA by itself doesn't give information about which classes have higher or lower means\n", "# To gain that information, an additional test (Tukey's )\n", "TukeyHSD(result2)" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ "# Extracting residuals from the ANOVA results\n", "df.data$residuals2 <- result2$residuals" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/plain": [ "\n", "\tShapiro-Wilk normality test\n", "\n", "data: df.data$residuals2\n", "W = 0.99231, p-value = 0.9998\n" ] }, "execution_count": 22, "metadata": { }, "output_type": "execute_result" } ], "source": [ "# Performing a normality test on the residuals\n", "shapiro.test(df.data$residuals2)" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "collapsed": false }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Warning message:\n", "“package ‘car’ was built under R version 3.6.3”" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Loading required package: carData\n" ] }, { "data": { "text/html": [ "\n", "\n", "\n", "\t\n", "\t\n", "\n", "\n", "\t\n", "\t\n", "\n", "
A anova: 2 × 3
DfF valuePr(>F)
<int><dbl><dbl>
group 20.80236090.4666029
15 NA NA
\n" ], "text/latex": [ "A anova: 2 × 3\n", "\\begin{tabular}{r|lll}\n", " & Df & F value & Pr(>F)\\\\\n", " & & & \\\\\n", "\\hline\n", "\tgroup & 2 & 0.8023609 & 0.4666029\\\\\n", "\t & 15 & NA & NA\\\\\n", "\\end{tabular}\n" ], "text/markdown": [ "\n", "A anova: 2 × 3\n", "\n", "| | Df <int> | F value <dbl> | Pr(>F) <dbl> |\n", "|---|---|---|---|\n", "| group | 2 | 0.8023609 | 0.4666029 |\n", "| | 15 | NA | NA |\n", "\n" ], "text/plain": [ " Df F value Pr(>F) \n", "group 2 0.8023609 0.4666029\n", " 15 NA NA" ] }, "execution_count": 24, "metadata": { }, "output_type": "execute_result" } ], "source": [ "# Performing a homoscedasticity test on the residuals for blurriness level\n", "library(car)\n", "leveneTest(residuals2 ~ Experience.Level, data = df.data)" ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "collapsed": false }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\t\n", "\t\n", "\n", "\n", "\t\n", "\t\n", "\n", "
A anova: 2 × 3
DfF valuePr(>F)
<int><dbl><dbl>
group 25.1030150.02038925
15 NA NA
\n" ], "text/latex": [ "A anova: 2 × 3\n", "\\begin{tabular}{r|lll}\n", " & Df & F value & Pr(>F)\\\\\n", " & & & \\\\\n", "\\hline\n", "\tgroup & 2 & 5.103015 & 0.02038925\\\\\n", "\t & 15 & NA & NA\\\\\n", "\\end{tabular}\n" ], "text/markdown": [ "\n", "A anova: 2 × 3\n", "\n", "| | Df <int> | F value <dbl> | Pr(>F) <dbl> |\n", "|---|---|---|---|\n", "| group | 2 | 5.103015 | 0.02038925 |\n", "| | 15 | NA | NA |\n", "\n" ], "text/plain": [ " Df F value Pr(>F) \n", "group 2 5.103015 0.02038925\n", " 15 NA NA" ] }, "execution_count": 25, "metadata": { }, "output_type": "execute_result" } ], "source": [ "#Performing a homoscedasticity test on the residuals for blurriness level\n", "leveneTest(residuals2 ~ Blurriness.Level, data = df.data)" ] }, { "cell_type": "code", "execution_count": 0, "metadata": { "collapsed": false }, "outputs": [ ], "source": [ ] } ], "metadata": { "kernelspec": { "display_name": "R (R-Project)", "language": "r", "metadata": { "cocalc": { "description": "R statistical programming language", "priority": 10, "url": "https://www.r-project.org/" } }, "name": "ir" }, "language_info": { "codemirror_mode": "r", "file_extension": ".r", "mimetype": "text/x-r-source", "name": "R", "pygments_lexer": "r", "version": "3.6.1" } }, "nbformat": 4, "nbformat_minor": 4 }