Project 2 work week 2 material updated.

.gitignore

@@ -10,4 +10,13 @@
 *.log
 *.vrb
 *.snm
+*.fdb_latexmk
 .Rhistory
+.latex.json
+beamer.cls
+*.pdf
+*.bbl
+*.blg
+lectureDraftArchives/
+lecture_1_classroom_survey.csv
+lecture_1_survey_data_clean.csv

Chp 2/2-1_numerical_data/figures/gpa_dot_plot/gpa.R

@@ -24,6 +24,19 @@ polygon(M + c(-2,2,0)*0.01, c(0.25, 0.25, 0.5), border=COL[4], col=COL[4])
 
 dev.off()
 
+# with median
+
+myPDF('gpa_dot_plot_median.pdf', 7, 1.5, mar=c(4,0.5,0.5,0.5), cex.lab = 1.5, cex.axis = 1.25)
+
+openintro::dotPlot(gpa, pch = 19, col = COL[1,4], xlab = "GPA", xlim = c(2.5,4), ylab = "")
+M <- mean(d$gpa[d$gpa <= 4], na.rm = TRUE)
+polygon(M + c(-2,2,0)*0.01, c(0.25, 0.25, 0.5), border=COL[7], col=COL[7])
+Med <- median(d$gpa[d$gpa <= 4], na.rm = TRUE)
+polygon(Med + c(-2,2,0)*0.01, c(0.25, 0.25, 0.5), border=COL[4], col=COL[4])
+
+dev.off()
+
+
 # stacked
 
 

Chp 2/2-1_numerical_data/figures/house_income/house_income.R

@@ -5,6 +5,10 @@ d = read.csv("house_income.csv")
 
 house_income = d$house_income[!is.na(d$house_income) & d$house_income < 4000000]
 
+# Sort the cleaned house_income vector and save as a new CSV
+house_income_sorted <- sort(house_income)
+write.csv(data.frame(house_income = house_income_sorted), file = "house_income_sorted.csv", row.names = FALSE)
+
 
 myPDF('house_income_dot_stacked.pdf', 7, 3, mar=c(4,2,0.5,0.5), cex.lab = 1.5, cex.axis = 1.25)
 

Chp 5/5-1_point_est_sampling_var/5-1_point_est_sampling_var.tex

@@ -1,6 +1,6 @@
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 
-\section{Point estimates and sampling variability}
+\section{Point estimates and sampling variability!!!}
 
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 
@@ -52,9 +52,9 @@ \subsection{Understanding the variability of a point estimate}
 \frametitle{}
 
 \begin{center}
-\includegraphics[width=0.95\textwidth]{5-1_point_est_sampling_var/figures/pew/pew1} \\
-\includegraphics[width=0.95\textwidth]{5-1_point_est_sampling_var/figures/pew/pew2} \\
-\includegraphics[width=0.95\textwidth]{5-1_point_est_sampling_var/figures/pew/pew3}
+\includegraphics[width=0.95\textwidth]{\chp5@path/5-1_point_est_sampling_var/figures/pew/pew1} \\
+\includegraphics[width=0.95\textwidth]{\chp5@path/5-1_point_est_sampling_var/figures/pew/pew2} \\
+\includegraphics[width=0.95\textwidth]{\chp5@path/5-1_point_est_sampling_var/figures/pew/pew3}
 \end{center}
 
 \ct{\webURL{http://pewresearch.org/pubs/2191/young-adults-workers-labor-market-pay-careers-advancement-recession}}
@@ -67,7 +67,7 @@ \subsection{Understanding the variability of a point estimate}
 \frametitle{Margin of error}
 
 \begin{center}
-\includegraphics[width=0.95\textwidth]{5-1_point_est_sampling_var/figures/pew/pew4}
+\includegraphics[width=0.95\textwidth]{\chp5@path/5-1_point_est_sampling_var/figures/pew/pew4}
 \end{center}
 
 \begin{itemize}
@@ -157,7 +157,7 @@ \subsection{Application exercise}
 Suppose you were to repeat this process many times and obtain many $\hat{p}$s. This distribution is called a \hl{sampling distribution}.
 
 \begin{center}
-\includegraphics[width=0.6\textwidth]{5-1_point_est_sampling_var/figures/solar-power/solar-power-sampling.pdf}
+\includegraphics[width=0.6\textwidth]{\chp5@path/5-1_point_est_sampling_var/figures/solar-power/solar-power-sampling.pdf}
 \end{center}
 
 \end{frame}
@@ -170,7 +170,7 @@ \subsection{Application exercise}
 \dq{What is the shape and center of this distribution? Based on this distribution, what do you think is the true population proportion?}
 
 \begin{center}
-\includegraphics[width=0.6\textwidth]{5-1_point_est_sampling_var/figures/solar-power/solar-power-sampling.pdf}
+\includegraphics[width=0.6\textwidth]{\chp5@path/5-1_point_est_sampling_var/figures/solar-power/solar-power-sampling.pdf}
 \end{center}
 
 $\:$ \\
@@ -282,7 +282,7 @@ \subsection{More details regarding the Central Limit Theorem}
 
 \soln{No, the success-failure condition is not met ($50 * 0.05 = 2.5$), hence we would not expect the sampling distribution to be nearly normal.
 \begin{center}
-\includegraphics[width=0.55\textwidth]{5-1_point_est_sampling_var/figures/sf/low-p.pdf}
+\includegraphics[width=0.55\textwidth]{\chp5@path/5-1_point_est_sampling_var/figures/sf/low-p.pdf}
 \end{center}
 }
 
@@ -295,8 +295,8 @@ \subsection{More details regarding the Central Limit Theorem}
 \dq{What happens when $np$ and/or $n(1-p)$ $<$ 10?}
 
 \begin{center}
-\includegraphics[width=0.45\textwidth]{5-1_point_est_sampling_var/figures/clt_prop_grid/clt_prop_grid_1.pdf}
-\includegraphics[width=0.45\textwidth]{5-1_point_est_sampling_var/figures/clt_prop_grid/clt_prop_grid_2.pdf}
+\includegraphics[width=0.45\textwidth]{\chp5@path/5-1_point_est_sampling_var/figures/clt_prop_grid/clt_prop_grid_1.pdf}
+\includegraphics[width=0.45\textwidth]{\chp5@path/5-1_point_est_sampling_var/figures/clt_prop_grid/clt_prop_grid_2.pdf}
 \end{center}
 
 \end{frame}

Chp 5/5-2_ci_prop/5-2_ci_prop.tex

@@ -20,13 +20,13 @@ \subsection{Capturing the population parameter}
 $\:$ \\
 \begin{columns}[c]
 \column{0.25\textwidth}
-\includegraphics[width=\textwidth]{5-2_ci_prop/figures/spear}
+\includegraphics[width=\textwidth]{\chp5@path/5-2_ci_prop/figures/spear}
 \column{0.5\textwidth}
 {\small
 We can throw a spear where we saw a fish but we will probably miss. If we toss a net in that area, we have a good chance of catching the fish.
 }
 \column{0.25\textwidth}
-\includegraphics[width=\textwidth]{5-2_ci_prop/figures/net}
+\includegraphics[width=\textwidth]{\chp5@path/5-2_ci_prop/figures/net}
 \end{columns}
 $\:$ \\
 \item If we report a point estimate, we probably won't hit the exact population parameter. If we report a range of plausible values we have a good shot at capturing the parameter. 
@@ -135,7 +135,7 @@ \subsection{Constructing a 95\% confidence interval}
 
 \dq{Can you see any drawbacks to using a wider interval?}
 \begin{center}
-\includegraphics[width=0.9\textwidth]{5-2_ci_prop/figures/garfield}
+\includegraphics[width=0.9\textwidth]{\chp5@path/5-2_ci_prop/figures/garfield}
 \end{center}
 
 \pause
@@ -192,7 +192,7 @@ \subsection{Changing the confidence level}
 
 \soln{\only<2>{
 \begin{center}
-\includegraphics[width=0.7\textwidth]{5-2_ci_prop/figures/middle98/middle98}
+\includegraphics[width=0.7\textwidth]{\chp5@path/5-2_ci_prop/figures/middle98/middle98}
 \end{center}
 }}
 

Chp 5/5-3_ht_prop/5-3_ht_prop.tex

@@ -47,7 +47,7 @@ \subsection{Hypothesis testing framework}
 \frametitle{Result}
 
 \begin{center}
-\includegraphics[width=0.75\textwidth]{5-3_ht_prop/figures/discRandDotPlot/discRandDotPlot}
+\includegraphics[width=0.75\textwidth]{\chp5@path/5-3_ht_prop/figures/discRandDotPlot/discRandDotPlot}
 \end{center}
 
 \pause

Chp 5/chp5.tex

@@ -7,6 +7,7 @@
 \documentclass[t,compress,mathserif]{beamer}
 \newcommand{\soln}[1]{\textit{#1}}
 \newcommand{\solnGr}[1]{#1}
+\def\chp5@path{.}
 
 % Option 2: Handouts without solutions
 
@@ -66,9 +67,9 @@
 % Sections
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
 
-\input{5-1_point_est_sampling_var/5-1_point_est_sampling_var}
-\input{5-2_ci_prop/5-2_ci_prop}
-\input{5-3_ht_prop/5-3_ht_prop}
+\input{\chp5@path/5-1_point_est_sampling_var/5-1_point_est_sampling_var}
+\input{\chp5@path/5-2_ci_prop/5-2_ci_prop}
+\input{\chp5@path/5-3_ht_prop/5-3_ht_prop}
 
 
 %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

Chp 7/7-1_one_t/figures/guiness/guiness.R

@@ -0,0 +1,78 @@
+# Guinness alcohol content example
+library(openintro)
+
+# Data: alcohol content (% ABV) for 8 batches 
+alcohol <- c(4.8, 4.6, 4.7, 4.5, 4.9, 4.6, 4.8, 4.4)
+target <- 4.5
+
+# Histogram
+myPDF("guinessHist.pdf", 1.1*5.5, 3.3, mar=c(3.5,3.5,0.15,0.5), mgp=c(2.4,0.7,0))
+
+histPlot(
+  alcohol,
+  col="#22558833",
+  border="#225588",
+  xlab = "Alcohol Content of Guinness Batches (%)",
+  xlim = c(4.25, 5.05),
+  breaks = seq(4.25, 5.05, by = 0.1),
+  axes = FALSE
+)
+# Add custom x and y axes
+axis(1, at=seq(4.3, 5.0, by=0.1))
+axis(2)
+
+dev.off()
+
+
+# t-test
+tres <- t.test(alcohol, mu=target, alternative = "two.sided")
+tstat <- as.numeric(tres$statistic)
+df <- tres$parameter
+pval <- tres$p.value
+
+# P-value plot
+myPDF('guinessPvalue.pdf', 4, 2, mar=c(4,1,0.1,1), mgp=c(5,0.45,0))
+
+plot(c(-4, 4), c(0, dnorm(0)), type='n', axes=FALSE, ylab = "", xlab = "")
+mean_alc <- mean(alcohol)
+symm_val <- 2*target - mean_alc
+
+axis(1, at = c(-5, -tstat, 0, tstat, 5),
+     labels = c(NA, 
+                -round(tstat,2), 
+                0, 
+                round(tstat,2), 
+                NA),
+     line=0)
+mtext("t", side = 1, line = 0.5, at = 4, adj = 1, cex = 1)
+
+axis(1, at = c(-5, -tstat, 0, tstat, 5),
+     labels = c(NA,
+                round(symm_val,2),
+                expression(paste(mu, "= 4.5")),
+                bquote(bar(X) == .(round(mean_alc,2))),
+                NA),
+     line=2.5)
+
+abline(h=0)
+
+X <- seq(-8, 8, 0.01)
+Y <- dt(X, df)
+lines(X, Y, col="black")
+
+these <- which(X > tstat)
+yy <- c(0, Y[these], 0)
+these <- c(these[1], these, rev(these)[1])
+xx <- X[these]
+polygon(xx, yy, col='#22558833', border='#225588')
+
+these <- which(X < -tstat)
+yy <- c(0, Y[these], 0)
+these <- c(these[1], these, rev(these)[1])
+xx <- X[these]
+polygon(xx, yy, col='#22558833', border='#225588')
+
+text(3,0.8*max(Y),"df = 7", cex = 0.9)
+
+dev.off()
+

Week1/Lecture1/Lecture1_agenda.tex

@@ -0,0 +1,23 @@
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+% Recap/Agenda 
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+% TODO better formatting
+\begin{frame}
+    \frametitle{Module 1: Exploratory Data Analysis and Study Design}
+    \begin{itemize}
+        % \item \hl{This time: }Course introduction
+        \item \hl{Reading: }Chapter 1 for next time
+        \item \hl{Deadlines/Announcements: }
+        \begin{itemize}
+            \item See/email me (estephen@bu.edu) for any registration issues
+            \item Edfinity classroom survey by lecture on Friday \\
+            (if you haven't done it yet)
+            \item Labs start this week (Friday)
+            \item Discussions start next week
+            \item Edfinity Homework 1 due on Monday
+        \end{itemize}
+    \end{itemize}
+
+\end{frame}
+