---
title: "ETC 2420/5242 Lab 3 2017"
author: "Di Cook"
date: "Week 3"
output: pdf_document
---
```{r echo = FALSE, message = FALSE, warning = FALSE, warning = FALSE}
knitr::opts_chunk$set(
message = FALSE,
warning = FALSE,
error = FALSE,
echo = FALSE,
collapse = TRUE,
comment = "#",
fig.height = 4,
fig.width = 8,
fig.align = "center",
cache = FALSE
)
```
## Purpose
This lab is to examine testing hypotheses using permutation.
## Background
Read Sections 2.3, and the exercises in 2.9.3, of the online textbook "IntroStat with Randomization and Simulation".
## Problem description
Is yawning contagious? An experiment conducted by the MythBusters, a science entertainment TV program on the Discovery Channel, tested if a person can be subconsciously influenced into yawning if another person near them yawns. 50 people were randomly assigned to two groups: 34 to a group where a person near them yawned (treatment) and 16 to a group where there wasnâ€™t a person yawning near them (control). The following table shows the results of this experiment.
```{r}
yawn_expt <- data.frame(group=c(rep("treatment", 34), rep("control", 16)),
yawn=c(rep("yes", 10), rep("no", 24), rep("yes", 4), rep("no", 12)))
library(dplyr)
library(tidyr)
library(knitr)
yawn_expt %>%
group_by(group, yawn) %>%
tally() %>%
ungroup() %>%
spread(yawn, n, fill=0) %>%
mutate(total = rowSums(.[-1])) %>%
kable()
```
## Question 1
a. How many subjects participated in the experiment?
b. How were participants assigned to treatment and control groups?
c. What are the two variables that describe the experiment?
d. Compute the proportion of the treatment and control groups who yawned. Add this to the table.
e. Compute the difference in proportions between the two groups.
## Question 2
The null hypothesis for the experiment is
$$H_o: p_{control} = p_{treatment}$$
a. Write the null hypothesis as an English sentence.
b. What would be the alternative hypothesis tested by MythBusters? $H_o: p_{control} \neq p_{treatment}$, $H_a: p_{control} < p_{treatment}$ or $H_a: p_{control} > p_{treatment}$
c. Explain your reasoning.
## Question 3
Write a function that permutes the `yawn` variable, and computes the difference between proportions of treatment and control groups.
## Question 4
a. Run the function 10000 times, saving the result.
b. Make a histogram (or a dotplot) of the results.
c. Draw a vertical line on the plot that represents the difference for the actual data.
d. Compute the proportion of times that the permuted data yields a difference larger than the difference of the actual data.
## Question 5
a. Compute the (permutation) p-value for testing the null hypothesis.
b. Based on your p-value, what is your decision about the null hypothesis? (Reject or fail to reject the null)
c. Write a sentence stating your conclusion.
d. Finally, based on these experimental results how would you answer "Is yawning contagious?"
## TURN IN
- Your `.Rmd` and `html` files
- Make sure your group members are listed as authors, one person per group will turn in the report
## Resources
- [IntroStat with Randomization and Simulation](https://www.openintro.org/stat/textbook.php)