This homework assignment was written in R Studio using RMarkdown. Now that we have learned this tool, you will use it to type up your answers (including R code). You can use this document as a template for your own submission (which must include answers and code in an .Rmd input file and in an output file). Remember that in order to create your Word document, click the arrow next to Knit in the RStudio toolbar and choose Knit to Word. If you choose to create .html output instead, you will need to convert this to .pdf before submitting to Blackboard. I am sharing the .pdf output for this homework, but also the .Rmd file used to produce it.

Part I - The Mark of a Criminal Record Revisited

In Homework 2, we analyzed data from an important field experiment by Devah Pager about the the effect of race and criminal record on employment:

The Mark of a Criminal Record. American Journal of Sociology 108(5):937-975. Look here to watch Professor Pager discuss the design and result.

This is a follow-up exercise using the same data set. Last time you encountered the paper, you described the different callback rates between groups. Now we are going to use what weve learned about statistical inference to better understand those patterns. You are welcomeand even encouragedto reuse code from HW2. In fact, in practice you often have to work with the same dataset many times, and writing good code the first time helps you reuse the code in future projects.

The dataset is called criminalrecord.csv. You should be able to find these data on your computer from the beginning of the semester. You may not need to use all of these variables for this activity. Weve kept these unnecessary variables in the dataset because it is common to receive a dataset with much more information than you need.

Name

jobid callback black crimrec interact 

city distance 

Description

Job ID number 1 if tester received a callback, 0 if the tester did not receive a callback. 1 if the tester is black, 0 if the tester is white. 1 if the tester has a criminal record, 0 if the tester does not. 1 if tester interacted with employer during the job application, 0 if tester doesnt interact with employer. 1 is job is located in the city center, 0 if job is located in the suburbs. Jobs average distance to downtown.

Question 4 (2 points)

Calculate the estimated effect of a criminal record for white applicants by comparing the callback rate in the treatment condition and the callback rate in the control condition. Create a 95% confidence interval around this estimate of the difference in means between treatment and control groups (for white applicants). Recall that

is how we have been estimating the standard error for difference in means for proportions. Next, describe the estimate and confidence interval in a way that could be understood by a general audience.