Language: R

The `HELPfull` data within the `mosaicData` package contains information about the Health Evaluation and Linkage to Primary Care (HELP) randomized trial in tall format.

1. Generate a table of the data for subjects (ID) 1, 2, and 3 that includes the ID variable, the TIME variable, and the DRUGRISK and SEXRISK variables (measures of drug and sex risk-taking behaviors, respectively).

2. The HELP trial was designed to collect information at 0, 6, 12, 18, and 24 month intervals. At which timepoints were measurements available on the *RISK variables for subject 3?

3. Lets restrict our attention to the data from the baseline (TIME = 0) and 6-month data. Use the pivot_wider() function from the dplyr package to create a table that looks like the following:

# A tibble: 3  5 ID DRUGRISK_0 DRUGRISK_6 SEXRISK_0 SEXRISK_6      1 1 0 0 4 1 2 2 0 0 7 0 3 3 20 13 2 4 

4. Repeat this process using all subjects. What is the Pearson correlation between the baseline (TIME = 0) and 6-month DRUGRISK scores? Repeat this for the SEXRISK scores. (Hint: use the use = "complete.obs" option from the cor() function.)