Homework 1b (bonus) - Data Wrangling

Due Date

Tuesday, September 24 Thursday, September 26

Data Wrangling

The learning objectives are to conduct data wrangling and generate some summary statastics.

You will need to download two datasets from https://github.com/USCbiostats/data-science-data. The individual and regional CHS datasets in 01_chs. The individual data includes personal and health characteristics of children in 12 communities across Southern California. The regional data include air quality measurements at the community level. Once downloaded, you can merge these datasets using the location variable. Once combined, you will need to do the following:

1. After merging the data, make sure you don’t have any duplicates by counting the number of rows. Make sure it matches.

   In the case of missing values, impute data using the average within the variables “male” and “hispanic.” If you are interested (and feel adventurous) in the theme of Data Imputation, take a look at this paper on “Multiple Imputation” using the Amelia R package here.

2. Create a new categorical variable named “obesity_level” using the BMI measurement (underweight BMI<14; normal BMI 14-22; overweight BMI 22-24; obese BMI>24). To make sure the variable is rightly coded, create a summary table that contains the minimum BMI, maximum BMI, and the total number of observations per category.

3. Create another categorical variable named “smoke_gas_exposure” that summarizes “Second Hand Smoke” and “Gas Stove.” The variable should have four categories in total.

4. Create four summary tables showing the average (or proportion, if binary) and sd of “Forced expiratory volume in 1 second (ml)” and asthma indicator by town, sex, obesity level, and “smoke_gas_exposure.”