For this assignment, you will need to have access to the ECLS, ELS, HSLS, or PISA data. With the dataset that you plan to use for your project, complete the following steps:

  1. Using your research question from the first assignment along with my comments, describe briefly 10 variables that you think might be relevant to this study.
  2. Using the dataset that you’d like to work with, find indicators to match the variables you’re looking for.
  3. Generate code to subset your chosen variables from the full dataset.
  4. Describe the data you’ve selected. Include the following information in your description of each continuous indicator:
    • Mean
    • Standard error of the mean
    • Median
    • Number missing

For categorical indicators, I need a tabulation across the levels of the indicator, including a category for missing data.

NB: Skip weights, etc, and focus on your variables of interest.

For this assignment, you should submit a do file that

  1. subsets the variables you want from the full dataset (saving optional)
  2. generates the proper descriptive statistics