Data Cleaning – Quiz 7

Now reshape the dataset long so that there are four observations per teacher code, one for each person-round of measurement (i.e. two observations for the two teacher measurements and two observations for the two student measurements). Note that you may need to specify the ‘string’ option when you run the reshape command, depending on what you named your four new variables.

1. How many non-missing values are there for your teacher/student observation variable in the reshaped dataset?

2. What percent of teachers or students were on-task during the observation? Ignore missing values. Round to the nearest percent.

Now collapse the data to the school-level. Calculate the fraction of teacher/student observations that were on-task per school.

3. Which school has the lowest on-task rate? Enter the school ID. If there are multiple schools that are tied with the lowest on-task rate, enter any of those IDs.

4. What is the average on-task rate across schools, in percentage terms? Round to the nearest percent.