Question 1. Clustered Samples and Panels. Suppose that, for one semester, you collect the following data on a random sample of university students for each unit / subject taken: a standardised final exam score (score), fraction of lectures attended (attdrte), a dummy variable indicating whether the unit is required for the student's major (major), cumulative grade point average at the start of semester (cumGPA) and university entry score (AT AR). (i) This data set is classified as a clustered sample. Is what ways is this sample like a panel data set? How is it different from a standard panel ? Roughly how many observations would you expect for the typical student ? (ii) Write down an unobserved effects model that explains final exam performance (score) in terms of attendance and other characteristics. Use s to subscript student and c to subscript class. Which variables do not vary within a student ? (iii) If you pool all of the data and use OLS, what are you assuming about the unobserved student charac- teristics that affect performance and attendance rate? What roles do AT AR score and prior GPA play in this regard? (iv) If you think AT AR score and prior GPA (cumGPA) do not adequately capture student ability, how would you estimate the effect of attendance on final exam performance? Question 1. Clustered Samples and Panels. Suppose that, for one semester, you collect the following data on a random sample of university students for each unit / subject taken: a standardised final exam score (score), fraction of lectures attended (attdrte), a dummy variable indicating whether the unit is required for the student's major (major), cumulative grade point average at the start of semester (cumGPA) and university entry score (AT AR). (i) This data set is classified as a clustered sample. Is what ways is this sample like a panel data set? How is it different from a standard panel ? Roughly how many observations would you expect for the typical student ? (ii) Write down an unobserved effects model that explains final exam performance (score) in terms of attendance and other characteristics. Use s to subscript student and c to subscript class. Which variables do not vary within a student ? (iii) If you pool all of the data and use OLS, what are you assuming about the unobserved student charac- teristics that affect performance and attendance rate? What roles do AT AR score and prior GPA play in this regard? (iv) If you think AT AR score and prior GPA (cumGPA) do not adequately capture student ability, how would you estimate the effect of attendance on final exam performance
