Exam 2

Date: Thursday, April 16, in Class

Mode: All Multiple Choice

Applying Basic Micro Preferences and Technology (or Supply and Demand) to Happiness

Statistical Topics:

• Multiple Hypothesis Test Correction Using Benjamini-Hochberg FDR Method

• OLS and IV bias using arrow diagrams

• Miles’s 5 big mistakes people make in statistical interpretation

  • The Generic Confound of the Social Sciences

  • Scale-Use Heterogeneity

  • Control variables measured with error only partially control, plus the fact that almost everything is only a proxy (and therefore measured with error) for what you really want, theoretically

  • p-hacking (which FDR addresses if people are honest)

  • The interpretation of coefficients changing when other variables are in the regression.

    • For example, if ln(HH size) is in the regression, then the coefficient on ln(Y) can be interpreted as being about effective income per person (after possibly allowing for returns to scale). Without ln(HH size) in the regression, it doesn’t have that interpretation.

    • Similarly, if ln(height) is in a regression, then the coefficient on ln(weight) can be interpreted as being about BMI (body mass index). Without ln(height) in the regression, it could be just as much about height (which on average is positively correlated with weight) and not about fat/thin.

    • As a 3d example, with ln(Y) in the regression, the coefficient on a dummy for finishing college is about correlations with education beyond any relation of education to income. Without ln(Y) in the regression, it includes relationships involving income.