Use the data set CRIME1 and consider the linear probability model:
arr86 = β0 + β1pcnv + β2avgsen + β3totime + β4ptime86 + β5qemp86 + ε
(a) Use the "describe" command and state what the definitions of each of the variables in the model are. Create the dummy variable arr86 such that it takes value 1 if number of arrests in 1986 was greater than or equal to 1, and 0 otherwise. Thus this variable is simply an indicator for whether the individual was arrested in 1986 at all or not.
(b) Estimate this model by OLS and find the fitted (predicted) values for arr86. Verify that these are strictly between 0 and 1. What are largest and smallest fitted values (make use of the "summarize" command).
(c) Estimate the equation using weighted least squares (WLS).
(d) Use the WLS estimates to determine whether avgsen and tottime are jointly significant at the 5% level.
Attachment:- CRIME1.rar