Analyze the data from Smithson et al. (2007), Study 3. In R, the data file is available via the command data("guilt3", package = "smdata"). Stata users may access the file via the link “ch6 guilt3.dta” at https://dl.dropbox

.com/u/1857674/SmiMerBook/SmiMerDoc.html. It contains 96 observations and three variables: pguilt (the judged probability of guilt), v1 which equals 1 if a “Guilty” verdict was returned and 0 otherwise, and v2 which equals 1 if a “Not Guilty” verdict was returned and 0 otherwise. The third verdict alternative is, of course, “Not Proven.”

(a) Find the best model for pguilt.

(b) Compare the MLEs in your model with the bias-corrected and bias-reduced estimates (R users only).

(c) Compare your results with the model for the probability-of-guilt example featured in this chapter.