The logreg.savefit objects are the results of fitting logreg with various options. The examples in the functions of the LogicReg packages all use far fewer iterations than is needed. (The number of iterations was reduced to provide quick results for bug-checking.) The number of iterations in the logreg.savefit objects are more reasonable (though they would still be small for larger problems). Otherwise the arguments used to fit the logreg.savefit objects are identical as those used in the examples of logreg. The logreg.savefit objects are used for examples involving things like plotting, printing, and predicting.
logreg.testdat has 500 cases, and 21 columns. Column 1 is the response Y, column k+1, k=1,...,20 is (binary) predictor Xk. Each predictor Xk is simulated as an independent Bernoulli(pk) random variables, with success probabilities pk between 0.1 and 0.9. The response variable is simulated from the model
providing 
.