A multi-faceted model for the selection of answers for multiple-choice tests was developed from the findings of a series of exploratory studies. This model implies that answer selection should be curvilinear. A series of models were tested for fit using the chi square procedure. Data were collected from 359 elementary school students ages 9-12. For each student, the data included the frequency of selection of each of four alternatives on the first three items of Gorham's Proverbs Test. None of the linear models fitted, even when wrong answers were included in the model. The curved-line model which was developed from Bock's MULTIQUAL and which included quadratic and cubic polynomials was the only model to fit. Estimates for explained variance suggest that about 25 per cent may be available from right answers alone. More than twice as much may be available from a curved-line procedure. (Author/BW)