Using Response Times to Model Not-Reached Items due to Time Limits

Missing values at the end of a test typically are the result of test takers running out of time and can as such be understood by studying test takers’ working speed. As testing moves to computer-based assessment, response times become available allowing to simulatenously model speed and ability. Integrating research on response time modeling with research on modeling missing responses, we propose using response times to model missing values due to time limits. We identify similarities between approaches used to account for not-reached items (Rose et al. in ETS Res Rep Ser 2010:i–53, 2010) and the speed-accuracy (SA) model for joint modeling of effective speed and effective ability as proposed by van der Linden (Psychometrika 72(3):287–308, 2007). In a simulation, we show (a) that the SA model can recover parameters in the presence of missing values due to time limits and (b) that the response time model, using item-level timing information rather than a count of not-reached items, results in person parameter estimates that differ from missing data IRT models applied to not-reached items. We propose using the SA model to model the missing data process and to use both, ability and speed, to describe the performance of test takers. We illustrate the application of the model in an empirical analysis.

     

On the form of stimulus generalization curves for visual intensity

Twelve pigeons were given successive discrimination training involving variable-interval reinforcement for key pecking in the presence of one intensity of monochromatic light randomly alternated with extinction for pecking during another intensity. All of the pigeons were then tested in extinction for generalization along the intensity dimension, and all showed a displacement of maximal responding from the positive stimulus in the direction opposite the negative stimulus. For six of the pigeons, for which the test included only three values beyond the positive stimulus, four showed peaked gradients but two did not, showing monotonic gradients with maximal responding to the most extreme test value. For another six pigeons tested over a wider range, all showed peaked gradients. Thus, when a sufficiently wide range of test values is employed, generalization gradients for visual intensity have the same peaked form as do gradients for qualitative visual dimensions such as wavelength or line angle.     

Der Analogiebegriff in der modernen Phyfik

Ohne Zusammenfassung