Bayesian estimation of the learning effects of repeated pointing tasks
Koki Kyo, Kevin H. Knuth, Ariel Caticha, Adom Giffin, Carlos C. Rodríguez · AIP conference proceedings · 2007
Recently, in the field of human‐computer interaction, the SH‐model was developed for evaluating the performance of the input devices of a computer. This model was then modified by introducing a learning effect factor, which is expressed by using two deterministic functions. A remarkable merit of the use of deterministic functions is that parameters can be estimated easily by using the method of least squares. However, since the deterministic functions used to express the learning effect can only be fitted to some special patterns, performance of the modified SH‐model may be somewhat restricted. In this paper, we apply a Bayesian modeling method for estimating the learning effect. We consider the parameters describing the learning effect as random variables and introduce smoothness priors for them. Results show that the learning effect can be estimated satisfactorily, thus providing proof of the validity of our model.