Knowledge that Transforms

A stochastic filtering method is presented for on-line recursive estimation and forecasting of autocorrelated time series. Several state space models for nonseasonal and seasonal time series, which belong to the autoregressive integrated-moving average class, are presented. The Kalman filter is introduced as the recursive data processor for on-line time series forecasting. The estimation problem and initial values determination are discussed, and numerical examples are given. An extension of Brown's adaptive smoothing method for autocorrelated time series through the proposed filtering approach is also presented.

Individuals often use several different strategies such as the expected value rule, conjunctive rule, and elimination-by-aspects, to make decisions. It has been hypothesized that strategy selection is, in part, a function of (1) the ability of a strategy to produce an accurate response and (2) the strategy's demand for mental resources or effort. We examine effort and accuracy and their role in strategy selection. Several strategies that may be used to make choices under risk are simulated using a production system framework. This framework allows the estimation of the effort required to use the strategy in a choice environment, while simultaneously measuring its accuracy relative to a normative model. A series of Monte-Carlo studies varied several aspects of the choice environments, including the complexity of the task and the presence or absence of dominated alternatives. These simulations identify strategies which approximate the accuracy of normative procedures while requiring substantially less effort. These results, however, are highly contingent upon characteristics of the task environment. The potential of production system models in understanding task effects in decisions is stressed.