Forecasting relative quality
暂无分享,去创建一个
This paper develops a model to forecast the likely quality rating of new automobiles. A scheme is devised and implemented for 1982 whereby the probability that a specific model will have one of five quality ratings is computed. The quality ratings are based on the trouble index computed by Consumer Reports based on a survey of its subscribers. A multinomial logit specification is used whereby the relative probability that a given level of quality is realized is a function of previous quality ratings, the location of the manufacturer of the automobile, the size of the automobile and the list price (or port-of-entry prices, in the case of imports). The forecast results when compared in a qualitative way to actual 1982 quality ratings prove to be acceptable.
[1] A. Zellner. An Efficient Method of Estimating Seemingly Unrelated Regressions and Tests for Aggregation Bias , 1962 .
[2] Arnold Zellner,et al. JOINT ESTIMATION OF RELATIONSHIPS INVOLVING DISCRETE RANDOM VARIABLES , 1965 .
[3] W. R. Sharp,et al. A Steering and Visualization Toolkit for Distributed Applications , 2006, PDPTA.
[4] J. Triplett,et al. Assessing the Quality Error in Output Measures: The Case of Refrigerators , 1977 .