Cost Function Estimation and Quality Bias: The Regulated Automobile Insurance Industry
研究受监管的汽车保险公司中，内生产品质量如何影响成本函数估计，并说明忽略服务质量数据会导致估计偏差，还提供了一个检验该偏差的新方法。
This article explores the implications of endogenous product quality (and therefore endogenous output) in the empirical estimation of cost functions for regulated automobile collision insurance firms. It contains a structural model of such a firm and provides an illustration of the types of biases that can result if data on quality of service are unavailable or otherwise omitted. The analysis shows how the directions of biases depend on the nature of the variations in the observed (nonquality) data. A new test suggests that such bias is present in insurance cost functions.