... calculation of standard errors, confidence intervals, and p-values for test statistics, and we canget a good idea of the amount of finite-sample bias in the estimation method. In ad-dition, under ... yÞ 12: 9ÞComparing equations (12. 8) and (12. 9), we see that M-estimators are based on theanalogy principle. Once yohas been defined, finding an appropriate function q that Chapter 123 4412M-Estimation 12. 1 ... the iterations. Of course, as we discussed in Sec-tion 12. 6.2, this form of the LM statistic is often ill-behaved even with fairly largesample sizes. 12. 7.3 The Generalized Gauss-Newton MethodThe...