Abstract | ||
---|---|---|
In a generalized linear model of binary data, we consider models based on a general link function including a logistic regression model and a probit model as special cases. For testing the null hypothesis H"0 that the considered model is correct, we consider a family of @f-divergence goodness-of-fit test statistics C"@f that includes a power divergence family of statistics R^a. We propose a transformed C"@f statistics that improves the speed of convergence to a chi-square limiting distribution and show numerically that the transformed R^a statistic performs well. We also give a real data example of the transformed R^a statistic being more reliable than the original R^a statistic for testing H"0. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1016/j.jmva.2013.09.014 | J. Multivariate Analysis |
Keywords | Field | DocType |
considered model,binary data,original r,probit model,power divergence family,statistics r,generalized linear model,transformed goodness-of-fit statistic,null hypothesis h,f-divergence goodness-of-fit test statistic,logistic regression model,asymptotic expansion | Econometrics,Statistic,PRESS statistic,Generalized linear array model,Generalized linear model,Binary data,Statistics,Generalized linear mixed model,Goodness of fit,Mathematics,Asymptotic distribution | Journal |
Volume | ISSN | Citations |
123, | 0047-259X | 0 |
PageRank | References | Authors |
0.34 | 1 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nobuhiro Taneichi | 1 | 1 | 1.30 |
Yuri Sekiya | 2 | 1 | 1.30 |
Jun Toyama | 3 | 130 | 19.87 |