Influence analysis for Poisson inverse Gaussian regression models based on the EM algorithm

For Poisson inverse Gaussian regression models, it is very complicated to obtain the influence measures based on the traditional method, because the associated likelihood function involves intractable expressions, such as the modified Bessel function. In this paper, the EM algorithm is employed as a basis to derive diagnostic measures for the models by treating them as a mixed Poisson regression with the weights from the inverse Gaussian distributions. Several diagnostic measures are obtained in both case-deletion model and local influence analysis, based on the conditional expectation of the complete-data log-likelihood function in the EM algorithm. Two numerical examples are given to illustrate the results.

[1]  Gordon E. Willmot,et al.  A mixed poisson–inverse‐gaussian regression model , 1989 .

[2]  R. Cook.  Assessment of Local Influence , 1986 .

[3]  S. Weisberg,et al.  Residuals and Influence in Regression , 1982 .

[4]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[5]  Wai-Yin Poon,et al.  Influence analysis of structural equation models with polytomous variables , 1999 .

[6]  C. Dean.  Testing for Overdispersion in Poisson and Binomial Regression Models , 1992 .

[7]  Bo-Cheng Wei,et al.  Case-deletion measures for models with incomplete data , 2001 .

[8]  Erling B. Andersen.  Diagnostics in categorical data analysis , 1992 .

[9]  Sik-Yum Lee,et al.  Local influence for incomplete data models , 2001 .

[10]  Heping Zhang,et al.  A diagnostic procedure based on local influence , 2004 .

[11]  Pravin K. Trivedi,et al.  Regression Analysis of Count Data , 1998 .

[12]  New York Dover,et al.  ON THE CONVERGENCE PROPERTIES OF THE EM ALGORITHM , 1983 .

[13]  Musa H. Asyali,et al.  The Poisson Inverse Gaussian Regression Model in the Analysis of Clustered Counts Data , 2021, Journal of Data Science.

[14]  R. Cook.  Detection of influential observation in linear regression , 2000 .

[15]  Anthony C. Davison,et al.  Regression model diagnostics , 1992 .

[16]  Christopher J. Nachtsheim,et al.  Diagnostics for mixed-model analysis of variance , 1987 .

[17]  S. Jaggia,et al.  Multiple bids as a consequence of target management resistance: A count data approach , 1993 .

[18]  D. Karlis.  A general EM approach for maximum likelihood estimation in mixed Poisson regression models , 2001 .

[19]  Jean-Paul Chavas,et al.  Validation of Empirical Measures of Welfare Change: A Comparison of Nonmarket Techniques , 1985 .