×

Poisson loglinear modeling with linear constraints on the expected cell frequencies. (English) Zbl 1281.62142

Summary: In this paper we consider Poisson loglinear models with linear constraints (LMLC) on the expected table counts. Multinomial and product multinomial loglinear models can be obtained by considering that some marginal totals (linear constraints on the expected table counts) have been prefixed in a Poisson loglinear model. Therefore with the theory developed in this paper, multinomial and product multinomial loglinear models can be considered as a particular case. To carry out inferences on the parameters in the LMLC an information-theoretic approach is followed from which the classical maximum likelihood estimators and Pearson chi-square statistics for goodness-of fit are obtained. In addition, nested hypotheses are proposed as a general procedure for hypothesis testing. Through a simulation study the appropriateness of proposed inference tools is illustrated.

MSC:

62H17 Contingency tables
62F05 Asymptotic properties of parametric tests
62F07 Statistical ranking and selection procedures
62F30 Parametric inference under constraints
PDFBibTeX XMLCite
Full Text: DOI arXiv

References:

[1] Agresti, A. (2002). Categorical data analysis, 2nd ed. Wiley, New York. · Zbl 1018.62002
[2] Agresti, A. (2007). An introduction to categorical data analysis, 2nd ed. Wiley, New York. · Zbl 1266.62008
[3] Aitchison, J. and Silvey, S.D. (1958). Maximum likelihood estimation of parameters subject to constraints. Annals of Mathematical Statistics, 29, 813–828. · Zbl 0092.36704 · doi:10.1214/aoms/1177706538
[4] Caussinus, H. (1966). Contribution à l’analyse statistique des tableaux de correlation. Ann. Fac. Sci. Toulouse, 29, 77–182. · Zbl 0168.39904 · doi:10.5802/afst.519
[5] Chatterjee, S. and Hadi, A.S. (2006). Regression analysis by example, 4th ed. John Wiley & Sons, Hoboken, New Jersey. · Zbl 1250.62035
[6] Cressie, N. and Pardo, L. (2000). Minimum -divergence estimator and hierarchical testing in loglinear models. Statist. Sinica, 10, 867–884. · Zbl 0969.62047
[7] Cressie, N. and Pardo, L. (2002). Model checking in loglinear models using -divergences and MLEs. J. Statist. Plann. Inference, 103, 437–453. · Zbl 0988.62041 · doi:10.1016/S0378-3758(01)00236-1
[8] Cressie, N. and Read, T.R.C. (1984). Multinomial goodness-of-fit tests. J. R. Stat. Soc. Ser. B Stat. Methodol., 46, 440–464. · Zbl 0571.62017
[9] Christensen, R. (1997). Log-linear model and logistic regression, 2nd ed. Springer-Verlag, New York. · Zbl 0880.62073
[10] Dale, J.R. (1986). Asymptotic normality of goodness-of-fit statistics for sparse product multinomials. J. R. Stat. Soc. Ser. B Stat. Methodol., 41, 48–59. · Zbl 0611.62017
[11] Ferguson, T.S. (1996). A course in large sample theory. Chapman & Hall, London. · Zbl 0871.62002
[12] Gail, M. (1978). The analysis of heterogeneity for indirect standardized mortality ratios. J. Roy. Statist. Soc. Ser. A, 141, 224–234. · doi:10.2307/2344454
[13] Haber, M. and Brown, M.B. (1986). Maximum likelihood methods for log-linear models when expected frequencies are subject to linear constraints. J. Amer. Statist. Assoc., 81, 477–482. · Zbl 0604.62058
[14] Haberman, S.J. (1973). Log-linear models for frequency data: sufficient statistics and likelihood equations. Ann. Statist., 1, 617–632. · Zbl 0261.62005 · doi:10.1214/aos/1176342458
[15] Haberman, S.J. (1974). The analysis of frequency data. University of Chicago Press, Chicago. · Zbl 0325.62017
[16] Kateri, M. and Agresti, A. (2007). A class of ordinal quasi-symmetry models for square contingency tables. Statist. Probab. Lett., 77, 598–603. · Zbl 1116.62067 · doi:10.1016/j.spl.2006.09.015
[17] Lang, J.B. (1996a). Maximum likelihood methods for a generalized class of log-linear models. Ann. Statist., 24, 726–752. · Zbl 0859.62061 · doi:10.1214/aos/1032894462
[18] Lang, J.B. (1996b). On the comparison of multinomial and Poisson log-linear models. J. R. Stat. Soc. Ser. B Stat. Methodol., 58, 253–266. · Zbl 0850.62567
[19] Lang, J.b. (2004). Multinomial–Poisson homogeneous models for contingency tables. Ann. Statist., 32, 340–383. · Zbl 1105.62352 · doi:10.1214/aos/1079120140
[20] Martín, N. and Pardo, L. (2008a). Minimum phi-divergence estimators for loglinear models with linear constraints and multinomial sampling. Statist. Papers, 49, 15–36. · Zbl 1183.62035 · doi:10.1007/s00362-006-0370-3
[21] Martín, N. and Pardo, L. (2008b). New families of estimators and test statistics in loglinear models. J. Multivariate Anal., 99, 1590–1609. · Zbl 1144.62041 · doi:10.1016/j.jmva.2008.01.002
[22] Martín, N. and Li, Y. (2011). A new class of minimum power divergence estimators with applications to cancer surveillance. J. Multivariate Anal., 102, 1175–1193. · Zbl 1216.62176 · doi:10.1016/j.jmva.2011.03.011
[23] Pardo, L. (2006). Statistical inference based on divergence measures. Chapman & Hall/CRC, Boca de Raton. · Zbl 1118.62008
[24] Pardo, J.A., Pardo, L. and Zografos, K. (2002). Minimum -divergence estimators with constraints in multinomial populations. J. Statist. Plann. Inference, 104, 221–237. · Zbl 0988.62014 · doi:10.1016/S0378-3758(01)00113-6
[25] Pardo, L. and Martín, N. (2009). Homogeneity/heterogeneity hypotheses for standardized mortality ratios based on minimum power-divergence estimators. Biom. J., 51, 819–836. · doi:10.1002/bimj.200800158
[26] Rao, C.R. (1973). Linear statistical inference and its applications, 2nd ed. John Wiley & Sons, New York. · Zbl 0256.62002
[27] Rao, C.R. and Toutenburg, H. (1999). Linear models: least squares and alternatives, 2nd ed. Springer, New York. · Zbl 0846.62049
[28] Rivas, M.J., Santos, M.T. and Morales, D. (1995). Rényi test statistics for partially observed diffusion processes. J. Statist. Plann. Inference, 127, 91–102. · Zbl 1052.62084 · doi:10.1016/j.jspi.2003.08.010
[29] Searle, S.R. (1971). Linear models. John Wiley & Sons, New York. · Zbl 0218.62071
[30] Zelterman, D. (1999). Models for discrete data. Oxford University Press, New York. · Zbl 0943.62053
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.