The \(r\)-\(d\) class estimator in generalized linear models: applications on gamma, Poisson and binomial distributed responses. (English) Zbl 07193743
Summary: In order to combat multicollinearity, the \(r\)-\(d\) class estimator was introduced in linear and binary logistic regression models. Since the generalized linear models (GLMs) are the models that include logistic regression model, Poisson regression model, etc., we introduce the iterative and first-order approximated \(r\)-\(d\) class estimator in GLMs. The sampling distribution of the \(r\)-\(d\) class estimator at convergence is given and the test on the regression coefficients is provided. The properties of the first-order approximated \(r\)-\(d\) class estimator in GLMs are discussed, comparisons of the three constitute estimators in the sense of bias, variance and scalar mean square errors are done, and a cross-validation method and a mean square error method for the selection of the shrinkage parameter are given. Finally, a simulation study is conducted for Poisson response and two real data analyses are done for gamma and binomial response data to examine the performance of the first-order approximated \(r\)-\(d\) class estimator versus the first-order approximated maximum likelihood, Liu, PCR and ridge estimators in GLMs.
MSC:
| 62-XX | Statistics |
Keywords:
generalized linear models; principal component regression estimator; Liu estimator; maximum likelihood estimator; mean squared errorReferences:
| [1] | McCullagh P, Nelder JA. Generalized linear models. London: Chapman and Hall; 1989. [Crossref], [Google Scholar] · Zbl 0744.62098 |
| [2] | Agresti A. Foundations of linear and generalized linear models. Hoboken: Wiley; 2015. [Google Scholar] · Zbl 1309.62001 |
| [3] | Marx BD, Smith EP.Principal component estimation for generalized linear regression. Biometrika. 1990;77(1):23-31. doi: 10.1093/biomet/77.1.23[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0692.62051 |
| [4] | Nyquist H.Restricted estimation of generalized linear models. J Roy Statist Soc Ser C. 1991;40(1):133-141. [Web of Science ®], [Google Scholar] · Zbl 0825.62612 |
| [5] | Segerstedt B.On ordinary ridge regression in generalized linear models. Commun Statist Theory Methods. 1992;21(8):2227-2246. doi: 10.1080/03610929208830909[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 0775.62185 |
| [6] | Kurtoğlu F, Özkale MR.Liu estimation in generalized linear models: application on gamma distributed response variable. Statist Papers. 2016;57(4):911-928. doi: 10.1007/s00362-016-0814-3[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1416.62427 |
| [7] | Mansson K, Kibria BMG, Shukur G.On Liu estimators for the logit regression model. Econ Model. 2012;29:1483-1488. doi: 10.1016/j.econmod.2011.11.015[Crossref], [Web of Science ®], [Google Scholar] |
| [8] | Urgan NN, Tez M. Liu estimator in logistic regression when the data are collinear. In: The 20th International Conference, EURO Mini Conference Continuous Optimization and Knowledge-Based Technologies (EurOPT-2008), p. 323-327 2008. [Google Scholar] |
| [9] | Wu J, Asar Y.On almost unbiased ridge logistic estimator for the logistic regression model. Hacettepe J Math Statist. 2016;45(3):989-998. [Web of Science ®], [Google Scholar] · Zbl 1359.62299 |
| [10] | Chang X. On the almost unbiased ridge and Liu estimator in logistic regression model. In International Conference on Social Science, Education, Management and Sports Education. Atlantis Press, p. 1663-1665 2015. [Google Scholar] |
| [11] | Varathan N, Wijekoon P.Optimal generalized logistic estimator. Comm Statist Theory Methods. 2018;47(2):463-474. doi: 10.1080/03610926.2017.1307406[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1388.62221 |
| [12] | Huang J. A simulation based research on a biased estimator in logistic regression model. In: Computational Intelligence and Intelligent Systems. Berlin: Springer; p. 389-395 2012. [Google Scholar] |
| [13] | Kibria BMG, Månsson K, Shukur G.Performance of some logistic ridge regression parameters. Comput Econ. 2012;40:401-414. doi: 10.1007/s10614-011-9275-x[Crossref], [Web of Science ®], [Google Scholar] |
| [14] | Kibria BMG, Månsson K, Shukur G.A simulation study of some biasing parameters for the ridge type estimation of Poisson regression. Commun Statist Simul Comput. 2015;44(4):943-957. doi: 10.1080/03610918.2013.796981[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1328.62459 |
| [15] | Månsson K, Shukur G.A Poisson ridge regression estimator. Econ Model. 2011;28:1475-1481. doi: 10.1016/j.econmod.2011.02.030[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1225.62098 |
| [16] | Turkan S, Özel G.A new modified Jackknifed estimator for the Poisson regression model. J Appl Stat. 2016;43(10):1892-1905. doi: 10.1080/02664763.2015.1125861[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1514.62905 |
| [17] | Saleh AKMdE, Kibria BMG.Improved ridge regression estimators for the logistic regression model. Comput Stat. 2013;26(6):2519-2558. doi: 10.1007/s00180-013-0417-6[Crossref], [Google Scholar] · Zbl 1306.65129 |
| [18] | Siray GU, Toker S, Kaciranlar S.On the restricted Liu estimator in the logistic regression model. Commun Statist Simul Comput. 2015;44(1):217-232. doi: 10.1080/03610918.2013.771742[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1328.62403 |
| [19] | Wu J, Asar Y.More on the restricted Liu estimator in the logistic regression model. Commun Statist Simul Comput. 2017;46(5):3680-3689. [Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1368.62187 |
| [20] | Wu J, Asar Y, Arashi M.On the restricted almost unbiased Liu estimator in the logistic regression model. Commun Statist Theory Methods. 2018;47(18):4389-4401. doi: 10.1080/03610926.2017.1376082[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1508.62181 |
| [21] | Kaçıranlar S, Sakallıoğlu S.Combining the Liu estimator and the principal component regression estimator. Comm Statist Theory Methods. 2001;30(12):2699-2705. doi: 10.1081/STA-100108454[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1009.62560 |
| [22] | Liu K.A new class of biased estimate in linear regression. Comm Statist Theory Methods. 1993;22(2):393-402. doi: 10.1080/03610929308831034[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 0784.62065 |
| [23] | Inan D.Combining the Liu-type estimator and the principal components regression estimator. Stat Papers. 2015;56(1):147-156. doi: 10.1007/s00362-013-0571-5[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1305.62253 |
| [24] | Liu K.Using Liu-type estimator to combat collinearity. Commun Statist Theory Methods. 2003;32(5):1009-1020. doi: 10.1081/STA-120019959[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1107.62345 |
| [25] | Wu H, Yang H.On the principal component Liu-type estimator in linear regression. Commun Statist Simulation Comput. 2015;44:1061-2072. [Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 1328.62470 |
| [26] | Huang WH, Qi JJ, Huang NT.Liu-type estimator for linear model with linear restrictions. J Syst Sci Math Sci. 2009;29:937-946. [Google Scholar] · Zbl 1210.62092 |
| [27] | Baye MR, Parkar FP.Combining ridge and principal component regression: a money demand illustration. Commun Statist Theory Methods. 1984;13:197-225. doi: 10.1080/03610928408828675[Taylor & Francis Online], [Web of Science ®], [Google Scholar] |
| [28] | First-order r-d class estimator in binary logistic regression model. Statist Probab Lett. 2015;106:19-29. doi: 10.1016/j.spl.2015.06.021[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1352.62117 |
| [29] | Dobson AJ, Barnett AG. An introduction to generalized linear models. Boca Raton: CRC Press; 2008. [Google Scholar] · Zbl 1165.62049 |
| [30] | Khuri AI. Linear model methodology. Boca Raton: CRC Press; 2010. [Google Scholar] · Zbl 1247.62168 |
| [31] | Myers RH, Montgomery DC, Vining GGV, et al. Generalized linear models: with applications in engineering and the sciences. Hoboken: John Wiley and Sons; 2010. [Crossref], [Google Scholar] · Zbl 1267.62082 |
| [32] | Obenchain RL.Ridge analysis following a preliminary test of the shrunken hypothesis. Technometrics. 1975;17(4):431-441. doi: 10.1080/00401706.1975.10489369[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 0324.62050 |
| [33] | Obenchain RL.Classical F-tests and confidence regions for ridge regression. Technometrics. 1977;19(4):429-439. doi: 10.1080/00401706.1977.10489582[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 0375.62066 |
| [34] | Du J. Which estimator of the dispersion parameter for the Gamma family generalized linear models is to be chosen? Dalarna University, D-level Master’s Thesis 2007. [Google Scholar] |
| [35] | Ruoyan M. Estimation of dispersion parameters in GLMs with and without random effects. Examensarbete 5 2004. [Google Scholar] |
| [36] | Smith EP, Marx BD.Ill-conditioned information matrices, generalized linear models and estimation of the effects of acid rain. Environmetrics. 1990;1(1):57-71. doi: 10.1002/env.3170010107[Crossref], [Google Scholar] |
| [37] | Mallows CL.Some comments on Cp. Technometrics. 1973;15(4):661-675. [Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 0269.62061 |
| [38] | Ahn BJ.A Ridge-type estimator for generalized linear models. Korean J App Statist. 1994;7(1):75-82. [Google Scholar] · Zbl 1262.62109 |
| [39] | McDonald GC, Galarneau DI.A Monte Carlo evaluation of ridge-type estimators. J Amer Statist Assoc. 1975;70:407-416. doi: 10.1080/01621459.1975.10479882[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 0319.62049 |
| [40] | Schaefer RL.Alternative estimators in logistic regression when the data are collinear. J Statist Comput Simul. 1986;25(1-2):75-91. doi: 10.1080/00949658608810925[Taylor & Francis Online], [Google Scholar] · Zbl 0596.62060 |
| [41] | Mackinnon MJ. Collinearity in generalized linear models. Dissertation, The University of British Columbi; 1986. [Google Scholar] |
| [42] | Freund RJ. Regression with SAS with emphasis on PROC REG. In: Eighth Anual SAS Users Group International Conference, New Orleans, LA, p. 16-19 1983. [Google Scholar] |
| [43] | Vargas TM, Ferrari SLP, Lemonte AJ.Improved likelihood inference in generalized linear models. Comput Statist Data Anal. 2014;74:110-124. doi: 10.1016/j.csda.2013.12.002[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1506.62181 |
| [44] | Lemonte A. The gradient test: another likehood-based test. Amsterdam: Academic Press; 2016. [Google Scholar] · Zbl 1338.62011 |
| [45] | Harden JW, Hilbe JM. Generalized linear models and extensions. Texas: Stata Press; 2012. [Google Scholar] · Zbl 1306.62012 |
| [46] | Weissfeld LA, Sereika SM.A multicollinearity diagnostic for generalized linear models. Comm Statist Theory Methods. 1991;20(4):1183-1198. doi: 10.1080/03610929108830558[Taylor & Francis Online], [Web of Science ®], [Google Scholar] |
| [47] | Wattimena RK, Kramadibrata S, Sidi ID, et al. Developing coal pillar stability chart using logistic regression. Int J Rock Mech Mining Sci. 2013;58:55-60. doi: 10.1016/j.ijrmms.2012.09.004[Crossref], [Web of Science ®], [Google Scholar] |
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.
