Multilevel models are often fitted to survey data gathered with a complex multistage sampling design. However, if such a design is informative, in the sense that the inclusion probabilities depend on the response variable even after conditioning on the covariates, then standard maximum likelihood estimators are biased. In this paper, following the Pseudo Maximum Likelihood (PML) approach of Skinner (1989), we propose a probability-weighted estimation procedure for multilevel ordinal and binary models which eliminates the bias generated by the informativeness of the design. The reciprocals of the inclusion probabilities at each sampling stage are used to weight the log-likelihood function and the weighted estimators obtained in this way are tested by means of a simulation study for the simple case of a binary random intercept model with and without covariates. The variance estimators are obtained by a bootstrap procedure. The maximization of the weighted log-likelihood of the model is done by the NLMIXED procedure of the SAS, which is based on adaptive Gaussian quadrature. Also the bootastrap estimation of variances is implemented in the SAS environment.

Weighted estimation in multilevel ordinal and binary models in the presence of informative sampling designs / L. GRILLI; M. PRATESI. - In: SURVEY METHODOLOGY. - ISSN 0714-0045. - STAMPA. - 30:(2004), pp. 93-103.

Weighted estimation in multilevel ordinal and binary models in the presence of informative sampling designs

GRILLI, LEONARDO;
2004

Abstract

Multilevel models are often fitted to survey data gathered with a complex multistage sampling design. However, if such a design is informative, in the sense that the inclusion probabilities depend on the response variable even after conditioning on the covariates, then standard maximum likelihood estimators are biased. In this paper, following the Pseudo Maximum Likelihood (PML) approach of Skinner (1989), we propose a probability-weighted estimation procedure for multilevel ordinal and binary models which eliminates the bias generated by the informativeness of the design. The reciprocals of the inclusion probabilities at each sampling stage are used to weight the log-likelihood function and the weighted estimators obtained in this way are tested by means of a simulation study for the simple case of a binary random intercept model with and without covariates. The variance estimators are obtained by a bootstrap procedure. The maximization of the weighted log-likelihood of the model is done by the NLMIXED procedure of the SAS, which is based on adaptive Gaussian quadrature. Also the bootastrap estimation of variances is implemented in the SAS environment.
2004
30
93
103
L. GRILLI; M. PRATESI
File in questo prodotto:
File Dimensione Formato  
Grilli_Pratesi_SM2004.pdf

Accesso chiuso

Tipologia: Versione finale referata (Postprint, Accepted manuscript)
Licenza: Tutti i diritti riservati
Dimensione 277.04 kB
Formato Adobe PDF
277.04 kB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/211225
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact