In the analysis of clustered binary data with random cluster sizes, traditional approaches assuming fixed cluster sizes are generally used. Appropriate inference should take account of both intra-cluster correlation and extra-variation arising from the random cluster sizes. We introduce a dual Poisson random effects model for performing appropriate analyses of such data. Our orthodox best linear unbiased predictor approach to this model depends only on the first- and second- moment assumptions of unobserved random effects. This approach is illustrated with analyses of seed germination data and developmental toxicity data.
Agresti A
(2002) Categorical data analysis. 2nd ed.New York: John Wiley & Sons
.
2.
Breslow NE
and
Clayton DG
(1993)
Approximate inference in generalized linear mixed models
. Journal of the American Statistical Association, 88,
9–25
.
3.
Bowman D
and
George EO
(1995)
A saturated model for analyzing exchangeable binary data: applications to clinical and developmental toxicity studies
. Journal of the American Statistical Association, 90,
871–79
.
4.
Coull BA
and
Agresti A
(2000)
Random effects modeling of multiple binomial responses using the multivariate binomial logistic-normal distribution
. Biometrics, 56,
73–80
.
5.
Coull BA
,
Houseman EA
and
Betensky RA
(2006)
A computationally tractable multivariate random effects model for clustered binary data
. Biometrika, 93,
587–99
.
Dunson DB
,
Chen Z
and
Harry J
(2003)
A Bayesian approach for joint modeling of cluster size and subunit-specific outcomes
. Biometrics, 59,
521–30
.
8.
George EO
and
Bowman D
(1995)
A full likelihood procedure for analyzing exchangeable binary data
. Biometrics, 51,
512–23
.
9.
Gueorguieva RV
(2005)
Comments about joint modeling of cluster size and binary and continuous subunit-specific outcomes
. Biometrics, 61,
862–67
.
10.
Ha ID
and
Lee Y
(2005)
Comparison of hierarchical likelihood versus orthodox best linear unbiased predictor approaches for frailty models
. Biometrika, 92,
717–23
.
11.
Jiang J
(2001)
Mixed-effects models with random cluster sizes
. Statistics and Probability Letters, 53,
201–206
.
12.
Jørgensen B
,
Lundbye-Christensen S
,
Song X-K
and
Sun L
(1996)
A longitudinal study of emergency room visits and air pollution for Prince George, British Columbia
. Statistics in Medicine, 15,
823–36
.
13.
Kagan AM
,
Linnik YV
and
Rao CR
(1973) Characterization problems in mathematical statistics.
New York: John Wiley & Sons
.
14.
Lee Y
and
Nelder JA
(1996)
Hierarchical generalized linear models
. Journal of Royal Statistical Society, B58,
619–78
.
15.
Ma R
and
Jørgensen B
(2007)
Nested generalized linear models: an orthodox best linear unbiased predictor approach
. Journal of the Royal Statistical Society, B69,
625–41
.
16.
Ma R
,
Krewski D
and
Burnett RT
(2003)
Random effects Cox models: a Poisson modelling approach
. Biometrika, 90,
157–69
.
17.
McCullagh P
and
Nelder JA
(1989) Generalized Linear Models. 2nd editionLondon: Chapman & Hall
.
18.
Morton R
(1991)
Analysis of extra-multinomial data derived from extra-Poisson variables conditional on their total
. Biometrika, 78,
1–6
.
19.
Stefanescu C
and
Turnbull BW
(2003)
Likelihood inference for exchangeable binary data with varying cluster sizes
. Biometrics, 59,
18–24
.
20.
Ten Have TR
and
Chinchilli VM
(1998)
Two-stage negative binomial and overdispersed Poisson models for clustered developmental toxicity data with random cluster size
. Journal of Agricultural, Biological and Environmental Statistics, 3,
75–98
.
21.
Zhu J
,
Eickhoff JC
and
Kaiser MS
(2003)
Modeling the dependence between number of trials and success probability in beta-binomial-Poisson mixture distribution
. Biometrics, 59,
955–61
.
22.
Zou G
(2004)
A modified Poisson regression approach to prospective studies with binary data
. American Journal of Epidemiology, 159,
702–06
.
