Kung Yee Liang

Models for longitudinal data: a generalized estimating equation approach.

This article discusses extensions of generalized linear models for the analysis of longitudinal data. Two approaches are considered: subject-specific (SS) models in which heterogeneity in regression parameters is explicitly modelled; and population-averaged (PA) models in which the aggregate response for the population is the focus. We use a generalized estimating equation approach to fit both classes of models for discrete and continuous outcomes. When the subject-specific parameters are assumed to follow a Gaussian distribution, simple relationships between the PA and SS parameters are available. The methods are illustrated with an analysis of data on mothers smoking and childrens respiratory disease.

Asymptotic Properties of Maximum Likelihood Estimators and Likelihood Ratio Tests under Nonstandard Conditions

Abstract Large sample properties of the likelihood function when the true parameter value may be on the boundary of the parameter space are described. Specifically, the asymptotic distribution of maximum likelihood estimators and likelihood ratio statistics are derived. These results generalize the work of Moran (1971), Chant (1974), and Chernoff (1954). Some of Chants results are shown to be incorrect. The approach used in deriving these results follows from comments made by Moran and Chant. The problem is shown to be asymptotically equivalent to the problem of estimating the restricted mean of a multivariate Gaussian distribution from a sample of size 1. In this representation the Gaussian random variable corresponds to the limit of the normalized score statistic and the estimate of the mean corresponds to the limit of the normalized maximum likelihood estimator. Thus the limiting distribution of the maximum likelihood estimator is the same as the distribution of the projection of the Gaussian random v...

Bipolar I Disorder and Schizophrenia: A 440-Single-Nucleotide Polymorphism Screen of 64 Candidate Genes among Ashkenazi Jewish Case-Parent Trios

Bipolar, schizophrenia, and schizoaffective disorders are common, highly heritable psychiatric disorders, for which familial coaggregation, as well as epidemiological and genetic evidence, suggests overlapping etiologies. No definitive susceptibility genes have yet been identified for any of these disorders. Genetic heterogeneity, combined with phenotypic imprecision and poor marker coverage, has contributed to the difficulty in defining risk variants. We focused on families of Ashkenazi Jewish descent, to reduce genetic heterogeneity, and, as a precursor to genomewide association studies, we undertook a single-nucleotide polymorphism (SNP) genotyping screen of 64 candidate genes (440 SNPs) chosen on the basis of previous linkage or of association and/or biological relevance. We genotyped an average of 6.9 SNPs per gene, with an average density of 1 SNP per 11.9 kb in 323 bipolar I disorder and 274 schizophrenia or schizoaffective Ashkenazi case-parent trios. Using single-SNP and haplotype-based transmission/disequilibrium tests, we ranked genes on the basis of strength of association (P<.01). Six genes (DAO, GRM3, GRM4, GRIN2B, IL2RB, and TUBA8) met this criterion for bipolar I disorder; only DAO has been previously associated with bipolar disorder. Six genes (RGS4, SCA1, GRM4, DPYSL2, NOS1, and GRID1) met this criterion for schizophrenia or schizoaffective disorder; five replicate previous associations, and one, GRID1, shows a novel association with schizophrenia. In addition, six genes (DPYSL2, DTNBP1, G30/G72, GRID1, GRM4, and NOS1) showed overlapping suggestive evidence of association in both disorders. These results may help to prioritize candidate genes for future study from among the many suspected/proposed for schizophrenia and bipolar disorders. They provide further support for shared genetic susceptibility between these two disorders that involve glutamate-signaling pathways.

A genome-wide association study of cleft lip with and without cleft palate identifies risk variants near MAFB and ABCA4

Case-parent trios were used in a genome-wide association study of cleft lip with and without cleft palate. SNPs near two genes not previously associated with cleft lip with and without cleft palate (MAFB, most significant SNP rs13041247, with odds ratio (OR) per minor allele = 0.704, 95% CI 0.635–0.778, P = 1.44 × 10−11; and ABCA4, most significant SNP rs560426, with OR = 1.432, 95% CI 1.292–1.587, P = 5.01 × 10−12) and two previously identified regions (at chromosome 8q24 and IRF6) attained genome-wide significance. Stratifying trios into European and Asian ancestry groups revealed differences in statistical significance, although estimated effect sizes remained similar. Replication studies from several populations showed confirming evidence, with families of European ancestry giving stronger evidence for markers in 8q24, whereas Asian families showed stronger evidence for association with MAFB and ABCA4. Expression studies support a role for MAFB in palatal development.

Prevalence and Correlates of Hoarding Behavior in a Community-Based Sample

Little is known about the prevalence and correlates of hoarding behavior in the community. We estimated the prevalence and evaluated correlates of hoarding in 742 participants in the Hopkins Epidemiology of Personality Disorder Study. The prevalence of hoarding was nearly 4% (5.3%, weighted) and was greater in older than younger age groups, greater in men than women, and inversely related to household income. Hoarding was associated with alcohol dependence; paranoid, schizotypal, avoidant, and obsessive-compulsive personality disorder traits; insecurity from home break-ins and excessive physical discipline before 16 years of age; and parental psychopathology. These findings suggest that hoarding may be relatively prevalent and that alcohol dependence, personality disorder traits, and specific childhood adversities are associated with hoarding in the community.

Sample size calculations for studies with correlated observations.

Correlated data occur frequently in biomedical research. Examples include longitudinal studies, family studies, and ophthalmologic studies. In this paper, we present a method to compute sample sizes and statistical powers for studies involving correlated observations. This is a multivariate extension of the work by Self and Mauritsen (1988, Biometrics 44, 79-86), who derived a sample size and power formula for generalized linear models based on the score statistic. For correlated data, we appeal to a statistic based on the generalized estimating equation method (Liang and Zeger, 1986, Biometrika 73, 13-22). We highlight the additional assumptions needed to deal with correlated data. Some special cases that are commonly seen in practice are discussed, followed by simulation studies.

The familial phenotype of obsessive-compulsive disorder in relation to tic disorders: the Hopkins OCD family study

BACKGROUND Obsessive-compulsive disorder (OCD) and tic disorders have phenomenological and familial-genetic overlaps. An OCD family study sample that excludes Tourettes syndrome in probands is used to examine whether tic disorders are part of the familial phenotype of OCD. METHODS Eighty case and 73 control probands and their first-degree relatives were examined by experienced clinicians using the Schedule for Affective Disorders and Schizophrenia-Lifetime Anxiety version. DSM-IV psychiatric diagnoses were ascertained by a best-estimate consensus procedure. The prevalence and severity of tic disorders, age-at-onset of OCD symptoms, and transmission of OCD and tic disorders by characteristics and type of proband (OCD + tic disorder, OCD - tic disorder) were examined in relatives. RESULTS Case probands and case relatives had a greater lifetime prevalence of tic disorders compared to control subjects. Tic disorders spanning a wide severity range were seen in case relatives; only mild severity was seen in control relatives. Younger age-at-onset of OCD symptoms and possibly male gender in case probands were associated with increased tic disorders in relatives. Although relatives of OCD + tic disorder and OCD - tic disorder probands had similar prevalences of tic disorders, this result is not conclusive. CONCLUSIONS Tic disorders constitute an alternate expression of the familial OCD phenotype.

Application of transmission disequilibrium tests to nonsyndromic oral clefts: Including candidate genes and environmental exposures in the models

Extensive epidemiological and genetic studies of the cause of oral clefts have demonstrated strong familial aggregation but have failed to yield definitive evidence of any single genetic mechanism. We used the transmission/disequilibrium test (TDT) to investigate the relationship between oral clefts and markers associated with five candidate genes by utilizing 160 parent-offspring trios. Conditional logistic regression models extended the TDT to include covariates as effect modifiers, thus permitting tests for gene-environment interactions. For four of these candidates [transforming growth factor alpha (TGFA), transforming growth factor beta 3 (TGFB3), retinoic acid receptor (RARA), and the proto-oncogene BCL3], we detected modestly elevated odds ratios for the transmission of one marker allele to cleft probands when all the trios were analyzed together. These odds ratios increased when information on type of cleft, race, family history, or maternal smoking were incorporated as effect modifiers. We detected significant interaction between maternal smoking and the transmission of alleles for markers near TGFA and TGFB3; excess transmission of allele 3 at BCL3 was most significant among cleft lip probands; and the odds ratios for transmission of alleles at D19S178 and THRA1 were significant when ethnic group was included in the model. We suggest that utilizing an analytical strategy that allows for stratification of data and incorporating environmental effects into a single analysis may be more effective for detecting genes of small effect.

Replication Study Supports Evidence for Linkage to 9p24 in Obsessive-Compulsive Disorder

Obsessive-compulsive disorder (OCD) is a severe psychiatric illness that is characterized by intrusive and senseless thoughts and impulses (obsessions) and by repetitive behaviors (compulsions). Family, twin, and segregation studies support the presence of both genetic and environmental susceptibility factors, and the only published genome scan for OCD identified a candidate region on 9p24 at marker D9S288 that met criteria for suggestive significance (Hanna et al. 2002). In an attempt to replicate this finding, we genotyped 50 pedigrees with OCD, using microsatellite markers spanning the 9p24 candidate region, and analyzed the data, using parametric and nonparametric linkage analyses under both a narrow phenotype model (DSM-IV OCD definite; 41 affected sib pairs) and a broad phenotype model (DSM-IV OCD definite and probable; 50 affected sib pairs). Similar to what was described by Hanna et al. (2002), our strongest findings came with the dominant parameters and the narrow phenotype model: the parametric signal peaked at marker D9S1792 with an HLOD of 2.26 ( alpha =0.59), and the nonparametric linkage signal (NPL) peaked at marker D9S1813 with an NPL of 2.52 (P=.006). These findings are striking in that D9S1813 and D9S1792 lie within 0.5 cM (<350 kb) of the original 9p24 linkage signal at D9S288; furthermore, pedigree-based association analyses also implicated the 9p24 candidate region by identifying two markers (D9S288 and GATA62F03) with modest evidence (P=.046 and .02, respectively) for association.

Normal personality traits and comorbidity among phobic, panic and major depressive disorders

High comorbidity among anxiety and depressive conditions is a consistent but not well-understood finding. The current study examines how normal personality traits relate to this comorbidity. In the Baltimore Epidemiologic Catchment Area Follow-up Study, psychiatrists administered the full Schedules for Clinical Assessment in Neuropsychiatry to 320 subjects, all of whom completed the Revised NEO Personality Inventory. The disorders of interest were simple phobia, social phobia, agoraphobia, panic disorder, and major depression. Analyses were carried out with second-order generalized estimating equations. The unadjusted summary odds ratio (SOR - or weighted mean odds ratio) for all five disorders was 1.72 (95% confidence interval=1.21-2.46). Neuroticism, introversion, younger age, and female gender were all significant predictors of prevalence of disorders. After adjustment for the relationships between these personality and demographic predictors and prevalence, the association among disorders was much weaker (SOR=1.11, 95% CI=0.79-1.56). However, subjects with high extraversion had a SOR 213% as high (95% CI=102-444%) as those with low extraversion (1.60 vs. 0.75). Therefore, neuroticism and introversion are associated with increased comorbidity due to relationships in common with the prevalence of the different disorders. In contrast, extraversion is associated with increased comorbidity per se.