Dulal K. Bhaumik

Full-Information Item Bifactor Analysis of Graded Response Data

A plausible factorial structure for many types of psychological and educational tests exhibits a general factor and one or more group or method factors. This structure can be represented by a bifactor model. The bifactor structure results from the constraint that each item has a nonzero loading on the primary dimension and, at most, one of the group factors. The authors develop estimation procedures for fitting the graded response model when the data follow the bifactor structure. Using maximum marginal likelihood estimation of item parameters, the bifactor restriction leads to a major simplification of the likelihood equations and (a) permits analysis of models with large numbers of group factors, (b) permits conditional dependence within identified subsets of items, and (c) provides more parsimonious factor solutions than an unrestricted full-information item factor analysis in some cases. Analysis of data obtained from 586 chronically mentally ill patients revealed a clear bifactor structure.

Relationship between antidepressants and suicide attempts: an analysis of the Veterans Health Administration data sets.

OBJECTIVE In late 2006, a U.S. Food and Drug Administration advisory committee recommended that the 2004 black box warning regarding suicidality in pediatric patients receiving antidepressants be extended to include young adults. This study examined the relationship between antidepressant treatment and suicide attempts in adult patients in the Veterans Administration health care system. METHOD The authors analyzed data on 226,866 veterans who received a diagnosis of depression in 2003 or 2004, had at least 6 months of follow-up, and had no history of depression from 2000 to 2002. Suicide attempt rates overall as well as before and after initiation of antidepressant therapy were compared for patients who received selective serotonin reuptake inhibitors (SSRIs), new-generation non-serotonergic-specific (non-SSRI) antidepressants (bupropion, mirtazapine, nefazodone, and venlafaxine), tricyclic antidepressants, or no antidepressant. Age group analyses were also performed. RESULTS Suicide attempt rates were lower among patients who were treated with antidepressants than among those who were not, with a statistically significant odds ratio for SSRIs and tricyclics. For SSRIs versus no antidepressant, this effect was significant in all adult age groups. Suicide attempt rates were also higher prior to treatment than after the start of treatment, with a significant relative risk for SSRIs and for non-SSRIs. For SSRIs, this effect was seen in all adult age groups and was significant in all but the 18-25 group. CONCLUSIONS These findings suggest that SSRI treatment has a protective effect in all adult age groups. They do not support the hypothesis that SSRI treatment places patients at greater risk of suicide.

Meta-Analysis of Rare Binary Adverse Event Data

We examine the use of fixed-effects and random-effects moment-based meta-analytic methods for analysis of binary adverse-event data. Special attention is paid to the case of rare adverse events that are commonly encountered in routine practice. We study estimation of model parameters and between-study heterogeneity. In addition, we examine traditional approaches to hypothesis testing of the average treatment effect and detection of the heterogeneity of treatment effect across studies. We derive three new methods, a simple (unweighted) average treatment effect estimator, a new heterogeneity estimator, and a parametric bootstrapping test for heterogeneity. We then study the statistical properties of both the traditional and the new methods via simulation. We find that in general, moment-based estimators of combined treatment effects and heterogeneity are biased and the degree of bias is proportional to the rarity of the event under study. The new methods eliminate much, but not all, of this bias. The various estimators and hypothesis testing methods are then compared and contrasted using an example dataset on treatment of stable coronary artery disease.

Post-Approval Drug Safety Surveillance

Following the drug-approval process, concerns remain regarding the safety of new drugs that are introduced into the marketplace. In the case of rare adverse events, the number of subjects that are treated in randomized controlled trials is invariably inadequate to determine the safety of the new pharmaceutical. Identifying safety signals for new and/or existing drugs is a major priority in the protection of public health. Unfortunately, design, analysis, and available data are often quite limited for detecting in a timely fashion any potentially harmful effects of drugs. In this review, we examine a variety of approaches for determining the possibility of adverse drug reactions. Our review includes spontaneous reports, meta-analysis of randomized controlled clinical trials, ecological studies, and analysis of medical claims data. We consider both experimental design and analytic problems as well as potential solutions. Many of these methodologies are then illustrated through application to data on the possible relationship between taking antidepressants and increased risk of suicidality.

Testing Parameters of a Gamma Distribution for Small Samples.

The gamma distribution is relevant to numerous areas of application in the physical, environmental, and biological sciences. The focus of this paper is on testing the shape, scale, and mean of the gamma distribution. Testing the shape parameter of the gamma distribution is relevant to failure time modeling where it can be used to determine if the failure rate is constant, increasing, or decreasing. Testing the scale parameter is also relevant to problems in survival analysis, where when the shape parameter κ=1, the reciprocal of the scale parameter measures the hazard function. Finally, testing the mean of the gamma distribution allows us to determine if the average concentration of an environmental contaminant is higher, lower, or equivalent to a health-based standard. In this paper, we first derive new small sample-based tests and then via simulation, we study the Type I error rate and statistical power of these tests. Results of these simulation studies reveal that in terms of maintaining Type I error rate, the new tests perform extremely well as long as the shape parameter is not too small, and even then the results are only slightly conservative. We illustrate the new tests using three real datasets taken from the fields of engineering, medicine, and environmental science. This article has supplementary material online.

One-Sided Approximate Prediction Intervals for at Least p of m Observations From a Gamma Population at Each of r Locations

We develop simultaneous approximate statistical prediction limits for a gamma-distributed random variable. Specifically, we develop an upper prediction limit (UPL) for p of m future samples at each of r locations, based on a previous sample of n measurements. A typical example is the environmental monitoring problem in which the distribution of an analyte of concern is typically non-Gaussian, simultaneous determinations are required for multiple locations (e.g., ground-water monitoring wells), and, in the event of an initial exceedance of the prediction limit, one or more verification samples are obtained to confirm evidence of an impact on the environment. For example, consider a ground-water monitoring program with r wells and the requirement that at least p = 1 of the m = 2 samples in each of the r wells be below the UPL. We provide derivation of simultaneous approximate gamma UPLs, illustration of the relevance of the gamma distribution to environmental data, a limited simulation study of type I and II error rates achieved using the method and comparison with normal and nonparametric alternatives, tables that aid computation, and an example using ground-water monitoring data.

Estimation and classification of fMRI hemodynamic response patterns

In this paper, we propose an approach to modeling functional magnetic resonance imaging (fMRI) data that combines hierarchical polynomial models, Bayes estimation, and clustering. A cubic polynomial is used to fit the voxel time courses of event-related design experiments. The coefficients of the polynomials are estimated by Bayes estimation, in a two-level hierarchical model, which allows us to borrow strength from all voxels. The voxel-specific Bayes polynomial coefficients are then transformed to the times and magnitudes of the minimum and maximum points on the hemodynamic response curve, which are in turn used to classify the voxels as being activated or not. The procedure is demonstrated on real data from an event-related design experiment of visually guided saccades and shown to be an effective alternative to existing methods.

DNA Methylation/Demethylation Network Expression in Psychotic Patients with a History of Alcohol Abuse

BACKGROUND Recent studies suggest that protracted and excessive alcohol use induces an epigenetic dysregulation in human and rodent brains. We recently reported that DNA methylation dynamics are altered in brains of psychotic (PS) patients, including schizophrenia and bipolar disorder patients. Because PS patients are often comorbid with chronic alcohol abuse, we examined whether the altered expression of multiple members of the DNA methylation/demethylation network observed in postmortem brains of PS patients was modified in PS patients with a history of chronic alcohol abuse. METHODS DNA-methyltransferase-1 (DNMT1) mRNA-positive neurons were counted in situ in prefrontal cortex samples obtained from the Harvard Brain Tissue Resource Center, Belmont, MA. 10-11-translocation (TETs 1, 2, 3), apolipoprotein B editing complex enzyme (APOBEC-3C), growth and DNA-damage-inducible protein 45β (GADD45β), and methyl-binding domain protein-4 (MBD4) mRNAs were measured by quantitative real-time polymerase chain reaction in inferior parietal cortical lobule samples obtained from the Stanley Foundation Neuropathology Consortium, Bethesda, MD. RESULTS We observed an increase in DNMT1 mRNA-positive neurons in PS patients compared with non-PS subjects. In addition, there was a pronounced decrease in APOBEC-3C and a pronounced increase in GADD45β and TET1 mRNAs in PS patients with no history of alcohol abuse. In PS patients with a history of chronic alcohol abuse, the numbers of DNMT1-positive neurons were not increased significantly. Furthermore, the decrease in APOBEC-3C mRNA was less pronounced, while the increase in TET1 mRNA had a tendency to be potentiated in those PS patients that were chronic alcohol abusers. GADD45β and MBD4 mRNAs were not influenced by alcohol abuse. The effect of chronic alcohol abuse on DNA methylation/demethylation network enzymes cannot be attributed to confounding demographic variables or to the type and dose of medication used. CONCLUSIONS Based on these results, we hypothesize that PS patients may abuse alcohol as a potential attempt at self-medication to normalize altered DNA methylation/demethylation network pathways. However, before accepting this conclusion, we need to study alterations in the DNA methylation/demethylation pathways and the DNA methylation dynamics in a substantial number of alcoholic PS and non-PS patients. Additional investigation may also be necessary to determine whether the altered DNA methylation dynamics are direct or the consequence of an indirect interaction of alcohol with the neuropathogenetic mechanisms underlying psychosis.

Mixed-effects Poisson regression analysis of adverse event reports: The relationship between antidepressants and suicide

A new statistical methodology is developed for the analysis of spontaneous adverse event (AE) reports from post-marketing drug surveillance data. The method involves both empirical Bayes (EB) and fully Bayes estimation of rate multipliers for each drug within a class of drugs, for a particular AE, based on a mixed-effects Poisson regression model. Both parametric and semiparametric models for the random-effect distribution are examined. The method is applied to data from Food and Drug Administration (FDA)s Adverse Event Reporting System (AERS) on the relationship between antidepressants and suicide. We obtain point estimates and 95 per cent confidence (posterior) intervals for the rate multiplier for each drug (e.g. antidepressants), which can be used to determine whether a particular drug has an increased risk of association with a particular AE (e.g. suicide). Confidence (posterior) intervals that do not include 1.0 provide evidence for either significant protective or harmful associations of the drug and the adverse effect. We also examine EB, parametric Bayes, and semiparametric Bayes estimators of the rate multipliers and associated confidence (posterior) intervals. Results of our analysis of the FDA AERS data revealed that newer antidepressants are associated with lower rates of suicide adverse event reports compared with older antidepressants. We recommend improvements to the existing AERS system, which are likely to improve its public health value as an early warning system.

Weighted Random-Effects Regression Models With Application to Interlaboratory Calibration

In this article, we present a general random-effects regression model for the case of heteroscedastic measurement errors. The model is both motivated by and illustrated with a problem from analytical chemistry in which measurement errors are constant for near-zero concentrations and increase proportionally with higher concentrations. The parameters of the calibration curve that relate instrument responses to true concentration are allowed to vary over laboratories. The estimation of model parameters is accomplished by iteratively reweighted maximum marginal likelihood estimation. Properties of the method are examined in a limited simulation study and are applied to a typical interlaboratory calibration example for copper in distilled water. We illustrate a few applications of the model that include (1) determining if an analyte is present in a new sample, (2) approximate confidence bounds for true concentration given a new measurement, and (3) determination of the minimum concentration that supports quantitative determination.