A comparison study on modeling of clustered and overdispersed count data for multiple comparisons

Data collected in various scientific fields are count data. One way to analyze such data is to compare the individual levels of the factor treatment using multiple comparisons. However, the measured individuals are often clustered - e.g. according to litter or rearing. This must be considered when estimating the parameters by a repeated measurement model. In addition, ignoring the overdispersion to which count data is prone leads to an increase of the type one error rate. We carry out simulation studies using several different data settings and compare different multiple contrast tests with parameter estimates from generalized estimation equations and generalized linear mixed models in order to observe coverage and rejection probabilities. We generate overdispersed, clustered count data in small samples as can be observed in many biological settings. We have found that the generalized estimation equations outperform generalized linear mixed models if the variance-sandwich estimator is correctly specified. Furthermore, generalized linear mixed models show problems with the convergence rate under certain data settings, but there are model implementations with lower implications exists. Finally, we use an example of genetic data to demonstrate the application of the multiple contrast test and the problems of ignoring strong overdispersion.

Simultaneous inference for multiple marginal generalized estimating equation models

Motivated by small-sample studies in ophthalmology and dermatology, we study the problem of simultaneous inference for multiple endpoints in the presence of repeated observations. We propose a framework in which a generalized estimating equation model is fit for each endpoint marginally, taking into account dependencies within the same subject. The asymptotic joint normality of the stacked vector of marginal estimating equations is used to derive Wald-type simultaneous confidence intervals and hypothesis tests for multiple linear contrasts of regression coefficients of the multiple marginal models. The small sample performance of this approach is improved by a bias adjustment to the estimate of the joint covariance matrix of the regression coefficients from multiple models. As a further small sample improvement a multivariate t-distribution with appropriate degrees of freedom is specified as reference distribution. In addition, a generalized score test based on the stacked estimating equations is derived. Simulation results show strong control of the family-wise type I error rate for these methods even with small sample sizes and increased power compared to a Bonferroni-Holm multiplicity adjustment. Thus, the proposed methods are suitable to efficiently use the information from repeated observations of multiple endpoints in small-sample studies.

A unifying framework for robust association testing, estimation, and genetic model selection using the generalized linear model

The analysis of genome-wide genetic association studies generally starts with univariate statistical tests of each single-nucleotide polymorphism. The standard approach is the Cochran-Armitage trend test or its logistic regression equivalent although this approach can lose considerable power if the underlying genetic model is not additive. An alternative is the MAX test, which is robust against the three basic modes of inheritance. Here, the asymptotic distribution of the MAX test is derived using the generalized linear model together with the Delta method and multiple contrasts. The approach is applicable to binary, quantitative, and survival traits. It may be used for unrelated individuals, family-based studies, and matched pairs. The approach provides point and interval effect estimates and allows selecting the most plausible genetic model using the minimum P-value. R code is provided. A Monte-Carlo simulation study shows that the asymptotic MAX test framework meets type I error levels well, has good power, and good model selection properties for minor allele frequencies ≥0.3. Pearson's χ(2)-test is superior for lower minor allele frequencies with low frequencies for the rare homozygous genotype. In these cases, the model selection procedure should be used with caution. The use of the MAX test is illustrated by reanalyzing findings from seven genome-wide association studies including case-control, matched pairs, and quantitative trait data.

Human embryonic stem cell-derived test systems for developmental neurotoxicity: a transcriptomics approach

Developmental neurotoxicity (DNT) and many forms of reproductive toxicity (RT) often manifest themselves in functional deficits that are not necessarily based on cell death, but rather on minor changes relating to cell differentiation or communication. The fields of DNT/RT would greatly benefit from in vitro tests that allow the identification of toxicant-induced changes of the cellular proteostasis, or of its underlying transcriptome network. Therefore, the ‘human embryonic stem cell (hESC)-derived novel alternative test systems (ESNATS)’ European commission research project established RT tests based on defined differentiation protocols of hESC and their progeny. Valproic acid (VPA) and methylmercury (MeHg) were used as positive control compounds to address the following fundamental questions: (1) Does transcriptome analysis allow discrimination of the two compounds? (2) How does analysis of enriched transcription factor binding sites (TFBS) and of individual probe sets (PS) distinguish between test systems? (3) Can batch effects be controlled? (4) How many DNA microarrays are needed? (5) Is the highest non-cytotoxic concentration optimal and relevant for the study of transcriptome changes? VPA triggered vast transcriptional changes, whereas MeHg altered fewer transcripts. To attenuate batch effects, analysis has been focused on the 500 PS with highest variability. The test systems differed significantly in their responses (<20 % overlap). Moreover, within one test system, little overlap between the PS changed by the two compounds has been observed. However, using TFBS enrichment, a relatively large ‘common response’ to VPA and MeHg could be distinguished from ‘compound-specific’ responses. In conclusion, the ESNATS assay battery allows classification of human DNT/RT toxicants on the basis of their transcriptome profiles.

Testing strategies in multi-dose experiments including active control

Inferential test strategies for multi-arm trials are adapted or proposed for the special situation when more than one dose of a test treatment, placebo and active control(s) are compared. This includes between doses, dose-placebo and dose-active-control comparisons. The procedures refer to situations when detailed comparisons make sense only if the sensitivity of the trial has been shown, for example, if a dose-response relationship or a difference between active control and placebo has been established. Split strategies, hierarchical (assuming an order restriction among doses) or linked procedures are introduced. In linked procedures, equivalence to the active control will be established only if the dose is also shown to be effective as compared to placebo. All the inferential procedures control the experimentwise error rate in the strong sense for the respective sets of null hypotheses considered.

Teleradiology: results of a questionnaire of German radiologists

A questionnaire was sent by mail to 4400 radiologists (i.e. to at least 1000 radiological institutions). The response rate was about 5%. The results showed that 47% of respondents felt well informed about teleradiology, 49% not enough and 3% not at all. Image and report transfer as well as interfaces to reference databases, educational applications, technical quality surveillance and product support (maintenance) were considered to be increasingly important areas. Smaller institutions (1-3 doctors) judged expert consultation as more important than bigger institutions. Standardization, system stability and data security were demanded as well as guidelines, for example concerning the linking of report and image, correct documentation and required image quality. Technically most demands can be fulfilled today but this technology is not yet commonly included in teleradiology systems.

Biostatistical analysis of the micronucleus mutagenicity assay based on the assumption of a mixing distribution

The in vivo micronucleus assay can be analyzed by comparing the number of micronuclei (MN) of several dose groups with those of a control group. In several publications, difficulties arose in estimating a suitable distribution for MN, even in the untreated historical control groups. Mitchell et al. described the presence of a subpopulation of more susceptible responders. Based on this assumption of such a subpopulation, score tests were used for the mixing distribution of responders and nonresponders (behavior same as in untreated control animals) within the dose groups. The power behavior of these tests was characterized with a simulation study. The advantage of score tests can be shown, even in the practical and important guideline case of only five animals per group.

Multiple comparisons in long-term toxicity studies

Several multiple comparison procedures (MCPs) are discussed in relation to the specific formulation of type I and type II errors in toxicity studies and the typical one-way design control versus k treatment/dose groups. Examples for these MCPs are: the standard many-to-one MCP (Dunnett's procedure), sequential rejection modifications, closed testing procedures, many-to-one MCPs with an ordered alternative hypothesis, procedures based on the assumption of a mixing distribution of responders and nonresponders, and MCP's for multiple end points.

Tumor induction in a rat model for ureterosigmoidostomy without evidence of nitrosamine formation

Twenty rats were randomized into a vesicosigmoidostomy and an unoperated control group. In both groups the 24 hour excretion of secondary amines, nitrate, nitrite and nitrosamines was measured before and after gavage of proline and nitrate, piperazine and nitrate, N-nitrosoproline, mono-N-nitrosopiperazine. The urinary nitrosamine concentrations were not significantly different between both groups neither before nor after application of the several substances. Thirty rats were randomized into two vesicosigmoidostomy groups with and without antibiotic coverage and an unoperated control group. After ligation of distal rectum and mesosigmoid the rectosigmoids were removed. No significant concentrations of volatile nitrosamines could be measured in the rectosigmoid contents of the three groups. One hundred and twenty rats randomized into three groups following vesicosigmoidostomy received the potential nitrosamine antidotes sodium-2-mercaptoethane sulfonate or sodiumpentosan-polysulfate or acted as controls. 12/118 (10.2%) developed adenomas and 25/118 (21.2%) adenocarcinomas at the vesico-colonic anastomosis with no significant differences between the three groups concerning tumor incidence or mortality. The results show that colon carcinomas occur in a rat model for ureterosigmoidostomy without evidence for thus induced nitrosamine formation. This and the missing effect of nitrosamine antidotes suggest that other factors than nitrosation must be responsible for colon carcinogenesis following urinary diversion via intestine.