A new class of modified binomial distributions with applications to certain toxicological experiments ∗

A large class of distributions is proposed to fit the binary data obtained from certain toxicological experiments in which, for example, the outcome of interest is the occurrence of dead or malformed fetuses in a litter. This class of distribution includes the additive model proposed by Altham (1978) as a special case. The fits to three real-life data sets using this new distribution are shown to be much better than those provided by beta-binomial distribution used by Williams (1975) and by the correlated-binomial distribution proposed by Kupper and Haseman (1978).     

A Threshold Dose-Response Model with Random Effects in Teratological Experiments

Abstract

Teratological experiments are controlled dose-response studies in which impregnated animals are randomly assigned to various exposure levels of a toxic substance. Subsequently, both continuous and discrete responses are recorded on the litters of fetuses that these animals produce. Discrete responses are usually binary in nature, such as the presence or absence of some fetal anomaly. This clustered binary data usually exhibits over-dispersion (or under-dispersion), which can be interpreted as either variation between litter response probabilities or intralitter correlation. To model the correlation and/or variation, the beta-binomial distribution has been assumed for the number of positive fetal responses within a litter. Although the mean of the beta-binomial model has been linked to dose-response functions, in terms of measuring over-dispersion, it may be a restrictive method in modeling data from teratological studies. Also for certain toxins, a threshold effect has been observed in the dose-response pattern of the data. We propose to incorporate a random effect into a general threshold dose-response model to account for the variation in responses, while at the same time estimating the threshold effect. We fit this model to a well-known data set in the field of teratology. Simulation studies are performed to assess the validity of the random effects threshold model in these types of studies.     

Estimation of the Parameters of a Clumped Binomial Model via the EM Algorithm

Binary-response data arise in teratology and mutagenicity studies in which each treatment is applied to a group of litters. In a large experiment, a contingency table can be constructed to test the treatment X litter size interaction (see Kastenbaum and Lamphiear 1959). In situations in which there is a clumped category, as in the Kastenbaum and Lamphiear mice-depletion data, a clumped binomial model (Koch et al. 1976) or a clumped beta-binomial model (Paul 1979) can be used to analyze these data. When a clumped binomial model is appropriate, the maximum likelihood estimates of the parameters of the model under the hypothesis of no treatment X litter size interaction, as well as under the hypothesis of the said interaction, can be estimated via the EM algorithm for computing maximum likelihood estimates from incomplete data (Dempster et al. 1977). In this article the EM algorithm is described and used to test treatment X litter size interaction for the Kastenbaum and Lamphiear data and for a set of data given in Luning et al. (1966).     

Effects of correlation in modeling clustered binary data

A simulation study is conducted to determine the effects of varying correlation structures on two estimation procedures used to model clustered binary data; a parametric model, the beta-binomial, and a non-parametric model, the exchangeable binary. The simulations detected bias in estimation of the mean response parameter and the correlation parameter when assuming a parametric model. In addition it was found that variance parameters can be severely underestimated if the correlation structure is considered strictly a nuisance parameter.     

Optimal designs for beta-binomial logistic regression models

Optimal designs for a logistic regression model with over-dispersion introduced by a beta-binomial distribution are characterized. Designs are defined by a set of design points and design weights as usual but, in addition, the experimenter must also make a choice of a sub-sampling design specifying the distribution of observations on sample sizes. In an earlier work it has been shown that Ds-optimal sampling designs for estimation of the parameters of the beta-binomial distribution are supported on at most two design points. This admits a simplified approach using single sample sizes. Linear predictor values for Ds-optimal designs using a common sample size are tabulated for different levels of over-dispersion and choice of subsets of parameters.     

An empirical investigation of different operating characteristics of several estimators of the intraclass correlation in the analysis of binary data

This paper is concerned with properties (bias, standard deviation, mean square error and efficiency) of twenty six estimators of the intraclass correlation in the analysis of binary data. Our main interest is to study these properties when data are generated from different distributions. For data generation we considered three over-dispersed binomial distributions, namely, the beta-binomial distribution, the probit normal binomial distribution and a mixture of two binomial distributions. The findings regarding bias, standard deviation and mean squared error of all these estimators, are that (a) in general, the distributions of biases of most of the estimators are negatively skewed. The biases are smallest when data are generated from the beta-binomial distribution and largest when data are generated from the mixture distribution; (b) the standard deviations are smallest when data are generated from the beta-binomial distribution; and (c) the mean squared errors are smallest when data are generated from the beta-binomial distribution and largest when data are generated from the mixture distribution. Of the 26, nine estimators including the maximum likelihood estimator, an estimator based on the optimal quadratic estimating equations of Crowder (1987), and an analysis of variance type estimator is found to have least amount of bias, standard deviation and mean squared error. Also, the distributions of the bias, standard deviation and mean squared error for each of these estimators are, in general, more symmetric than those of the other estimators. Our findings regarding efficiency are that the estimator based on the optimal quadratic estimating equations has consistently high efficiency and least variability in the efficiency results. In the important range in which the intraclass correlation is small (≤0 5), on the average, this estimator shows best efficiency performance. The analysis of variance type estimator seems to do well for larger values of the intraclass correlation. In general, the estimator based on the optimal quadratic estimating equations seems to show best efficiency performance for data from the beta-binomial distribution and the probit normal binomial distribution, and the analysis of variance type estimator seems to do well for data from the mixture distribution.     

The power of the fisher permutation test in 2 × k tables

The power of the Fisher permutation test extended to 2 × k tables is evaluated unconditionally as a function of the under-lying cell probabilities in the table. These results are then applied in assessing the sensitivity of two-generation cancer bioassays in which a fixed number of pups from each litter born in the first generation are selected to continue on test in the second generation. In this case, the two rows of the table correspond to two treatment groups and the k columns correspond to the number of animals responding in a litter. The cell probabilities in this application are based on a suitable beta-binomial superpopulation model.     

Simulations to improve experimental designs for u-shaped dose-response modeling

This paper investigates the results of simulations from which clustered binary dose-response data are generated. This data mimics the type of discrete data collected from experiments conducted in developmental toxicity studies on animals. In particular one assumption used in the design of these simulations is that hormesis exists, as evidenced by the dose-response pattern of the generated data. This implies the existence of a threshold level, as hormesis, if it exists, would exist below this level. Below the threshold level, no adverse effects above the response at the control dose level should exist. While hormesis implies several dose-response patterns below threshold, in this paper, the hormetic pattern is assumed to be U-shaped. Improving upon the design of current and past developmental studies, these simulations also include designs in which dose levels and litters (clusters of animals) are allocated in a way that increases the power for detecting hormesis, assuming it exists. The beta-binomial distribution is used to model the clustered binary data that results from responses of animals in the same litter. The results of these simulations will indicate that by altering current designs of developmental studies, this improves the ability to detect hormesis.     

Two Conditionally Specified Mixed Binomial Distributions

Two generalized hypergeometric distributions are identified as mixed binomial distributions by conditional specification. Both distributions show profiles that are not possible in other mixed binomial distributions such as the beta-binomial distribution. A simulation study illustrates that beta-binomial distribution is more precise to fit data with usual profiles but the two distributions presented can improve the capability of fitting data in other less common scenes.     

Comparison of dichotomized and distributional approaches in rare event clinical trial design: a fixed Bayesian design

This research was motivated by our goal to design an efficient clinical trial to compare two doses of docosahexaenoic acid supplementation for reducing the rate of earliest preterm births (ePTB) and/or preterm births (PTB). Dichotomizing continuous gestational age (GA) data using a classic binomial distribution will result in a loss of information and reduced power. A distributional approach is an improved strategy to retain statistical power from the continuous distribution. However, appropriate distributions that fit the data properly, particularly in the tails, must be chosen, especially when the data are skewed. A recent study proposed a skew-normal method. We propose a three-component normal mixture model and introduce separate treatment effects at different components of GA. We evaluate operating characteristics of mixture model, beta-binomial model, and skew-normal model through simulation. We also apply these three methods to data from two completed clinical trials from the USA and Australia. Finite mixture models are shown to have favorable properties in PTB analysis but minimal benefit for ePTB analysis. Normal models on log-transformed data have the largest bias. Therefore we recommend finite mixture model for PTB study. Either finite mixture model or beta-binomial model is acceptable for ePTB study.     

A statistical problem arising in ascertainment

In this paper, an alternative model is examined for the distribution arising out of ascertainment. The weighted beta-binomial is suggested for this purpose as it incorporates the variability in the parameter ø of the weighted binomial distribution. The latter distribution has been the model considered by Rao (1965, 1985) and Kocherlakota and Kocherlakota (1990). Techniques for separate families introduced in Kocherlakota and Kocherlakota (1986) are applied to demonstrate that the weighted beta-binomial model is more appropriate in this situation.     

New Confidence Intervals for the Proportion of Interest in One-Sample Correlated Binary Data

Correlated binary data is obtained in many fields of biomedical research. When constructing a confidence interval for the proportion of interest, asymptotic confidence intervals have already been developed. However, such asymptotic confidence intervals are unreliable in small samples. To improve the performance of asymptotic confidence intervals in small samples, we obtain the Edgeworth expansion of the distribution of the studentized mean of beta-binomial random variables. Then, we propose new asymptotic confidence intervals by correcting the skewness in the Edgeworth expansion in one direct and two indirect ways. New confidence intervals are compared with the existing confidence intervals in simulation studies.     

Adaptive Percolation Using Subjective Likelihoods

A phenomenon that I call “adaptive percolation” commonly arises in biology, business, economics, defense, finance, manufacturing, and the social sciences. Here one wishes to select a handful of entities from a large pool of entities via a process of screening through a hierarchy of sieves. The process is not unlike the percolation of a liquid through a porous medium. The probability model developed here is based on a nested and adaptive Bayesian approach that results in the product of beta-binomial distributions with common parameters. The common parameters happen to be the observed data. I call this the percolated beta-binomial distribution . The model turns out to be a slight generalization of the probabilistic model used in percolation theory. The generalization is a consequence of using a subjectively specified likelihood function to construct a probability model. The notion of using likelihoods for constructing probability models is not a part of the conventional toolkit of applied probabilists. To the best of my knowledge, a use of the product of beta-binomial distributions as a probability model for Bernoulli trials appears to be new. The development of the material of this article is illustrated via data from the 2009 astronaut selection program, which motivated this work.     

Empirical-distribution-function Tests for the Beta-Binomial Model

Empirical-distribution-function (EDF) goodness-of-fit tests are considered for the beta-binomial model. The testing procedures based on EDF statistics are given. A Monte Carlo study is conducted to investigate the accuracy and power of the tests against various alternative distributions. Our method is found to produce considerably greater power than that of Garren et al. (2001) in most cases. The tests are applied to data sets of the foraging behavior of herons and environmental toxicity studies.     

Bayesian Estimation and Prediction for the Beta-Binomial Model

The beta-binomial distribution, which is generated by a simple mixture model, has been widely applied in the social, physical, and health sciences. Problems of estimation, inference, and prediction have been addressed in the past, but not in a Bayesian framework. This article develops Bayesian procedures for the beta-binomial model and, using a suitable reparameterization, establishes a conjugate-type property for a beta family of priors. The transformed parameters have interesting interpretations, especially in marketing applications, and are likely to be more stable. More specifically, one of these parameters is the market share and the other is a measure of the heterogeneity of the customer population. Analytical results are developed for the posterior and prediction quantities, although the numerical evaluation is not trivial. Since the posterior moments are more easily calculated, we also propose the use of posterior approximation using the Pearson system. A particular case (when there are two trials), which occurs in taste testing, brand choice, media exposure, and some epidemiological applications, is analyzed in detail. Simulated and real data are used to demonstrate the feasibility of the calculations. The simulation results effectively demonstrate the superiority of Bayesian estimators, particularly in small samples, even with uniform (“non-informed”) priors. Naturally, “informed” priors can give even better results. The real data on television viewing behavior are used to illustrate the prediction results. In our analysis, several problems with the maximum likelihood estimators are encountered. The superior properties and performance of the Bayesian estimators and the excellent approximation results are strong indications that our results will be potentially of high value in small sample applications of the beta-binomial and in cases in which significant prior information exists.     

A generalized estimating equation approach to modelling foetal response in developmental toxicity studies when the number of implants is dose dependent

Summary. In developmental toxicity studies with exposure before implantation, the toxin that is used may interfere with the early reproductive process and prevent the implantation of some foetuses that would otherwise have been formed. A manifestation of this effect is a decreasing trend in the number of implants per dam as the dose level increases. Because unformed foetuses are not observable, Dunson proposed a multiple-imputation approach to estimate the number of missing foetuses. We propose instead to build a model for observable quantities only, namely the observed litter sizes and the observed numbers of deaths or malformations within litters. Using the probabilistic concept of thinning, we express the probability that a foetus fails to implant in terms of the parameters of the litter size distribution. Estimation is by means of generalized estimating equations and takes into account underdispersion of the observed litter sizes and overdispersion of the numbers of foetal deaths or malformations. A combined risk measure that takes into account not just post-implantation death or malformation but also the possibility of failure to implant is proposed and used to determine the virtually safe dose VSD. It is demonstrated numerically and graphically that ignoring the possibility of unformed foetuses leads to estimates of VSD that are too liberal. The proposed generalized estimating equation approach to estimating VSD and finding lower confidence limits is found to work well in a simulation study. We apply the proposed method to two data sets and compare the results that are obtained with those of existing studies.     

Parameter estimation for the dirichlet-multinomial distribution using supplementary beta-binomial data

We develop estimates for the parameters of the Dirichlet-multinomial distribution (DMD) when there is insufficient data to obtain maximum likelihood or method of moment estimates known in the literature. We do, however, have supplemetary beta-binomial data pertaining to the marginals of the DMD, and use these data when estimating the DMD parameters. A real situation and data set are given where our estimates are applicable.     

PARAMETER ESTIMATION AND APPLICATIONS FOR A GENERALISATION OF THE BETA-BINOMIAL DISTRIBUTION

A three-parameter generalisation of the beta-binomial distribution (BBD) derived by Chandon (1976) is examined. We obtain the maximum likelihood estimates of the parameters and give the elements of the information matrix. To exhibit the applicability of the generalised distribution we show how it gives an improved fit over the BBD for magazine exposure and consumer purchasing data. Finally we derive an empirical Bayes estimate of a binomial proportion based on the generalised beta distribution used in this study.     

TEST FOR TREATMENT EFFECT BASED ON BINARY DATA WITH RANDOM SAMPLE SIZES

The problem of testing for treatment effect based on binary response data is considered, assuming that the sample size for each experimental unit and treatment combination is random. It is assumed that the sample size follows a distribution that belongs to a parametric family. The uniformly most powerful unbiased tests, which are equivalent to the likelihood ratio tests, are obtained when the probability of the sample size being zero is positive. For the situation where the sample sizes are always positive, the likelihood ratio tests are derived. These test procedures, which are unconditional on the random sample sizes, are useful even when the random sample sizes are not observed. Some examples are presented as illustration.     

A new sequential approximation method

A sequential method for estimating the expected value of a random variable is proposed. Using a parametric model, the updating formula is based on the maximum likelihood estimators of the roots of the expected value function. Under certain conditions, it is demonstrated that the estimators of the roots are consistent, when a two-parameter logit model version of the procedure is used for binary data. In addition, the estimators of the logit parameters have an asymptotic normal distribution. A simulation study is performed to evaluate the effectiveness of the new method for small to medium sample sizes. Compared to other sequential approximation methods, the proposed method performed well, especially when estimating several roots simultaneously.