Analyzing Binary Outcome Data with Small Clusters: A Simulation Study

Binary outcome data with small clusters often arise in medical studies and the size of clusters might be informative of the outcome. The authors conducted a simulation study to examine the performance of a range of statistical methods. The simulation results showed that all methods performed mostly comparable in the estimation of covariate effects. However, the standard logistic regression approach that ignores the clustering encountered an undercoverage problem when the degree of clustering was nontrivial. The performance of random-effects logistic regression approach tended to be affected by low disease prevalence, relatively small cluster size, or informative cluster size.     

On ℓ-overlapping Runs of Ones of Length k in Sequences of Independent Binary Random Variables

Consider a finite sequence of independent binary (zero-one) random variables ordered on a line or on a circle. The number of the ?-overlapping runs of ones of a fixed length k is studied for both types of the concerned ordering. Recurrences for the exact probability mass functions for these numbers are obtained via simple probabilistic arguments. Exact closed formulae, for the mean and variance of the studied numbers are obtained via their representations through properly defined indicators. Two application case studies, concerning record sequences and reliability of consecutive systems, clarify further the theoretical results.     

On threshold BDDs and the optimal variable ordering problem

Many combinatorial optimization problems can be formulated as 0/1 integer programs (0/1 IPs). The investigation of the structure of these problems raises the following tasks: count or enumerate the feasible solutions and find an optimal solution according to a given linear objective function. All these tasks can be accomplished using binary decision diagrams (BDDs), a very popular and effective datastructure in computational logics and hardware verification. We present a novel approach for these tasks which consists of an output-sensitive algorithm for building a BDD for a linear constraint (a so-called threshold BDD) and a parallel AND operation on threshold BDDs. In particular our algorithm is capable of solving knapsack problems, subset sum problems and multidimensional knapsack problems. BDDs are represented as a directed acyclic graph. The size of a BDD is the number of nodes of its graph. It heavily depends on the chosen variable ordering. Finding the optimal variable ordering is an NP-hard problem. We derive a 0/1 IP for finding an optimal variable ordering of a threshold BDD. This 0/1 IP formulation provides the basis for the computation of the variable ordering spectrum of a threshold function. We introduce our new tool azove 2.0 as an enhancement to azove 1.1 which is a tool for counting and enumerating 0/1 points. Computational results on benchmarks from the literature show the strength of our new method.     

Panel Binary Variables and Sufficiency: Generalizing Conditional Logit

This paper extends the conditional logit approach (Rasch, Andersen, Chamberlain) used in panel data models of binary variables with correlated fixed effects and strictly exogenous regressors. In a two‐period two‐state model, necessary and sufficient conditions on the joint distribution function of the individual‐and‐period specific shocks are given such that the sum of individual binary variables across time is a sufficient statistic for the individual effect. By extending a result of Chamberlain, it is shown that root‐n consistent regular estimators can be constructed in panel binary models if and only if the property of sufficiency holds. In applied work, the estimation method amounts to quasi‐differencing the binary variables as if they were continuous variables and transforming a panel data model into a cross‐section model. Semiparametric approaches can then be readily applied.     

Robust binary regression with continuous outcomes

The authors propose a robust bounded‐influence estimator for binary regression with continuous outcomes, an alternative to logistic regression when the investigator's interest focuses on the proportion of subjects who fall below or above a cut‐off value. The authors show both theoretically and empirically that in this context, the maximum likelihood estimator is sensitive to model misspecifications. They show that their robust estimator is more stable and nearly as efficient as maximum likelihood when the hypotheses are satisfied. Moreover, it leads to safer inference. The authors compare the different estimators in a simulation study and present an analysis of hypertension on Harlem survey data.     

Model selection in spline nonparametric regression

A Bayesian approach is presented for model selection in nonparametric regression with Gaussian errors and in binary nonparametric regression. A smoothness prior is assumed for each component of the model and the posterior probabilities of the candidate models are approximated using the Bayesian information criterion. We study the model selection method by simulation and show that it has excellent frequentist properties and gives improved estimates of the regression surface. All the computations are carried out efficiently using the Gibbs sampler.     

Functional-coefficient cointegration models in the presence of deterministic trends

In this article, we extend the functional-coefficient cointegration model (FCCM) to the cases in which nonstationary regressors contain both stochastic and deterministic trends. A nondegenerate distributional theory on the local linear (LL) regression smoother of the FCCM is explored. It is demonstrated that even when integrated regressors are endogenous, the limiting distribution is the same as if they were exogenous. Finite-sample performance of the LL estimator is investigated via Monte Carlo simulations in comparison with an alternative estimation method. As an application of the FCCM, electricity demand analysis in Illinois is considered.     

The effect of dependence in a binary sequence on tests for a changepoint or a changed segment

The effect of partial dependence in a binary sequence on tests for the presence of a changepoint or changed segment are investigated and exemplified in the context of modelling non-coding deoxyribonucleic acid (DNA). For the levels of dependence that are commonly seen in such DNA, the null distributions of the test statistics are approximately correct and so conclusions based on them are still valid. A strong dependence would, however, invalidate the use of such procedures.     

Detection of patterns in noisy time series

In the context of a research project in ergonomy, myoelectric signals monitored over two to three hour periods gave rise to long noisy time series, which were smoothed using running medians. Tests developed by the authors show that the patterns displayed by the smoothed time series are not artifacts of smoothed white noise. Indeed, the smoothed series show amplitude fluctuations and short‐term correlations which are larger than those obtained by applying running medians to independent, identically distributed data. The key idea is that of reduction of data to binary signals.     

The effect of verification bias on the comparison of predictive values of two binary diagnostic tests

The comparison of the accuracy of two binary diagnostic tests has traditionally required knowledge of the disease status in all of the patients in the sample via the application of a gold standard. In practice, the gold standard is not always applied to all patients in a sample, and the problem of partial verification of the disease arises. The accuracy of a binary diagnostic test can be measured in terms of positive and negative predictive values, which represent the accuracy of a diagnostic test when it is applied to a cohort of patients. In this paper, we deduce the maximum likelihood estimators of predictive values (PVs) of two binary diagnostic tests, and the hypothesis tests to compare these measures when, in the presence of partial disease verification, the verification process only depends on the results of the two diagnostic tests. The effect of verification bias on the naïve estimators of PVs of two diagnostic tests is studied, and simulation experiments are performed in order to investigate the small sample behaviour of hypothesis tests. The hypothesis tests which we have deduced can be applied when all of the patients are verified with the gold standard. The results obtained have been applied to the diagnosis of coronary stenosis.