Usual and Shortest Confidence Intervals on Odds Ratios from Logistic Regression

Based on the large-sample normal distribution of the sample log odds ratio and its asymptotic variance from maximum likelihood logistic regression, shortest 95% confidence intervals for the odds ratio are developed. Although the usual confidence interval on the odds ratio is unbiased, the shortest interval is not. That is, while covering the true odds ratio with the stated probability, the shortest interval covers some values below the true odds ratio with higher probability. The upper and lower limits of the shortest interval are shifted to the left of those of the usual interval, with greater shifts in the upper limits. With the log odds model γ + Xβ, in which X is binary, simulation studies showed that the approximate average percent difference in length is 7.4% for n (sample size) = 100, and 3.8% for n = 200. Precise estimates of the covering probabilities of the two types of intervals were obtained from simulation studies, and are compared graphically. For odds ratio estimates greater (less) than one, shortest intervals are more (less) likely to include one than are the usual intervals. The usual intervals are likelihood-based and the shortest intervals are not. The usual intervals have minimum expected length among the class of unbiased intervals. Shortest intervals do not provide important advantages over the usual intervals, which we recommend for practical use.     

Estimating a Marginal Causal Odds Ratio Subject to Confounding

Odds ratios are frequently used to describe the relationship between a binary treatment or exposure and a binary outcome. An odds ratio can be interpreted as a causal effect or a measure of association, depending on whether it involves potential outcomes or the actual outcome. An odds ratio can also be characterized as marginal versus conditional, depending on whether it involves conditioning on covariates. This article proposes a method for estimating a marginal causal odds ratio subject to confounding. The proposed method is based on a logistic regression model relating the outcome to the treatment indicator and potential confounders. Simulation results show that the proposed method performs reasonably well in moderate-sized samples and may even offer an efficiency gain over the direct method based on the sample odds ratio in the absence of confounding. The method is illustrated with a real example concerning coronary heart disease.     

Bayesian Inference of Odds Ratios in Misclassified Binary Data with a Validation Substudy

We propose a fully Bayesian model with a non-informative prior for analyzing misclassified binary data with a validation substudy. In addition, we derive a closed-form algorithm for drawing all parameters from the posterior distribution and making statistical inference on odds ratios. Our algorithm draws each parameter from a beta distribution, avoids the specification of initial values, and does not have convergence issues. We apply the algorithm to a data set and compare the results with those obtained by other methods. Finally, the performance of our algorithm is assessed using simulation studies.     

Reducing Bias and Mean Squared Error Associated With Regression-Based Odds Ratio Estimators

Ratio estimators of effect are ordinarily obtained by exponentiating maximum-likelihood estimators (MLEs) of log-linear or logistic regression coefficients. These estimators can display marked positive finite-sample bias, however. We propose a simple correction that removes a substantial portion of the bias due to exponentiation. By combining this correction with bias correction on the log scale, we demonstrate that one achieves complete removal of second-order bias in odds ratio estimators in important special cases. We show how this approach extends to address bias in odds or risk ratio estimators in many common regression settings. We also propose a class of estimators that provide reduced mean bias and squared error, while allowing the investigator to control the risk of underestimating the true ratio parameter. We present simulation studies in which the proposed estimators are shown to exhibit considerable reduction in bias, variance, and mean squared error compared to MLEs. Bootstrapping provides further improvement, including narrower confidence intervals without sacrificing coverage.     

Subject-specific odds ratios in binomial GLMMs with continuous response

In a regression context, the dichotomization of a continuous outcome variable is often motivated by the need to express results in terms of the odds ratio, as a measure of association between the response and one or more risk factors. Starting from the recent work of Moser and Coombs (Stat Med 23:1843–1860, 2004) in this article we explore in a mixed model framework the possibility of obtaining odds ratio estimates from a regression linear model without the need of dichotomizing the response variable. It is shown that the odds ratio estimators derived from a linear mixed model outperform those from a binomial generalized linear mixed model, especially when the data exhibit high levels of heterogeneity.     

Bayesian Estimation of the Number of Change Points in Simple Linear Regression Models

A Bayesian approach is considered to detect the number of change points in simple linear regression models. A normal-gamma empirical prior for the regression parameters based on maximum likelihood estimator (MLE) is employed in the analysis. Under mild conditions, consistency for the number of change points and boundedness between the estimated location and the true location of the change points are established. The Bayesian approach to the detection of the number of change points is suitable whether the switching simple regression is continuous or discontinuous. Some simulation results are given to confirm the accuracy of the proposed estimator.     

Notes on Test Homogeneity of the Odds Ratio in Matched Pairs Under Stratified Sampling: A Monte Carlo Evaluation

Using Monte Carlo simulation, we compare the performance of five asymptotic test procedures and a randomized permutation test procedure for testing the homogeneity of odds ratio under the stratified matched-pair design. We note that the weighted-least-square test procedure is liberal, while Pearson's goodness-of-fit (PGF) test procedure with the continuity correction is conservative. We note that PGF without the continuity correction, the conditional likelihood ratio test procedure, and the randomized permutation test procedure can generally perform well with respect to Type I error. We use the data taken from a case–control study regarding the endometrial cancer incidence published elsewhere to illustrate the use of these test procedures.     

A study of grouped failure time data and the misapplication of recurrent event modeling

Clinical trials often assess whether or not subjects have a disease at predetermined follow-up times. When the response of interest is a recurrent event, a subject may respond at multiple follow-up times over the course of the study. Alternatively, when the response of interest is an irreversible event, a subject is typically only observed until the time at which the response is first detected. However, some recent studies have recorded subjects responses at follow-up times after an irreversible event is initially observed. This study compares how existing models perform when failure time data are treated as recurrent events.     

Notes on Interval Estimation of Odds Ratio in Matched Pairs under Stratified Sampling

We develop four asymptotic interval estimators and one exact interval estimator for the odds ratio (OR) under stratified random sampling with matched pairs. We apply Monte Carlo simulation to evaluate the performance of these five interval estimators. We note that the conditional score test-based interval estimator with a monotonic transformation and the interval estimator based on the Mantel–Haenszel (MH) type point estimator with the logarithmic transformation are generally preferable to the others considered here. We also note that the conditional exact confidence interval can be of use when the total number of matched pairs with discordant responses is small.     

Analysis of longitudinal multiple-source binary data using generalized estimating equations

Summary.  We present a multivariate logistic regression model for the joint analysis of longitudinal multiple-source binary data. Longitudinal multiple-source binary data arise when repeated binary measurements are obtained from two or more sources, with each source providing a measure of the same underlying variable. Since the number of responses on each subject is relatively large, the empirical variance estimator performs poorly and cannot be relied on in this setting. Two methods for obtaining a parsimonious within-subject association structure are considered. An additional complication arises with estimation, since maximum likelihood estimation may not be feasible without making unrealistically strong assumptions about third- and higher order moments. To circumvent this, we propose the use of a generalized estimating equations approach. Finally, we present an analysis of multiple-informant data obtained longitudinally from a psychiatric interventional trial that motivated the model developed in the paper.     

Testing Serial Correlation in Partially Linear Single-Index Errors-in-Variables Models

In this article, we propose two test statistics for testing the underlying serial correlation in a partially linear single-index model Y = η(Z ^τα) + X ^τβ + ? when X is measured with additive error. The proposed test statistics are shown to have asymptotic normal or chi-squared distributions under the null hypothesis of no serial correlation. Monte Carlo experiments are also conducted to illustrate the finite sample performance of the proposed test statistics. The simulation results confirm that these statistics perform satisfactorily in both estimated sizes and powers.     

A Stepwise AIC Method for Variable Selection in Linear Regression

In this article, we study stepwise AIC method for variable selection comparing with other stepwise method for variable selection, such as, Partial F, Partial Correlation, and Semi-Partial Correlation in linear regression modeling. Then we show mathematically that the stepwise AIC method and other stepwise methods lead to the same method as Partial F. Hence, there are more reasons to use the stepwise AIC method than the other stepwise methods for variable selection, since the stepwise AIC method is a model selection method that can be easily managed and can be widely extended to more generalized models and applied to non normally distributed data. We also treat problems that always appear in applications, that are validation of selected variables and problem of collinearity.     

Understanding Canonical Correlation through the General Linear Model and Principal Components

Canonical correlation has been little used and little understood, even by otherwise sophisticated analysts. An alternative approach to canonical correlation, based on a general linear multivariate model, is presented. Properties of principal component analysis are used to help explain the method. Standard computational methods for full rank canonical correlation, techniques for canonical correlation on component scores, and canonical correlation with less than full rank are discussed. They are seen to be essentially equivalent when the model equation for canonical correlation on component scores is presented. The two approaches to less than full rank situations are equivalent in some senses, but quite different in usefulness, depending on the application. An example dataset is analyzed in detail to help demonstrate the conclusions.     

Saddlepoint Approximations to the Density and the Distribution Functions of Linear Combinations of Ratios of Partial Sums

A class of ratios of partial sums, including Normal, Weibull, Gamma, and Exponential distributions, is considered. The distribution of a linear combination of ratios of partial sums from this class is characterized by the distribution of a linear combination of Dirichlet components. This article presents two saddlepoint approaches to calculate the density and the distribution function for such a class of linear combinations. A simulation study is conducted to assess the performance of the saddlepoint methods and shows the great accuracy of the approximations over the usual asymptotic approximation. Applications of the presented approximations in statistical inferences are discussed.     

Quasi-Minimax Estimation in the Linear Model with Measurement Errors

In this article, we consider quasi-minimax estimation in the linear regression model where some covariates are measured with additive errors. When measurement errors are directly ignored the minimax risk of the resulting estimator can be large. By correcting the attenuation we propose a penalized quadratic risk function. A simulation study is conducted to illustrate the performance of the proposed estimators.     

农村居民生活满意度的影响因素分析

 本文将Logistic回归方法运用于生活满意度影响因素的分析,首先根据国内外研究成果选取五个影响因素并提出研究假设,其次运用无序多分类Logistic回归模型拟合调查数据,科学确定各因素的影响程度。研究发现家庭年收入、居住区域和对社会公平的看法这三个因素对江苏农村居民生活满意度有显著影响。因此,以经济持续稳定增长促进农村居民持续增收,以社会公平为目标推进政治经济建设将成为提高江苏农村居民生活满意度的有效措施。     

A General Class of Estimators for the Linear Regression Model Affected by Collinearity and Outliers

In this article, a general class of estimators for the linear regression model affected by outliers and collinearity is introduced and studied in some detail. This class of estimators combines the theory of light, maximum entropy, and robust regression techniques. Our theoretical findings are illustrated through a Monte Carlo simulation study.     

The Target Parameter of Adjusted R-Squared in Fixed-Design Experiments

R-squared (R²) and adjusted R-squared (R²_Adj) are sometimes viewed as statistics detached from any target parameter, and sometimes as estimators for the population multiple correlation. The latter interpretation is meaningful only if the explanatory variables are random. This article proposes an alternative perspective for the case where the x’s are fixed. A new parameter is defined, in a similar fashion to the construction of R², but relying on the true parameters rather than their estimates. (The parameter definition includes also the fixed x values.) This parameter is referred to as the “parametric” coefficient of determination, and denoted by ρ²_*. The proposed ρ²_* remains stable when irrelevant variables are removed (or added), unlike the unadjusted R², which always goes up when variables, either relevant or not, are added to the model (and goes down when they are removed). The value of the traditional R²_Adj may go up or down with added (or removed) variables, either relevant or not. It is shown that the unadjusted R² overestimates ρ²_*, while the traditional R²_Adj underestimates it. It is also shown that for simple linear regression the magnitude of the bias of R²_Adj can be as high as the bias of the unadjusted R² (while their signs are opposite). Asymptotic convergence in probability of R²_Adj to ρ²_* is demonstrated. The effects of model parameters on the bias of R² and R²_Adj are characterized analytically and numerically. An alternative bi-adjusted estimator is presented and evaluated.     

Marginal Correlation in Longitudinal Binary Data Based on Generalized Linear Mixed Models

This work aims at investigating marginal correlation within and between longitudinal data sequences. Useful and intuitive approximate expressions are derived based on generalized linear mixed models. Data from four double-blind randomized clinical trials are used to estimate the intra-class coefficient of reliability for a binary response. Additionally, the correlation between such a binary response and a continuous response is derived to evaluate the criterion validity of the binary response variable and the established continuous response variable.