Fitting stratified proportional odds models by amalgamating conditional likelihoods

Classical methods for fitting a varying intercept logistic regression model to stratified data are based on the conditional likelihood principle to eliminate the stratum-specific nuisance parameters. When the outcome variable has multiple ordered categories, a natural choice for the outcome model is a stratified proportional odds or cumulative logit model. However, classical conditioning techniques do not apply to the general K-category cumulative logit model (K>2) with varying stratum-specific intercepts as there is no reduction due to sufficiency; the nuisance parameters remain in the conditional likelihood. We propose a methodology to fit stratified proportional odds model by amalgamating conditional likelihoods obtained from all possible binary collapsings of the ordinal scale. The method allows for categorical and continuous covariates in a general regression framework. We provide a robust sandwich estimate of the variance of the proposed estimator. For binary exposures, we show equivalence of our approach to the estimators already proposed in the literature. The proposed recipe can be implemented very easily in standard software. We illustrate the methods via three real data examples related to biomedical research. Simulation results comparing the proposed method with a random effects model on the stratification parameters are also furnished.     

Likelihood methods for measuring statistical evidence

Focused on interpreting data as statistical evidence, the evidential paradigm uses likelihood ratios to measure the strength of statistical evidence. Under this paradigm, re-examination of accumulating evidence is encouraged because (i) the likelihood ratio, unlike a p-value, is unaffected by the number of examinations and (ii) the probability of observing strong misleading evidence is naturally low, even for study designs that re-examine the data with each new observation. Further, the controllable probabilities of observing misleading and weak evidence provide assurance that the study design is reliable without affecting the strength of statistical evidence in the data. This paper illustrates the ideas and methods associated with using likelihood ratios to measure statistical evidence. It contains a comprehensive introduction to the evidential paradigm, including an overview of how to quantify the probability of observing misleading evidence for various study designs. The University Group Diabetes Program (UGDP), a classic and still controversial multi-centred clinical trial, is used as an illustrative example. Some of the original UGDP results, and subsequent re-analyses, are presented for comparison purposes.     

Use of empirical likelihood to calibrate auxiliary information in partly linear monotone regression models

In statistical analysis, a regression model is needed if one is interested in finding the relationship between a response variable and covariates. When the response depends on the covariate, then it may also depend on the function of this covariate. If one has no knowledge of this functional form but expect for monotonic increasing or decreasing, then the isotonic regression model is preferable. Estimation of parameters for isotonic regression models is based on the pool‐adjacent‐violators algorithm (PAVA), where the monotonicity constraints are built in. With missing data, people often employ the augmented estimating method to improve estimation efficiency by incorporating auxiliary information through a working regression model. However, under the framework of the isotonic regression model, the PAVA does not work as the monotonicity constraints are violated. In this paper, we develop an empirical likelihood‐based method for isotonic regression model to incorporate the auxiliary information. Because the monotonicity constraints still hold, the PAVA can be used for parameter estimation. Simulation studies demonstrate that the proposed method can yield more efficient estimates, and in some situations, the efficiency improvement is substantial. We apply this method to a dementia study. Copyright © 2013 John Wiley & Sons, Ltd.     

Accounting for informatively missing data in logistic regression by means of reassessment sampling

We explore the ‘reassessment’ design in a logistic regression setting, where a second wave of sampling is applied to recover a portion of the missing data on a binary exposure and/or outcome variable. We construct a joint likelihood function based on the original model of interest and a model for the missing data mechanism, with emphasis on non‐ignorable missingness. The estimation is carried out by numerical maximization of the joint likelihood function with close approximation of the accompanying Hessian matrix, using sharable programs that take advantage of general optimization routines in standard software. We show how likelihood ratio tests can be used for model selection and how they facilitate direct hypothesis testing for whether missingness is at random. Examples and simulations are presented to demonstrate the performance of the proposed method. Copyright © 2015 John Wiley & Sons, Ltd.     

Regression with an ordered categorical response

A survey on Mseleni joint disease in South Africa involved the scoring of pelvic X-rays of women to measure osteoporosis. The scores were ordinal by construction and ranged from 0 to 12. It is standard practice to use ordinary regression techniques with an ordinal response that has that many categories. We give evidence for these data that the constraints on the response result in a misleading regression analysis. McCullagh's proportional-odds model is designed specifically for the regression analysis of ordinal data. We demonstrate the technique on these data, and show how it fills the gap between ordinary regression and logistic regression (for discrete data with two categories). In addition, we demonstrate non-parametric versions of these models that do not make any linearity assumptions about the regression function.     

A conditional likelihood approach for regression analysis using biomarkers measured with batch‐specific error

Measurement error is common in epidemiological and biomedical studies. When biomarkers are measured in batches or groups, measurement error is potentially correlated within each batch or group. In regression analysis, most existing methods are not applicable in the presence of batch‐specific measurement error in predictors. We propose a robust conditional likelihood approach to account for batch‐specific error in predictors when batch effect is additive and the predominant source of error, which requires no assumptions on the distribution of measurement error. Although a regression model with batch as a categorical covariable yields the same parameter estimates as the proposed conditional likelihood approach for linear regression, this result does not hold in general for all generalized linear models, in particular, logistic regression. Our simulation studies show that the conditional likelihood approach achieves better finite sample performance than the regression calibration approach or a naive approach without adjustment for measurement error. In the case of logistic regression, our proposed approach is shown to also outperform the regression approach with batch as a categorical covariate. In addition, we also examine a ‘hybrid’ approach combining the conditional likelihood method and the regression calibration method, which is shown in simulations to achieve good performance in the presence of both batch‐specific and measurement‐specific errors. We illustrate our method by using data from a colorectal adenoma study. Copyright © 2012 John Wiley & Sons, Ltd.     

A new estimation with minimum trace of asymptotic covariance matrix for incomplete longitudinal data with a surrogate process

Missing data is a very common problem in medical and social studies, especially when data are collected longitudinally. It is a challenging problem to utilize observed data effectively. Many papers on missing data problems can be found in statistical literature. It is well known that the inverse weighted estimation is neither efficient nor robust. On the other hand, the doubly robust (DR) method can improve the efficiency and robustness. As is known, the DR estimation requires a missing data model (i.e., a model for the probability that data are observed) and a working regression model (i.e., a model for the outcome variable given covariates and surrogate variables). Because the DR estimating function has mean zero for any parameters in the working regression model when the missing data model is correctly specified, in this paper, we derive a formula for the estimator of the parameters of the working regression model that yields the optimally efficient estimator of the marginal mean model (the parameters of interest) when the missing data model is correctly specified. Furthermore, the proposed method also inherits the DR property. Simulation studies demonstrate the greater efficiency of the proposed method compared with the standard DR method. A longitudinal dementia data set is used for illustration. Copyright © 2013 John Wiley & Sons, Ltd.     

A comparison of three different models for estimating relative risk in meta-analysis of clinical trials under unobserved heterogeneity

We focus on the comparison of three statistical models used to estimate the treatment effect in meta-analysis when individually pooled data are available. The models are two conventional models, namely a multi-level and a model based upon an approximate likelihood, and a newly developed model, the profile likelihood model which might be viewed as an extension of the Mantel-Haenszel approach. To exemplify these methods, we use results from a meta-analysis of 22 trials to prevent respiratory tract infections. We show that by using the multi-level approach, in the case of baseline heterogeneity, the number of clusters or components is considerably over-estimated. The approximate and profile likelihood method showed nearly the same pattern for the treatment effect distribution. To provide more evidence two simulation studies are accomplished. The profile likelihood can be considered as a clear alternative to the approximate likelihood model. In the case of strong baseline heterogeneity, the profile likelihood method shows superior behaviour when compared with the multi-level model.     

Robust estimation for linear panel data models

In different fields of applications including, but not limited to, behavioral, environmental, medical sciences, and econometrics, the use of panel data regression models has become increasingly popular as a general framework for making meaningful statistical inferences. However, when the ordinary least squares (OLS) method is used to estimate the model parameters, presence of outliers may significantly alter the adequacy of such models by producing biased and inefficient estimates. In this work, we propose a new, weighted likelihood based robust estimation procedure for linear panel data models with fixed and random effects. The finite sample performances of the proposed estimators have been illustrated through an extensive simulation study as well as with an application to blood pressure dataset. Our thorough study demonstrates that the proposed estimators show significantly better performances over the traditional methods in the presence of outliers and produce competitive results to the OLS based estimates when no outliers are present in the dataset.     

Identifying and Accommodating Statistical Outliers When Setting Prospective Payment Rates for Inpatient Rehabilitation Facilities

Objective. To demonstrate how a Bayesian outlier accommodation model identifies and accommodates statistical outlier hospitals when developing facility payment adjustments for Medicare's prospective payment system for inpatient rehabilitation care.
Data Sources/Study Setting. Administrative data on costs and facility characteristics of inpatient rehabilitation facilities (IRFs) for calendar years 1998 and 1999.
Study Design. Compare standard linear regression and the Bayesian outlier accommodation model for developing facility payment adjustors for a prospective payment system.
Data Collection. Variables describing facility average cost per case and facility characteristics were derived from several administrative data sources.
Principal Findings. Evidence was found of non-normality of regression errors in the data used to develop facility payment adjustments for the inpatient rehabilitation facilities prospective payment system (IRF PPS). The Bayesian outlier accommodation model is shown to be appropriate for these data, but the model is largely consistent with the standard linear regression used in the development of the IRF PPS payment adjustors.
Conclusions. The Bayesian outlier accommodation model is more robust to statistical outlier IRFs than standard linear regression for developing facility payment adjustments. It also allows for easy interpretation of model parameters, making it a viable policy alternative to standard regression in setting payment rates.     

Linear mixed models for replication data to efficiently allow for covariate measurement error

It is well known that measurement error in the covariates of regression models generally causes bias in parameter estimates. Correction for such biases requires information concerning the measurement error, which is often in the form of internal validation or replication data. Regression calibration (RC) is a popular approach to correct for covariate measurement error, which involves predicting the true covariate using error‐prone measurements. Likelihood methods have previously been proposed as an alternative approach to estimate the parameters in models affected by measurement error, but have been relatively infrequently employed in medical statistics and epidemiology, partly because of computational complexity and concerns regarding robustness to distributional assumptions. We show how a standard random‐intercepts model can be used to obtain maximum likelihood (ML) estimates when the outcome model is linear or logistic regression under certain normality assumptions, when internal error‐prone replicate measurements are available. Through simulations we show that for linear regression, ML gives more efficient estimates than RC, although the gain is typically small. Furthermore, we show that RC and ML estimates remain consistent even when the normality assumptions are violated. For logistic regression, our implementation of ML is consistent if the true covariate is conditionally normal given the outcome, in contrast to RC. In simulations, this ML estimator showed less bias in situations where RC gives non‐negligible biases. Our proposal makes the ML approach to dealing with covariate measurement error more accessible to researchers, which we hope will improve its viability as a useful alternative to methods such as RC. Copyright © 2009 John Wiley & Sons, Ltd.     

Measuring and illustrating statistical evidence in a cost-effectiveness analysis

Recently, there has been much interest in using the cost-effectiveness acceptability curve (CEAC) to measure the statistical evidence of cost-effectiveness. The CEAC has two well established but fundamentally different interpretations: one frequentist and one Bayesian. As an alternative, we suggest characterizing the statistical evidence about cost-effectiveness using the likelihood function (the key element of both approaches). Its interpretation is neither dependent on the sample space nor on the prior distribution. Moreover, the probability of observing misleading evidence is low and controllable, so this approach is justifiable in the traditional sense of frequentist long-run behaviour. We propose a new graphic for displaying the evidence about cost-effectiveness and explore the strengths of likelihood methods using data from an economic evaluation of a Program in Assertive Community Treatment (PACT).     

Random effects meta‐analysis of event outcome in the framework of the generalized linear mixed model with applications in sparse data

We consider random effects meta‐analysis where the outcome variable is the occurrence of some event of interest. The data structures handled are where one has one or more groups in each study, and in each group either the number of subjects with and without the event, or the number of events and the total duration of follow‐up is available. Traditionally, the meta‐analysis follows the summary measures approach based on the estimates of the outcome measure(s) and the corresponding standard error(s). This approach assumes an approximate normal within‐study likelihood and treats the standard errors as known. This approach has several potential disadvantages, such as not accounting for the standard errors being estimated, not accounting for correlation between the estimate and the standard error, the use of an (arbitrary) continuity correction in case of zero events, and the normal approximation being bad in studies with few events. We show that these problems can be overcome in most cases occurring in practice by replacing the approximate normal within‐study likelihood by the appropriate exact likelihood. This leads to a generalized linear mixed model that can be fitted in standard statistical software. For instance, in the case of odds ratio meta‐analysis, one can use the non‐central hypergeometric distribution likelihood leading to mixed‐effects conditional logistic regression. For incidence rate ratio meta‐analysis, it leads to random effects logistic regression with an offset variable. We also present bivariate and multivariate extensions. We present a number of examples, especially with rare events, among which an example of network meta‐analysis. Copyright © 2010 John Wiley & Sons, Ltd.     

A simple significance test for quantile regression

Where OLS regression seeks to model the mean of a random variable as a function of observed variables, quantile regression seeks to model the quantiles of a random variable as functions of observed variables. Tests for the dependence of the quantiles of a random variable upon observed variables have only been developed through the use of computer resampling or based on asymptotic approximations resting on distributional assumptions. We propose an exceedingly simple but heretofore undocumented likelihood ratio test within a logistic regression framework to test the dependence of a quantile of a random variable upon observed variables. Simulated data sets are used to illustrate the rationale, ease, and utility of the hypothesis test. Simulations have been performed over a variety of situations to estimate the type I error rates and statistical power of the procedure. Results from this procedure are compared to (1) previously proposed asymptotic tests for quantile regression and (2) bootstrap techniques commonly used for quantile regression inference. Results show that this less computationally intense method has appropriate type I error control, which is not true for all competing procedures, comparable power to both previously proposed asymptotic tests and bootstrap techniques, and greater computational ease. We illustrate the approach using data from 779 adolescent boys age 12-18 from the Third National Health and Nutrition Examination Survey (NHANES III) to test hypotheses regarding age, ethnicity, and their interaction upon quantiles of waist circumference.     

Likelihood approaches for proportional likelihood ratio model with right‐censored data

Regression methods for survival data with right censoring have been extensively studied under semiparametric transformation models such as the Cox regression model and the proportional odds model. However, their practical application could be limited because of possible violation of model assumption or lack of ready interpretation for the regression coefficients in some cases. As an alternative, in this paper, the proportional likelihood ratio model introduced by Luo and Tsai is extended to flexibly model the relationship between survival outcome and covariates. This model has a natural connection with many important semiparametric models such as generalized linear model and density ratio model and is closely related to biased sampling problems. Compared with the semiparametric transformation model, the proportional likelihood ratio model is appealing and practical in many ways because of its model flexibility and quite direct clinical interpretation. We present two likelihood approaches for the estimation and inference on the target regression parameters under independent and dependent censoring assumptions. Based on a conditional likelihood approach using uncensored failure times, a numerically simple estimation procedure is developed by maximizing a pairwise pseudo‐likelihood. We also develop a full likelihood approach, and the most efficient maximum likelihood estimator is obtained by a profile likelihood. Simulation studies are conducted to assess the finite‐sample properties of the proposed estimators and compare the efficiency of the two likelihood approaches. An application to survival data for bone marrow transplantation patients of acute leukemia is provided to illustrate the proposed method and other approaches for handling non‐proportionality. The relative merits of these methods are discussed in concluding remarks. Copyright © 2014 John Wiley & Sons, Ltd.     

A metastasis or a second independent cancer? Evaluating the clonal origin of tumors using array copy number data

When a cancer patient develops a new tumor it is necessary to determine if it is a recurrence (metastasis) of the original cancer, or an entirely new occurrence of the disease. This is accomplished by assessing the histo‐pathology of the lesions. However, there are many clinical scenarios in which this pathological diagnosis is difficult. Since each tumor is characterized by a distinct pattern of somatic mutations, a more definitive diagnosis is possible in principle in these difficult clinical scenarios by comparing the two patterns. In this article we develop and evaluate a statistical strategy for this comparison when the data are derived from array copy number data, designed to identify all of the somatic allelic gains and losses across the genome. First a segmentation algorithm is used to estimate the regions of allelic gain and loss. The correlation in these patterns between the two tumors is assessed, and this is complemented with more precise quantitative comparisons of each plausibly clonal mutation within individual chromosome arms. The results are combined to determine a likelihood ratio to distinguish clonal tumor pairs (metastases) from independent second primaries. Our data analyses show that in many cases a strong clonal signal emerges. Sensitivity analyses show that most of the diagnoses are robust when the data are of high quality. Copyright © 2010 John Wiley & Sons, Ltd.     

Improving likelihood‐based inference in control rate regression

Control rate regression is a diffuse approach to account for heterogeneity among studies in meta‐analysis by including information about the outcome risk of patients in the control condition. Correcting for the presence of measurement error affecting risk information in the treated and in the control group has been recognized as a necessary step to derive reliable inferential conclusions. Within this framework, the paper considers the problem of small sample size as an additional source of misleading inference about the slope of the control rate regression. Likelihood procedures relying on first‐order approximations are shown to be substantially inaccurate, especially when dealing with increasing heterogeneity and correlated measurement errors. We suggest to address the problem by relying on higher‐order asymptotics. In particular, we derive Skovgaard's statistic as an instrument to improve the accuracy of the approximation of the signed profile log‐likelihood ratio statistic to the standard normal distribution. The proposal is shown to provide much more accurate results than standard likelihood solutions, with no appreciable computational effort. The advantages of Skovgaard's statistic in control rate regression are shown in a series of simulation experiments and illustrated in a real data example. R code for applying first‐ and second‐order statistic for inference on the slope on the control rate regression is provided.     

Analysis of binary outcomes in longitudinal studies using weighted estimating equations and discrete-time survival methods: prevalence and incidence of smoking in an adolescent cohort.

Longitudinal studies are increasingly popular in epidemiology. In this tutorial we provide a detailed review of methods used by us in the analysis of a longitudinal (multiwave or panel) study of adolescent health, focusing on smoking behaviour. This example is explored in detail with the principal aim of providing an introduction to the analysis of longitudinal binary data, at a level suited to statisticians familiar with logistic regression and survival analysis but not necessarily experienced in longitudinal analysis or estimating equation methods. We describe recent advances in statistical methodology that can play a practical role in applications and are available with standard software. Our approach emphasizes the importance of stating clear research questions, and for binary outcomes we suggest these are best organized around the key epidemiological concepts of prevalence and incidence. For prevalence questions, we show how unbiased estimating equations and information-sandwich variance estimates may be used to produce a valid and robust analysis, as long as sample size is reasonably large. We also show how the estimating equation approach readily extends to accommodate adjustments for missing data and complex survey design. A detailed discussion of gender-related differences over time in our smoking outcome is used to emphasize the need for great care in separating longitudinal from cross-sectional information. We show how incidence questions may be addressed using a discrete-time version of the proportional hazards regression model. This approach has the advantages of providing estimates of relative risks, being feasible with standard software, and also allowing robust information-sandwich variance estimates.     

Joint modeling of binary response and survival for clustered data in clinical trials

In clinical trials, it is often desirable to evaluate the effect of a prognostic factor such as a marker response on a survival outcome. However, the marker response and survival outcome are usually associated with some potentially unobservable factors. In this case, the conventional statistical methods that model these two outcomes separately may not be appropriate. In this paper, we propose a joint model for marker response and survival outcomes for clustered data, providing efficient statistical inference by considering these two outcomes simultaneously. We focus on a special type of marker response: a binary outcome, which is investigated together with survival data using a cluster-specific multivariate random effect variable. A multivariate penalized likelihood method is developed to make statistical inference for the joint model. However, the standard errors obtained from the penalized likelihood method are usually underestimated. This issue is addressed using a jackknife resampling method to obtain a consistent estimate of standard errors. We conduct extensive simulation studies to assess the finite sample performance of the proposed joint model and inference methods in different scenarios. The simulation studies show that the proposed joint model has excellent finite sample properties compared to the separate models when there exists an underlying association between the marker response and survival data. Finally, we apply the proposed method to a symptom control study conducted by Canadian Cancer Trials Group to explore the prognostic effect of covariates on pain control and overall survival.