Case-control studies of genotypic relative risks using children of cases as controls

The use of a child as a case's control in a case-control study of genetic factors may be advantageous in some situations. We describe three methods of analysing such data. A method based upon the unconditional likelihood using case/child pairings apparently is the most efficient method. However, a conditional likelihood method using case/child pairs is more robust in that it allows for heterogeneity of the genetic trait among subpopulations as long as matings occur only within the same subpopulation. We argue that the child can be considered a genetic surrogate for the missing spouse and hence such designs are as valid as are those using spouses.     

Analysis strategies for serial multivariate ultrasonographic data that are incomplete.

Ultrasonographic measurement of intima-media thickness in the carotid artery has emerged as an important non-invasive means of assessing atherosclerosis, and has served to define primary outcome measures related to progression of arterial lesions in several large clinical trials and epidemiologic studies. It is characteristic that measurements often cannot be obtained from all sites during repeated examinations. This leads to incomplete multivariate serial data, for which the set and number of visualized sites may vary across time. We have contrasted several conditional and unconditional maximum likelihood analytical approaches, and have evaluated these with a simulation experiment based on characteristics of ultrasound measurements collected during the course of the Asymptomatic Carotid Artery Plaque Study. We examined analyses based on unweighted and generalized least squares regression in which we estimated cross-sectional summary statistics using raw means, unconditional maximum likelihood estimates and full maximum likelihood estimates. Since the genesis of missing data is not fully clear, and since the approaches we examined are based, to some degree, on the assumption that data are missing at random, we also examined the relative impact of deviations from such an assumption on each of the approaches considered. We found that maximum likelihood based approaches increased the expected efficiency of the analysis of serial ultrasound data over ignoring missing data by up to 21 per cent.     

Modelling competing risks data with missing cause of failure

When competing risks data arise, information on the actual cause of failure for some subjects might be missing. Therefore, a cause-specific proportional hazards model together with multiple imputation (MI) methods have been used to analyze such data. Modelling the cumulative incidence function is also of interest, and thus we investigate the proportional subdistribution hazards model (Fine and Gray model) together with MI methods as a modelling approach for competing risks data with missing cause of failure. Possible strategies for analyzing such data include the complete case analysis as well as an analysis where the missing causes are classified as an additional failure type. These approaches, however, may produce misleading results in clinical settings. In the present work we investigate the bias of the parameter estimates when fitting the Fine and Gray model in the above modelling approaches. We also apply the MI method and evaluate its comparative performance under various missing data scenarios. Results from simulation experiments showed that there is substantial bias in the estimates when fitting the Fine and Gray model with naive techniques for missing data, under missing at random cause of failure. Compared to those techniques the MI-based method gave estimates with much smaller biases and coverage probabilities of 95 per cent confidence intervals closer to the nominal level. All three methods were also applied on real data modelling time to AIDS or non-AIDS cause of death in HIV-1 infected individuals.     

A comparison of two methods for the estimation of precision with incomplete longitudinal data, jointly modelled with a time-to-event outcome

Several methods for the estimation and comparison of rates of change in longitudinal studies with staggered entry and informative drop-outs have been recently proposed. For multivariate normal linear models, REML estimation is used. There are various approaches to maximizing the corresponding log-likelihood; in this paper we use a restricted iterative generalized least squares method (RIGLS) combined with a nested EM algorithm. An important statistical problem in such approaches is the estimation of the standard errors adjusted for the missing data (observed data information matrix). Louis has provided a general technique for computing the observed data information in terms of completed data quantities within the EM framework. The multiple imputation (MI) method for obtaining variances can be regarded as an alternative to this. The aim of this paper is to develop, apply and compare the Louis and a modified MI method in the setting of longitudinal studies where the source of missing data is either death or disease progression (informative) or end of the study (assumed non-informative). Longitudinal data are simultaneously modelled with the missingness process. The methods are illustrated by modelling CD4 count data from an HIV-1 clinical trial and evaluated through simulation studies. Both methods, Louis and MI, are used with Monte Carlo simulations of the missing data using the appropriate conditional distributions, the former with 100 simulations, the latter with 5 and 10. It is seen that naive SEs based on the completed data likelihood can be seriously biased. This bias was largely corrected by Louis and modified MI methods, which gave broadly similar estimates. Given the relative simplicity of the modified MI method, it may be preferable.     

Probabilistic sensitivity analysis for decision trees with multiple branches: use of the Dirichlet distribution in a Bayesian framework.

In structuring decision models of medical interventions, it is commonly recommended that only 2 branches be used for each chance node to avoid logical inconsistencies that can arise during sensitivity analyses if the branching probabilities do not sum to 1. However, information may be naturally available in an unconditional form, and structuring a tree in conditional form may complicate rather than simplify the sensitivity analysis of the unconditional probabilities. Current guidance emphasizes using probabilistic sensitivity analysis, and a method is required to provide probabilistic probabilities over multiple branches that appropriately represents uncertainty while satisfying the requirement that mutually exclusive event probabilities should sum to 1. The authors argue that the Dirichlet distribution, the multivariate equivalent of the beta distribution, is appropriate for this purpose and illustrate its use for generating a fully probabilistic transition matrix for a Markov model. Furthermore, they demonstrate that by adopting a Bayesian approach, the problem of observing zero counts for transitions of interest can be overcome.     

The bivariate combined model for spatial data analysis

To describe the spatial distribution of diseases, a number of methods have been proposed to model relative risks within areas. Most models use Bayesian hierarchical methods, in which one models both spatially structured and unstructured extra‐Poisson variance present in the data. For modelling a single disease, the conditional autoregressive (CAR) convolution model has been very popular. More recently, a combined model was proposed that ‘combines’ ideas from the CAR convolution model and the well‐known Poisson‐gamma model. The combined model was shown to be a good alternative to the CAR convolution model when there was a large amount of uncorrelated extra‐variance in the data. Less solutions exist for modelling two diseases simultaneously or modelling a disease in two sub‐populations simultaneously. Furthermore, existing models are typically based on the CAR convolution model. In this paper, a bivariate version of the combined model is proposed in which the unstructured heterogeneity term is split up into terms that are shared and terms that are specific to the disease or subpopulation, while spatial dependency is introduced via a univariate or multivariate Markov random field. The proposed method is illustrated by analysis of disease data in Georgia (USA) and Limburg (Belgium) and in a simulation study. We conclude that the bivariate combined model constitutes an interesting model when two diseases are possibly correlated. As the choice of the preferred model differs between data sets, we suggest to use the new and existing modelling approaches together and to choose the best model via goodness‐of‐fit statistics. Copyright © 2016 John Wiley & Sons, Ltd.     

TESTING FOR TREATMENT DIFFERENCES WITH DROPOUTS PRESENT IN CLINICAL TRIALS – A COMPOSITE APPROACH

A major problem in the analysis of clinical trials is missing data from patients who drop out of the study before the predetermined schedule. In this paper we consider the situation where the outcome measure is a continuous variable and the final outcome at the end of the study is the main interest. We argue that the hypothetical complete-data marginal mean averaged over the dropout patterns is not as relevant clinically as the conditional mean of the completers together with the probability of completion or dropping out of the trial. We first take the pattern-mixture modelling approach to factoring the likelihood function, then direct the analysis to the multiple testings of a composite of hypotheses that involves the probability of dropouts and the conditional mean of the completers. We review three types of closed step-down multiple-testing procedures for this application. Data from several clinical trials are used to illustrate the proposed approach. © 1997 by John Wiley & Sons, Ltd.     

Imputation of missing values is superior to complete case analysis and the missing-indicator method in multivariable diagnostic research: a clinical example

BACKGROUND AND OBJECTIVES: To illustrate the effects of different methods for handling missing data--complete case analysis, missing-indicator method, single imputation of unconditional and conditional mean, and multiple imputation (MI)--in the context of multivariable diagnostic research aiming to identify potential predictors (test results) that independently contribute to the prediction of disease presence or absence. METHODS: We used data from 398 subjects from a prospective study on the diagnosis of pulmonary embolism. Various diagnostic predictors or tests had (varying percentages of) missing values. Per method of handling these missing values, we fitted a diagnostic prediction model using multivariable logistic regression analysis. RESULTS: The receiver operating characteristic curve area for all diagnostic models was above 0.75. The predictors in the final models based on the complete case analysis, and after using the missing-indicator method, were very different compared to the other models. The models based on MI did not differ much from the models derived after using single conditional and unconditional mean imputation. CONCLUSION: In multivariable diagnostic research complete case analysis and the use of the missing-indicator method should be avoided, even when data are missing completely at random. MI methods are known to be superior to single imputation methods. For our example study, the single imputation methods performed equally well, but this was most likely because of the low overall number of missing values.     

Simple pattern-mixture models for longitudinal data with missing observations: analysis of urinary incontinence data.

In longitudinal studies each subject is observed at several different times. Longitudinal studies are rarely balanced and complete due to occurrence of missing data. Little proposed pattern-mixture models for the analysis of incomplete multivariate normal data. Later, Little proposed an approach to modelling the drop-out mechanism based on the pattern-mixture models. We advocate the pattern-mixture models for analysing the longitudinal data with binary or Poisson responses in which the generalized estimating equations formulation of Liang and Zeger is sensible. The proposed method is illustrated with a real data set.     

Tests for the homogeneity of two binomial proportions in extremely unbalanced 2 x 2 contingency tables

Asymptotic tests such as the Pearson chi-square test are unreliable for testing the homogeneity of two binomial probabilities in extremely unbalanced cases. Two exact tests (conditional and unconditional) are available as alternatives and can be implemented easily in StatXact 6.0. In equal sample cases it is well known that the unconditional exact test is more powerful than the conditional exact test. However, in this paper, we show that the opposite result holds in extremely unbalanced cases. The reason is that the peaks of the type I error occur at the extremes of the nuisance parameter when the imbalance among the sample sizes becomes severe. After we show that the conditional exact test is more powerful than the unconditional exact test in extremely unbalanced cases whose sample ratio is greater than 20, we compare the conditional exact test with the Berger and Boos approach (J. Amer. Stat. Assoc. 1994; 89:1012-1016) in which the supremum is taken over a confidence interval for the nuisance parameter. The Berger and Boos approach turns out to be slightly more powerful than the conditional exact test in extremely unbalanced data. A real example is provided.     

Analyzing longitudinal data with patients in different disease states during follow‐up and death as final state

This paper considers the analysis of longitudinal data complicated by the fact that during follow‐up patients can be in different disease states, such as remission, relapse or death. If both the response of interest (for example, quality of life (QOL)) and the amount of missing data depend on this disease state, ignoring the disease state will yield biased means. Death as the final state is an additional complication because no measurements after death are taken and often the outcome of interest is undefined after death. We discuss a new approach to model these types of data. In our approach the probability to be in each of the different disease states over time is estimated using multi‐state models. In each different disease state, the conditional mean given the disease state is modeled directly. Generalized estimation equations are used to estimate the parameters of the conditional means, with inverse probability weights to account for unobserved responses. This approach shows the effect of the disease state on the longitudinal response. Furthermore, it yields estimates of the overall mean response over time, either conditionally on being alive or after imputing predefined values for the response after death. Graphical methods to visualize the joint distribution of disease state and response are discussed. As an example, the analysis of a Dutch randomized clinical trial for breast cancer is considered. In this study, the long‐term impact on the QOL for two different chemotherapy schedules was studied with three disease states: alive without relapse, alive after relapse and death. Copyright © 2009 John Wiley & Sons, Ltd.     

Functional Assessment of Cancer Therapy (FACT-G): Non-response to individual questions

The purpose of this investigation is to examine methods of scoring the FACT-G when there is nonresponse to individual questions. Using completed questionnaires from 350 patients, random and nonrandom missing responses where simulated. Seven methods of scoring the FACT-G are compared on the basis of accuracy (bias and precision) of both population estimates and prediction of individual scores. Substituting the mean of the completed items in the subscale when more than 50% are completed is generally the most unbiased and precise approach. Case deletion is the worst approach and results in clinically significant bias when the missing responses were non-random and a lack of precision when the rate of non-response was high.Supported by grants from the National Cancer Institute, DHHSCA-23318, CA-51926, and American Cancer Society #PBR6132.     

Analysing the effects of anaemia on local recurrence of head and neck cancer when covariate values are missing

We present a case study in the analysis of the prognostic effects of anaemia and other covariates on the local recurrence of head and neck cancer in patients who have been treated with radiation therapy. Because it is believed that a large fraction of the patients are cured by the therapy, we use a failure time mixture model for the outcomes, which simultaneously models both the relationship of the covariates to cure and the relationship of the covariates to local recurrence times for subjects who are not cured. A problematic feature of the data is that two covariates of interest having missing values, so that only 75 per cent of the subjects have complete data. We handle the missing-data problem by jointly modelling the covariates and the outcomes, and then fitting the model to all of the data, including the incomplete cases. We compare our approach to two traditional methods for handling missingness, that is, complete-case analysis and the use of an indicator variable for missingness. The comparison with complete-case analysis demonstrates gains in efficiency for joint modelling as well as sensitivity of some results to the method used to handle missing data. The use of an indicator variable yields results that are very similar to those from joint modelling for our data. We also compare the results obtained for the mixture model with results obtained for a standard (non-mixture) survival model. It is seen that the mixture model separates out effects in a way that is not possible with a standard survival model. In particular, conditional on other covariates, we find strong evidence of an association between anaemia and cure, whereas the evidence of an association between anaemia and time to local recurrence for patients who are not cured is weaker.     

Estimation and comparison of rates of change in longitudinal studies with informative drop-outs.

Many cohort studies and clinical trials have designs which involve repeated measurements of disease markers. One problem in such longitudinal studies, when the primary interest is to estimate and to compare the evolution of a disease marker, is that planned data are not collected because of missing data due to missing visits and/or withdrawal or attrition (for example, death). Several methods to analyse such data are available, provided that the data are missing at random. However, serious biases can occur when missingness is informative. In such cases, one needs to apply methods that simultaneously model the observed data and the missingness process. In this paper we consider the problem of estimation of the rate of change of a disease marker in longitudinal studies, in which some subjects drop out prematurely (informatively) due to attrition, while others experience a non-informative drop-out process (end of study, withdrawal). We propose a method which combines a linear random effects model for the underlying pattern of the marker with a log-normal survival model for the informative drop-out process. Joint estimates are obtained through the restricted iterative generalized least squares method which are equivalent to restricted maximum likelihood estimates. A nested EM algorithm is applied to deal with censored survival data. The advantages of this method are: it provides a unified approach to estimate all the model parameters; it can effectively deal with irregular data (that is, measured at irregular time points), a complicated covariance structure and a complex underlying profile of the response variable; it does not entail such complex computation as would be required to maximize the joint likelihood. The method is illustrated by modelling CD4 count data in a clinical trial in patients with advanced HIV infection while its performance is tested by simulation studies.     

Directly modelling matched case-control data

Matching in case-control studies is a situation in which one wishes to make inferences about a parameter of interest in the presence of nuisance parameters. The usual approach is to apply a conditional likelihood. A bivariate latent class log-linear model for binomial responses is shown to yield a standard likelihood identical to the usual conditional one. This extension of the Rasch model for binary responses gives consistent estimates and a suitable likelihood function for cases matched with any fixed number of controls.     

Bivariate logistic regression: modelling the association of small for gestational age births in twin gestations.

Clustered binary responses, such as disease status in twins, frequently arise in perinatal health and other epidemiologic applications. The scientific objective involves modelling both the marginal mean responses, such as the probability of disease, and the within-cluster association of the multivariate responses. In this regard, bivariate logistic regression is a useful procedure with advantages that include (i) a single maximization of the joint probability distribution of the bivariate binary responses, and (ii) modelling the odds ratio describing the pairwise association between the two binary responses in relation to several covariates. In addition, since the form of the joint distribution of the bivariate binary responses is assumed known, parameters for the regression model can be estimated by the method of maximum likelihood. Hence, statistical inferences may be based on likelihood ratio tests and profile likelihood confidence intervals. We apply bivariate logistic regression to a perinatal database comprising 924 twin foetuses resulting from 462 pregnancies to model obstetric and clinical risk factors for the association of small for gestational age births in twin gestations.     

Multi-level models for longitudinal growth norms

Multi-level models for estimating conditional and unconditional longitudinal growth norms are presented. The procedure involves transforming the original growth measurements to Normality and modelling these with a two-level random coefficient model. Growth norms for any desired time interval and function can be derived. Height and weight data are used for illustration. © 1997 John Wiley & Sons, Ltd.     

Analysis of incomplete multivariate data using linear models with structured covariance matrices

Incomplete and unbalanced multivariate data often arise in longitudinal studies due to missing or unequally-timed repeated measurements and/or the presence of time-varying covariates. A general approach to analysing such data is through maximum likelihood analysis using a linear model for the expected responses, and structural models for the within-subject covariances. Two important advantages of this approach are: (1) the generality of the model allows the analyst to consider a wider range of models than were previously possible using classical methods developed for balanced and complete data, and (2) maximum likelihood estimates obtained from incomplete data are often preferable to other estimates such as those obtained from complete cases from the standpoint of bias and efficiency. A variety of applications of the model are discussed, including univariate and multivariate analysis of incomplete repeated measures data, analysis of growth curves with missing data using random effects and time-series models, and applications to unbalanced longitudinal data.     

An alternative parameterization of the general linear mixture model for longitudinal data with non-ignorable drop-outs

This paper considers the mixture model methodology for handling non-ignorable drop-outs in longitudinal studies with continuous outcomes. Recently, Hogan and Laird have developed a mixture model for non-ignorable drop-outs which is a standard linear mixed effects model except that the parameters which characterize change over time depend also upon time of drop-out. That is, the mean response is linear in time, other covariates and drop-out time, and their interactions. One of the key attractions of the mixture modelling approach to drop-outs is that it is relatively easy to explore the sensitivity of results to model specification. However, the main drawback of mixture models is that the parameters that are ordinarily of interest are not immediately available, but require marginalization of the distribution of outcome over drop-out times. Furthermore, although a linear model is assumed for the conditional mean of the outcome vector given time of drop out, after marginalization, the unconditional mean of the outcome vector is not, in general, linear in the regression parameters. As a result, it is not possible to parsimoniously describe the effects of covariates on the marginal distribution of the outcome in terms of regression coefficients. The need to explicitly average over the distribution of the drop-out times and the absence of regression coefficients that describe the effects of covariates on the outcome are two unappealing features of the mixture modelling approach. In this paper we describe a particular parameterization of the general linear mixture model that circumvents both of these problems.