Robustness of the latent variable model for correlated binary data

The marginal regression model offers a useful alternative to conditional approaches to analyzing binary data (Liang, Zeger, and Qaqish, 1992, Journal of the Royal Statistical Society, Series B 54, 3-40). Instead of modelling the binary data directly as do Liang and Zeger (1986, Biometrika 73, 13-22), the parametric marginal regression model developed by Qu et al. (1992, Biometrics 48, 1095-1102) assumes that there is an underlying multivariate normal vector that gives rise to the observed correlated binary outcomes. Although this parametric approach provides a flexible way to model different within-cluster correlation structures and does not restrict the parameter space, it is of interest to know how robust the parameter estimates are with respect to choices of the latent distribution. We first extend the latent modelling to include multivariate t-distributed latent vectors and assess the robustness in this class of distributions. Then we show through a simulation that the parameter estimates are robust with respect to the latent distribution even if latent distribution is skewed. In addtion to this empirical evidence for robustness, we show through the iterative algorithm that the robustness of the regression coefficents with respect to misspecifications of covariance structure in Liang and Zeger's model in fact indicates robustness with respect to underlying distributional assumptions of the latent vector in the latent variable model.     

Simplifying the estimation of diagnostic testing accuracy over time for high specificity tests in the absence of a gold standard

Many different methods for evaluating diagnostic test results in the absence of a gold standard have been proposed. In this paper, we discuss how one common method, a maximum likelihood estimate for a latent class model found via the Expectation-Maximization (EM) algorithm can be applied to longitudinal data where test sensitivity changes over time. We also propose two simplified and nonparametric methods which use data-based indicator variables for disease status and compare their accuracy to the maximum likelihood estimation (MLE) results. We find that with high specificity tests, the performance of simpler approximations may be just as high as the MLE.     

A composite likelihood approach to latent multivariate Gaussian modeling of SNP data with application to genetic association testing

Many statistical tests have been proposed for case-control data to detect disease association with multiple single nucleotide polymorphisms (SNPs) in linkage disequilibrium. The main reason for the existence of so many tests is that each test aims to detect one or two aspects of many possible distributional differences between cases and controls, largely due to the lack of a general and yet simple model for discrete genotype data. Here we propose a latent variable model to represent SNP data: the observed SNP data are assumed to be obtained by discretizing a latent multivariate Gaussian variate. Because the latent variate is multivariate Gaussian, its distribution is completely characterized by its mean vector and covariance matrix, in contrast to much more complex forms of a general distribution for discrete multivariate SNP data. We propose a composite likelihood approach for parameter estimation. A direct application of this latent variable model is to association testing with multiple SNPs in a candidate gene or region. In contrast to many existing tests that aim to detect only one or two aspects of many possible distributional differences of discrete SNP data, we can exclusively focus on testing the mean and covariance parameters of the latent Gaussian distributions for cases and controls. Our simulation results demonstrate potential power gains of the proposed approach over some existing methods.     

Zygosity diagnosis in the absence of genotypic data: an approach using latent class analysis.

For zygosity diagnosis in the absence of genotypic data, or in the recruitment phase of a twin study where only single twins from same-sex pairs are being screened, or to provide a test for sample duplication leading to the false identification of a dizygotic pair as monozygotic, the appropriate analysis of respondents' answers to questions about zygosity is critical. Using data from a young adult Australian twin cohort (N = 2094 complete pairs and 519 singleton twins from same-sex pairs with complete responses to all zygosity items), we show that application of latent class analysis (LCA), fitting a 2-class model, yields results that show good concordance with traditional methods of zygosity diagnosis, but with certain important advantages. These include the ability, in many cases, to assign zygosity with specified probability on the basis of responses of a single informant (advantageous when one zygosity type is being oversampled); and the ability to quantify the probability of misassignment of zygosity, allowing prioritization of cases for genotyping as well as identification of cases of probable laboratory error. Out of 242 twins (from 121 like-sex pairs) where genotypic data were available for zygosity confirmation, only a single case was identified of incorrect zygosity assignment by the latent class algorithm. Zygosity assignment for that single case was identified by the LCA as uncertain (probability of being a monozygotic twin only 76%), and the co-twin's responses clearly identified the pair as dizygotic (probability of being dizygotic 100%). In the absence of genotypic data, or as a safeguard against sample duplication, application of LCA for zygosity assignment or confirmation is strongly recommended.     

Tractable Bayes of skew-elliptical link models for correlated binary data

Correlated binary response data with covariates are ubiquitous in longitudinal or spatial studies. Among the existing statistical models, the most well-known one for this type of data is the multivariate probit model, which uses a Gaussian link to model dependence at the latent level. However, a symmetric link may not be appropriate if the data are highly imbalanced. Here, we propose a multivariate skew-elliptical link model for correlated binary responses, which includes the multivariate probit model as a special case. Furthermore, we perform Bayesian inference for this new model and prove that the regression coefficients have a closed-form unified skew-elliptical posterior with an elliptical prior. The new methodology is illustrated by an application to COVID-19 data from three different counties of the state of California, USA. By jointly modeling extreme spikes in weekly new cases, our results show that the spatial dependence cannot be neglected. Furthermore, the results also show that the skewed latent structure of our proposed model improves the flexibility of the multivariate probit model and provides a better fit to our highly imbalanced dataset.     

Power and Sample Size Determination in the Rasch Model: Evaluation of the Robustness of a Numerical Method to Non-Normality of the Latent Trait

Patient-reported outcomes (PRO) have gained importance in clinical and epidemiological research and aim at assessing quality of life, anxiety or fatigue for instance. Item Response Theory (IRT) models are increasingly used to validate and analyse PRO. Such models relate observed variables to a latent variable (unobservable variable) which is commonly assumed to be normally distributed. A priori sample size determination is important to obtain adequately powered studies to determine clinically important changes in PRO. In previous developments, the Raschpower method has been proposed for the determination of the power of the test of group effect for the comparison of PRO in cross-sectional studies with an IRT model, the Rasch model. The objective of this work was to evaluate the robustness of this method (which assumes a normal distribution for the latent variable) to violations of distributional assumption. The statistical power of the test of group effect was estimated by the empirical rejection rate in data sets simulated using a non-normally distributed latent variable. It was compared to the power obtained with the Raschpower method. In both cases, the data were analyzed using a latent regression Rasch model including a binary covariate for group effect. For all situations, both methods gave comparable results whatever the deviations from the model assumptions. Given the results, the Raschpower method seems to be robust to the non-normality of the latent trait for determining the power of the test of group effect.     

Joint analysis of time-to-event and multiple binary indicators of latent classes

Multiple categorical variables are commonly used in medical and epidemiological research to measure specific aspects of human health and functioning. To analyze such data, models have been developed considering these categorical variables as imperfect indicators of an individual's "true" status of health or functioning. In this article, the latent class regression model is used to model the relationship between covariates, a latent class variable (the unobserved status of health or functioning), and the observed indicators (e.g., variables from a questionnaire). The Cox model is extended to encompass a latent class variable as predictor of time-to-event, while using information about latent class membership available from multiple categorical indicators. The expectation-maximization (EM) algorithm is employed to obtain maximum likelihood estimates, and standard errors are calculated based on the profile likelihood, treating the nonparametric baseline hazard as a nuisance parameter. A sampling-based method for model checking is proposed. It allows for graphical investigation of the assumption of proportional hazards across latent classes. It may also be used for checking other model assumptions, such as no additional effect of the observed indicators given latent class. The usefulness of the model framework and the proposed techniques are illustrated in an analysis of data from the Women's Health and Aging Study concerning the effect of severe mobility disability on time-to-death for elderly women.     

Latent class model diagnosis

In many areas of medical research, such as psychiatry and gerontology, latent class variables are used to classify individuals into disease categories, often with the intention of hierarchical modeling. Problems arise when it is not clear how many disease classes are appropriate, creating a need for model selection and diagnostic techniques. Previous work has shown that the Pearson chi 2 statistic and the log-likelihood ratio G2 statistic are not valid test statistics for evaluating latent class models. Other methods, such as information criteria, provide decision rules without providing explicit information about where discrepancies occur between a model and the data. Identifiability issues further complicate these problems. This paper develops procedures for assessing Markov chain Monte Carlo convergence and model diagnosis and for selecting the number of categories for the latent variable based on evidence in the data using Markov chain Monte Carlo techniques. Simulations and a psychiatric example are presented to demonstrate the effective use of these methods.     

Estimating Diagnostic Accuracy of Raters Without a Gold Standard by Exploiting a Group of Experts

Summary In diagnostic medicine, estimating the diagnostic accuracy of a group of raters or medical tests relative to the gold standard is often the primary goal. When a gold standard is absent, latent class models where the unknown gold standard test is treated as a latent variable are often used. However, these models have been criticized in the literature from both a conceptual and a robustness perspective. As an alternative, we propose an approach where we exploit an imperfect reference standard with unknown diagnostic accuracy and conduct sensitivity analysis by varying this accuracy over scientifically reasonable ranges. In this article, a latent class model with crossed random effects is proposed for estimating the diagnostic accuracy of regional obstetrics and gynaecological (OB/GYN) physicians in diagnosing endometriosis. To avoid the pitfalls of models without a gold standard, we exploit the diagnostic results of a group of OB/GYN physicians with an international reputation for the diagnosis of endometriosis. We construct an ordinal reference standard based on the discordance among these international experts and propose a mechanism for conducting sensitivity analysis relative to the unknown diagnostic accuracy among them. A Monte Carlo EM algorithm is proposed for parameter estimation and a BIC‐type model selection procedure is presented. Through simulations and data analysis we show that this new approach provides a useful alternative to traditional latent class modeling approaches used in this setting.     

Multilevel Latent Class Models with Dirichlet Mixing Distribution

Summary Latent class analysis (LCA) and latent class regression (LCR) are widely used for modeling multivariate categorical outcomes in social science and biomedical studies. Standard analyses assume data of different respondents to be mutually independent, excluding application of the methods to familial and other designs in which participants are clustered. In this article, we consider multilevel latent class models, in which subpopulation mixing probabilities are treated as random effects that vary among clusters according to a common Dirichlet distribution. We apply the expectation‐maximization (EM) algorithm for model fitting by maximum likelihood (ML). This approach works well, but is computationally intensive when either the number of classes or the cluster size is large. We propose a maximum pairwise likelihood (MPL) approach via a modified EM algorithm for this case. We also show that a simple latent class analysis, combined with robust standard errors, provides another consistent, robust, but less‐efficient inferential procedure. Simulation studies suggest that the three methods work well in finite samples, and that the MPL estimates often enjoy comparable precision as the ML estimates. We apply our methods to the analysis of comorbid symptoms in the obsessive compulsive disorder study. Our models' random effects structure has more straightforward interpretation than those of competing methods, thus should usefully augment tools available for LCA of multilevel data.     

Feature-specific penalized latent class analysis for genomic data

Genomic data are often characterized by a moderate to large number of categorical variables observed for relatively few subjects. Some of the variables may be missing or noninformative. An example of such data is loss of heterozygosity (LOH), a dichotomous variable, observed on a moderate number of genetic markers. We first consider a latent class model where, conditional on unobserved membership in one of k classes, the variables are independent with probabilities determined by a regression model of low dimension q. Using a family of penalties including the ridge and LASSO, we extend this model to address higher-dimensional problems. Finally, we present an orthogonal map that transforms marker space to a space of "features" for which the constrained model has better predictive power. We demonstrate these methods on LOH data collected at 19 markers from 93 brain tumor patients. For this data set, the existing unpenalized latent class methodology does not produce estimates. Additionally, we show that posterior classes obtained from this method are associated with survival for these patients.     

Latent Class Modeling Approaches for Assessing Diagnostic Error without a Gold Standard: With Applications to p53 Immunohistochemical Assays in Bladder Tumors

Improved characterization of tumors for purposes of guiding treatment decisions for cancer patients will require that accurate and reproducible assays be developed for a variety of tumor markers. No gold standards exist for most tumor marker assays. Therefore, estimates of assay sensitivity and specificity cannot be obtained unless a latent class model-based approach is used. Our goal in this article is to estimate sensitivity and specificity for p53 immunohistochemical assays of bladder tumors using data from a reproducibility study conducted by the National Cancer Institute Bladder Tumor Marker Network. We review latent class modeling approaches proposed by previous authors, and we find that many of these approaches impose assumptions about specimen heterogeneity that are not consistent with the biology of bladder tumors. We present flexible mixture model alternatives that are biologically plausible for our example, and we use them to estimate sensitivity and specificity for our p53 assay example. These mixture models are shown to offer an improvement over other methods in a variety of settings, but we caution that, in general, care must be taken in applying latent class models.     

The latent process decomposition of cDNA microarray data sets

We present a new computational technique (a software implementation, data sets, and supplementary information are available at http://www.enm.bris.ac.uk/lpd/) which enables the probabilistic analysis of cDNA microarray data and we demonstrate its effectiveness in identifying features of biomedical importance. A hierarchical Bayesian model, called Latent Process Decomposition (LPD), is introduced in which each sample in the data set is represented as a combinatorial mixture over a finite set of latent processes, which are expected to correspond to biological processes. Parameters in the model are estimated using efficient variational methods. This type of probabilistic model is most appropriate for the interpretation of measurement data generated by cDNA microarray technology. For determining informative substructure in such data sets, the proposed model has several important advantages over the standard use of dendrograms. First, the ability to objectively assess the optimal number of sample clusters. Second, the ability to represent samples and gene expression levels using a common set of latent variables (dendrograms cluster samples and gene expression values separately which amounts to two distinct reduced space representations). Third, in constrast to standard cluster models, observations are not assigned to a single cluster and, thus, for example, gene expression levels are modeled via combinations of the latent processes identified by the algorithm. We show this new method compares favorably with alternative cluster analysis methods. To illustrate its potential, we apply the proposed technique to several microarray data sets for cancer. For these data sets it successfully decomposes the data into known subtypes and indicates possible further taxonomic subdivision in addition to highlighting, in a wholly unsupervised manner, the importance of certain genes which are known to be medically significant. To illustrate its wider applicability, we also illustrate its performance on a microarray data set for yeast.     

Estimating linear causality in the presence of latent variables

Learning causality from data is known as the causal discovery problem, and it is an important and relatively new field. In many applications, there often exist latent variables, if such latent variables are completely ignored, which can lead to the estimation results seriously biased. In this paper, a method of combining exploratory factor analysis and path analysis (EFA-PA) is proposed to infer the causality in the presence of latent variables. Our method expands latent variables as well as their linear causal relationships with observed variables, which enhances the accuracy of causal models. Such model can be thought of as the simplest possible causal models for continuous data. The EFA-PA is very similar to that of structural equation model, but the theoretical model established by the structural equation model needs to be modified in the process of data fitting until the ideal model is established.The model gained by EFA-PA not only avoids subjectivity but also reduces estimation complexity. It is found that the EFA-PA estimation model is superior to the other models. EFA-PA can provides a basis for the correct estimation of the causal relationship between the observed variables in the presence of latent variables. The experiment shows that EFA-PA is better than the structural equation model.     

When Do Latent Class Models Overstate Accuracy for Diagnostic and Other Classifiers in the Absence of a Gold Standard?

Latent class models are increasingly used to assess the accuracy of medical diagnostic tests and other classifications when no gold standard is available and the true state is unknown. When the latent class is treated as the true class, the latent class models provide measures of components of accuracy including specificity and sensitivity and their complements, type I and type II error rates. The error rates according to the latent class model differ from the true error rates, however, and empirical comparisons with a gold standard suggest the true error rates often are larger. We investigate conditions under which the true type I and type II error rates are larger than those provided by the latent class models. Results from Uebersax (1988, Psychological Bulletin 104, 405-416) are extended to accommodate random effects and covariates affecting the responses. The results are important for interpreting the results of latent class analyses. An error decomposition is presented that incorporates an error component from invalidity of the latent class model.     

The Generalised Estimating Equations: An Annotated Bibliography

The Generalised Estimating Equations (GEE) proposed by Liang and Zeger (1986) and Zeger and Liang (1986) have found considerable attention in the last ten years and several extensions have been proposed. In this annotated bibliography we describe the development of the GEE and its extensions during the last decade. Additionally, we discuss advantages and disadvantages of the different parametrisations that have been proposed in the literature. Furthermore, we review regression diagnostic techniques and approaches for dealing with missing data. We give an insight to the different fields of application in biometry. We also describe the software available for the GEE.     

Marginalized transition models and likelihood inference for longitudinal categorical data

Marginal generalized linear models are now frequently used for the analysis of longitudinal data. Semiparametric inference for marginal models was introduced by Liang and Zeger (1986, Biometrics 73, 13-22). This article develops a general parametric class of serial dependence models that permits likelihood-based marginal regression analysis of binary response data. The methods naturally extend the first-order Markov models of Azzalini (1994, Biometrika 81, 767-775) and prove computationally feasible for long series.     

Generalized linear mixture models for handling nonignorable dropouts in longitudinal studies

This paper presents a method for analysing longitudinal data when there are dropouts. In particular, we develop a simple method based on generalized linear mixture models for handling nonignorable dropouts for a variety of discrete and continuous outcomes. Statistical inference for the model parameters is based on a generalized estimating equations (GEE) approach (Liang and Zeger, 1986). The proposed method yields estimates of the model parameters that are valid when nonresponse is nonignorable under a variety of assumptions concerning the dropout process. Furthermore, the proposed method can be implemented using widely available statistical software. Finally, an example using data from a clinical trial of contracepting women is used to illustrate the methodology.     

Derivative component analysis for mass spectral serum proteomic profiles

Background

As a promising way to transform medicine, mass spectrometry based proteomics technologies have seen a great progress in identifying disease biomarkers for clinical diagnosis and prognosis. However, there is a lack of effective feature selection methods that are able to capture essential data behaviors to achieve clinical level disease diagnosis. Moreover, it faces a challenge from data reproducibility, which means that no two independent studies have been found to produce same proteomic patterns. Such reproducibility issue causes the identified biomarker patterns to lose repeatability and prevents it from real clinical usage.

Methods

In this work, we propose a novel machine-learning algorithm: derivative component analysis (DCA) for high-dimensional mass spectral proteomic profiles. As an implicit feature selection algorithm, derivative component analysis examines input proteomics data in a multi-resolution approach by seeking its derivatives to capture latent data characteristics and conduct de-noising. We further demonstrate DCA's advantages in disease diagnosis by viewing input proteomics data as a profile biomarker via integrating it with support vector machines to tackle the reproducibility issue, besides comparing it with state-of-the-art peers.

Results

Our results show that high-dimensional proteomics data are actually linearly separable under proposed derivative component analysis (DCA). As a novel multi-resolution feature selection algorithm, DCA not only overcomes the weakness of the traditional methods in subtle data behavior discovery, but also suggests an effective resolution to overcoming proteomics data's reproducibility problem and provides new techniques and insights in translational bioinformatics and machine learning. The DCA-based profile biomarker diagnosis makes clinical level diagnostic performances reproducible across different proteomic data, which is more robust and systematic than the existing biomarker discovery based diagnosis.

Conclusions

Our findings demonstrate the feasibility and power of the proposed DCA-based profile biomarker diagnosis in achieving high sensitivity and conquering the data reproducibility issue in serum proteomics. Furthermore, our proposed derivative component analysis suggests the subtle data characteristics gleaning and de-noising are essential in separating true signals from red herrings for high-dimensional proteomic profiles, which can be more important than the conventional feature selection or dimension reduction. In particular, our profile biomarker diagnosis can be generalized to other omics data for derivative component analysis (DCA)'s nature of generic data analysis.

     

Inference for nonparanormal partial correlation via regularized rank-based nodewise regression

Partial correlation is a common tool in studying conditional dependence for Gaussian distributed data. However, partial correlation being zero may not be equivalent to conditional independence under non-Gaussian distributions. In this paper, we propose a statistical inference procedure for partial correlations under the high-dimensional nonparanormal (NPN) model where the observed data are normally distributed after certain monotone transformations. The NPN partial correlation is the partial correlation of the normal transformed data under the NPN model, which is a more general measure of conditional dependence. We estimate the NPN partial correlations by regularized nodewise regression based on the empirical ranks of the original data. A multiple testing procedure is proposed to identify the nonzero NPN partial correlations. The proposed method can be carried out by a simple coordinate descent algorithm for lasso optimization. It is easy-to-implement and computationally more efficient compared to the existing methods for estimating NPN graphical models. Theoretical results are developed to show the asymptotic normality of the proposed estimator and to justify the proposed multiple testing procedure. Numerical simulations and a case study on brain imaging data demonstrate the utility of the proposed procedure and evaluate its performance compared to the existing methods. Data used in preparation of this article were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database.