Composite Likelihood Approach Research Articles

Exploiting multivariate network meta-analysis: A calibrated Bayesian composite likelihood inference.

Multivariate network meta-analysis has emerged as a powerful tool in evidence synthesis by incorporating multiple outcomes and treatments. Despite its advantages, this method comes with methodological challenges, such as the issue of unreported within-study correlations among treatments and outcomes, which potentially lead to misleading conclusions. In this paper, we proposed a calibrated Bayesian composite likelihood approach to overcome this limitation. The proposed method eliminated the need to specify a full likelihood function while allowing for the unavailability of within-study correlations among treatments and outcomes. Additionally, we developed a hybrid Gibbs sampler algorithm along with the Open-Faced Sandwich post-sampling adjustment to enable robust posterior inference. Through comprehensive simulation studies, we demonstrated that the proposed approach yielded unbiased estimates while maintaining coverage probabilities close to the nominal level. Furthermore, we implemented the proposed method on two real-world network meta-analysis datasets; one comparing treatment procedures for the root coverage and another comparing treatments for anaemia in chronic kidney disease patients.

Network meta-analysis made simple: a composite likelihood approach.

What is already known?: Network meta-analysis extends conventional pairwise meta-analysis by simultaneously synthesizing multiple interventions in a single integrated analysis.A significant challenge in network meta-analysis is the lack of reported within-study correlations among treatment comparisons in the published studies.What is new?: We propose a new method for network meta-analysis that ensures vaild statistical inference without the need for knowledge of within-study correlations.The proposed method employs a composite likelihood and a sandwich-type robust variance estimator, offering a computationally efficient and scalable solution, particularly for network meta-analysis with a large number of treatments and studies.Potential impact for Research Synthesis Methods readers: The proposed method can be easily applied to any univariate network meta-analysis project without requiring knowledge of within-study correlations among treatment comparisons.

The use of real-world data for clinical investigation of effectiveness in drug development

ABSTRACT With the growing interest in leveraging real-world data (RWD) to support effectiveness evaluations for new indications, new target populations, and post-market performance, the United States Food and Drug Administration has published several guidance documents on RWD sources and real-world studies (RWS) to assist sponsors in generating credible real-world evidence (RWE). Meanwhile, the randomized controlled trial (RCT) remains the gold standard in drug evaluation. Along this line, we propose a hybrid two-stage adaptive design to evaluate effectiveness based on evidence from both RCT and RWS. At the first stage, a typical non-inferiority test is conducted using RCT data to test for not-ineffectiveness. Once not-ineffectiveness is established, the study proceeds to the second stage to conduct an RWS and test for effectiveness using integrated information from RCT and RWD. The composite likelihood approach is implemented as a down-weighing strategy to account for the impact of high variability in RWS population. An optimal sample size determination procedure for RCT and RWS is introduced, aiming to achieve the minimal expected sample size. Through extensive numerical study, the proposed design demonstrates the ability to control type I error inflation in most cases and consistently maintain statistical power above the desired level. In general, this RCT/RWS hybrid two-stage adaptive design is beneficial for effectiveness evaluations in drug development, especially for oncology and rare diseases.

Accommodating spatio-temporal dependency in airline demand modeling

The objective of the current study is to examine monthly air passenger departures at the airport level considering spatial interactions between airports. In this study, we develop a novel spatial grouped generalized ordered probit (SGGOP) model system of monthly air passenger departures at the airport level. Specifically, we estimate two variants of spatial models including spatial lag model and spatial error model. In the presence of repeated demand measures for the airports, we also consider temporal variations of spatial correlation effects among proximally located airports by employing space and time-based weight matrix. The proposed model is estimated using monthly air passenger departures for five years for 369 airports across the US. The proposed spatial model is implemented using composite marginal likelihood (CML) approach that offers a computationally feasible framework. From the estimation results, it is evident that air passenger departures at the airport level are influenced by different factors including MSA specific demographic characteristics, built environment characteristics, airport specific factors, spatial factors, and temporal factors. Moreover, spatial autocorrelation parameter is found to be significant validating our hypothesis of the presence of common unobserved factors associated with the spatial unit of analysis. In this study, we also perform a validation analysis to examine the predictive performance of the proposed spatial models. The results highlight the superiority of spatial error model compared to spatial lag model and the independent model that ignores the spatial interactions. Finally, we undertake an elasticity analysis to quantify the impact of the independent variables.

Demographic inference for spatially heterogeneous populations using long shared haplotypes

We introduce a modified spatial Λ-Fleming–Viot process to model the ancestry of individuals in a population occupying a continuous spatial habitat divided into two areas by a sharp discontinuity of the dispersal rate and effective population density. We derive an analytical formula for the expected number of shared haplotype segments between two individuals depending on their sampling locations. This formula involves the transition density of a skew diffusion which appears as a scaling limit of the ancestral lineages of individuals in this model. We then show that this formula can be used to infer the dispersal parameters and the effective population density of both regions, using a composite likelihood approach, and we demonstrate the efficiency of this method on a range of simulated data sets.

Demographically explicit scans for barriers to gene flow using gIMble.

Identifying regions of the genome that act as barriers to gene flow between recently diverged taxa has remained challenging given the many evolutionary forces that generate variation in genetic diversity and divergence along the genome, and the stochastic nature of this variation. Progress has been impeded by a conceptual and methodological divide between analyses that infer the demographic history of speciation and genome scans aimed at identifying locally maladaptive alleles i.e. genomic barriers to gene flow. Here we implement genomewide IM blockwise likelihood estimation (gIMble), a composite likelihood approach for the quantification of barriers, that bridges this divide. This analytic framework captures background selection and selection against barriers in a model of isolation with migration (IM) as heterogeneity in effective population size (Ne) and effective migration rate (me), respectively. Variation in both effective demographic parameters is estimated in sliding windows via pre-computed likelihood grids. gIMble includes modules for pre-processing/filtering of genomic data and performing parametric bootstraps using coalescent simulations. To demonstrate the new approach, we analyse data from a well-studied pair of sister species of tropical butterflies with a known history of post-divergence gene flow: Heliconius melpomene and H. cydno. Our analyses uncover both large-effect barrier loci (including well-known wing-pattern genes) and a genome-wide signal of a polygenic barrier architecture.

Frugal Gaussian clustering of huge imbalanced datasets through a bin-marginal approach

Clustering conceptually reveals all its interest when the dataset size considerably increases since there is the opportunity to discover tiny but possibly high value clusters which were out of reach with more modest sample sizes. However, clustering is practically faced to computer limits with such high data volume, since possibly requiring extremely high memory and computation resources. In addition, the classical subsampling strategy, often adopted to overcome these limitations, is expected to heavily failed for discovering clusters in the highly imbalanced cluster case. Our proposal first consists in drastically compressing the data volume by just preserving its bin-marginal values, thus discarding the bin-cross ones. Despite this extreme information loss, we then prove generic identifiability property for the diagonal mixture model and also introduce a specific EM-like algorithm associated to a composite likelihood approach. This latter is extremely more frugal than a regular but unfeasible EM algorithm expected to be used on our bin-marginal data, while preserving all consistency properties. Finally, numerical experiments highlight that this proposed method outperforms subsampling both in controlled simulations and in various real applications where imbalanced clusters may typically appear, such as image segmentation, hazardous asteroids recognition and fraud detection.

Rhometa: Population recombination rate estimation from metagenomic read datasets.

Prokaryotic evolution is influenced by the exchange of genetic information between species through a process referred to as recombination. The rate of recombination is a useful measure for the adaptive capacity of a prokaryotic population. We introduce Rhometa (https://github.com/sid-krish/Rhometa), a new software package to determine recombination rates from shotgun sequencing reads of metagenomes. It extends the composite likelihood approach for population recombination rate estimation and enables the analysis of modern short-read datasets. We evaluated Rhometa over a broad range of sequencing depths and complexities, using simulated and real experimental short-read data aligned to external reference genomes. Rhometa offers a comprehensive solution for determining population recombination rates from contemporary metagenomic read datasets. Rhometa extends the capabilities of conventional sequence-based composite likelihood population recombination rate estimators to include modern aligned metagenomic read datasets with diverse sequencing depths, thereby enabling the effective application of these techniques and their high accuracy rates to the field of metagenomics. Using simulated datasets, we show that our method performs well, with its accuracy improving with increasing numbers of genomes. Rhometa was validated on a real S. pneumoniae transformation experiment, where we show that it obtains plausible estimates of the rate of recombination. Finally, the program was also run on ocean surface water metagenomic datasets, through which we demonstrate that the program works on uncultured metagenomic datasets.

Principled leveraging of external data in the evaluation of diagnostic devices via the propensity score‐integrated composite likelihood approach

In the area of diagnostics, it is common practice to leverage external data to augment a traditional study of diagnostic accuracy consisting of prospectively enrolled subjects to potentially reduce the time and/or cost needed for the performance evaluation of an investigational diagnostic device. However, the statistical methods currently being used for such leveraging may not clearly separate study design and outcome data analysis, and they may not adequately address possible bias due to differences in clinically relevant characteristics between the subjects constituting the traditional study and those constituting the external data. This paper is intended to draw attention in the field of diagnostics to the recently developed propensity score-integrated composite likelihood approach, which originally focused on therapeutic medical products. This approach applies the outcome-free principle to separate study design and outcome data analysis and can mitigate bias due to imbalance in covariates, thereby increasing the interpretability of study results. While this approach was conceived as a statistical tool for the design and analysis of clinical studies for therapeutic medical products, here, we will show how it can also be applied to the evaluation of sensitivity and specificity of an investigational diagnostic device leveraging external data. We consider two common scenarios for the design of a traditional diagnostic device study consisting of prospectively enrolled subjects, which is to be augmented by external data. The reader will be taken through the process of implementing this approach step-by-step following the outcome-free principle that preserves study integrity.

Chromosome Fissions and Fusions Act as Barriers to Gene Flow between Brenthis Fritillary Butterflies.

Chromosome rearrangements are thought to promote reproductive isolation between incipient species. However, it is unclear how often, and under what conditions, fission and fusion rearrangements act as barriers to gene flow. Here we investigate speciation between two largely sympatric fritillary butterflies, Brenthis daphne and Brenthis ino. We use a composite likelihood approach to infer the demographic history of these species from whole-genome sequence data. We then compare chromosome-level genome assemblies of individuals from each species and identify a total of nine chromosome fissions and fusions. Finally, we fit a demographic model where effective population sizes and effective migration rate vary across the genome, allowing us to quantify the effects of chromosome rearrangements on reproductive isolation. We show that chromosomes involved in rearrangements experienced less effective migration since the onset of species divergence and that genomic regions near rearrangement points have a further reduction in effective migration rate. Our results suggest that the evolution of multiple rearrangements in the B. daphne and B. ino populations, including alternative fusions of the same chromosomes, have resulted in a reduction in gene flow. Although fission and fusion of chromosomes are unlikely to be the only processes that have led to speciation between these butterflies, this study shows that these rearrangements can directly promote reproductive isolation and may be involved in speciation when karyotypes evolve quickly.

Composite Likelihoods with Bounded Weights in Extrapolation of Data

ABSTRACT Among many efforts to facilitate timely access to safe and effective medicines to children, increased attention has been given to extrapolation. Loosely, it is the leveraging of conclusions or available data from adults or older age groups to draw conclusions for the target pediatric population when it can be assumed that the course of the disease and the expected response to a medicinal product would be sufficiently similar in the pediatric and the reference population. Extrapolation then can be characterized as a statistical mapping of information from the reference (adults or older age groups) to the target pediatric population. The translation, or loosely mapping of information, can be through a composite likelihood approach where the likelihood of the reference population is weighted by exponentiation and that this exponent is related to the value of the mapped information in the target population. The weight is bounded above and below recognizing the fact that similarity (of the disease and the expected response) is still valid despite variability of response between the cohorts. Maximum likelihood approaches are then used for estimation of parameters, and asymptotic theory is used to derive distributions of estimates for use in inference. Hence, the estimation of effects in the target population borrows information from the reference population. In addition, this manuscript also talks about how this method is related to the Bayesian statistical paradigm.

What drives the designation of protected areas? Accounting for spatial dependence using a composite marginal likelihood approach

Previous research indicates that policymakers make biodiversity conservation decisions with the goal of minimizing opportunity costs, as opposed to balancing conservation benefits and opportunity costs. However, such research used coarse biodiversity data and did not consider spatial dependence in observed conservation decisions. The present study estimates conservation choice models for two European countries (Spain and Italy) that, for the first time, include fine-resolution indicators of biodiversity conservation benefits and opportunity costs, and that account for spatial dependence using a pairwise composite marginal likelihood approach. For the preferred model specifications, we find that a 1% increase in species richness levels is associated with increases in the probability of protection of 0.59% and 0.22% in Spain and Italy, respectively. We also find evidence of spatial correlation and that accounting for it substantially affects the elasticity effects implied by the logit regression models. Although our findings confirm that protected area designations are consistently negatively associated with the potential for productive land-uses, local biodiversity levels may have played a larger role in protected area location decisions than suggested previously.

Mixture of Networks for Clustering Categorical Data: A Penalized Composite Likelihood Approach

One of the challenges in clustering categorical data is the curse of dimensionality caused by the inherent sparsity of high-dimensional data, the records of which include a large number of attributes. The latent class model (LCM) assumes local independence between the variables in clusters, and is a parsimonious model-based clustering approach that has been used to circumvent the problem. The mixture of a log-linear model is more flexible but requires more parameters to be estimated. In this research, we recognize that each categorical observation can be conceived as a network with pairwise linked nodes, which are the response levels of the observation attributes. Therefore, the categorical data for clustering is considered a finite mixture of different component layer networks with distinct patterns. We apply a penalized composite likelihood approach to a finite mixture of networks for sparse multivariate categorical data to reduce the number of parameters, implement the EM algorithm to estimate the model parameters, and show that the estimates are consistent and satisfy asymptotic normality. The performance of the proposed approach is shown to be better in comparison with the conventional methods for both synthetic and real datasets.

Inference for low‐ and high‐dimensional inhomogeneous Gibbs point processes

AbstractGibbs point processes (GPPs) constitute a large and flexible class of spatial point processes with explicit dependence between the points. They can model attractive as well as repulsive point patterns. Feature selection procedures are an important topic in high‐dimensional statistical modeling. In this paper, a composite likelihood (in particular pseudo‐likelihood) approach regularized with convex and nonconvex penalty functions is proposed to handle statistical inference for possibly high‐dimensional inhomogeneous GPPs. We particularly investigate the setting where the number of covariates diverges as the domain of observation increases. Under some conditions provided on the spatial GPP and on penalty functions, we show that the oracle property, consistency and asymptotic normality hold. Our results also cover the low‐dimensional case which fills a large gap in the literature. Through simulation experiments, we validate our theoretical results and finally, an application to a tropical forestry dataset illustrates the use of the proposed approach.

Separable spatio‐temporal kriging for fast virtual sensing

AbstractEnvironmental monitoring is a task that requires to surrogate system‐wide information with limited sensor readings. Under the proximity principle, an environmental monitoring system can be based on the virtual sensing logic and then rely on distance‐based prediction methods, foremostly spatio‐temporal kriging. The last one is cumbersome with large datasets, but we show that a suitable separability assumption reduces its computational cost to an extent broader than considered typically. Only spatial interpolation needs to be performed in a centralized way, while forecasting can be delegated to each sensor. This simplification is related to the fact that two separate models are involved, one in time and one in the space domain. Any of the two models can be replaced without re‐estimating the other under a composite likelihood (CL) approach. Moreover, the use of convenient spatial and temporal models eases up computation, not only in the CL approach, but also in maximum likelihood estimation. We show that this perspective on kriging allows to perform virtual sensing even in the case of tall datasets.

RADseq Data Suggest Occasional Hybridization between Microcebus murinus and M. ravelobensis in Northwestern Madagascar.

The occurrence of natural hybridization has been reported in a wide range of organisms, including primates. The present study focuses on the endemic lemurs of Madagascar, primates for which only a few species occur in sympatry or parapatry with congeners, thereby creating limited opportunity for natural hybridization. This study examines RADseq data from 480 individuals to investigate whether the recent expansion of Microcebus murinus towards the northwest and subsequent secondary contact with Microcebus ravelobensis has resulted in the occurrence of hybridization between the two species. Admixture analysis identified one individual with 26% of nuclear admixture, which may correspond to an F2- or F3-hybrid. A composite-likelihood approach was subsequently used to test the fit of alternative phylogeographic scenarios to the genomic data and to date introgression. The simulations yielded support for low levels of gene flow (2Nm0 = 0.063) between the two species starting before the Last Glacial Maximum (between 54 and 142 kyr). Since M. murinus most likely colonized northwestern Madagascar during the Late Pleistocene, the rather recent secondary contact with M. ravelobensis has likely created the opportunity for occasional hybridization. Although reproductive isolation between these distantly related congeners is not complete, it is effective in maintaining species boundaries.

Demographic Reconstruction of Antarctic Fur Seals Supports the Krill Surplus Hypothesis.

Much debate surrounds the importance of top-down and bottom-up effects in the Southern Ocean, where the harvesting of over two million whales in the mid twentieth century is thought to have produced a massive surplus of Antarctic krill. This excess of krill may have allowed populations of other predators, such as seals and penguins, to increase, a top-down hypothesis known as the ‘krill surplus hypothesis’. However, a lack of pre-whaling population baselines has made it challenging to investigate historical changes in the abundance of the major krill predators in relation to whaling. Therefore, we used reduced representation sequencing and a coalescent-based maximum composite likelihood approach to reconstruct the recent demographic history of the Antarctic fur seal, a pinniped that was hunted to the brink of extinction by 18th and 19th century sealers. In line with the known history of this species, we found support for a demographic model that included a substantial reduction in population size around the time period of sealing. Furthermore, maximum likelihood estimates from this model suggest that the recovered, post-sealing population at South Georgia may have been around two times larger than the pre-sealing population. Our findings lend support to the krill surplus hypothesis and illustrate the potential of genomic approaches to shed light on long-standing questions in population biology.

Learning Human Activity Patterns Using Clustered Point Processes With Active and Inactive States

Modeling event patterns is a central task in a wide range of disciplines. In applications such as studying human activity patterns, events often arrive clustered with sporadic and long periods of inactivity. Such heterogeneity in event patterns poses challenges for existing point process models. In this article, we propose a new class of clustered point processes that alternate between active and inactive states. The proposed model is flexible, highly interpretable, and can provide useful insights into event patterns. A composite likelihood approach and a composite EM estimation procedure are developed for efficient and numerically stable parameter estimation. We study both the computational and statistical properties of the estimator including convergence, consistency, and asymptotic normality. The proposed method is applied to Donald Trump’s Twitter data to investigate if and how his behaviors evolved before, during, and after the presidential campaign. Additionally, we analyze large-scale social media data from Sina Weibo and identify interesting groups of users with distinct behaviors.

An SEIR Model with Time-Varying Coefficients for Analyzing the SARS-CoV-2 Epidemic.

In this study, we propose a time‐dependent susceptible‐exposed‐infected‐recovered (SEIR) model for the analysis of the SARS‐CoV‐2 epidemic outbreak in three different countries, the United States, Italy, and Iceland using public data inherent the numbers of the epidemic wave. Since several types and grades of actions were adopted by the governments, including travel restrictions, social distancing, or limitation of movement, we want to investigate how these measures can affect the epidemic curve of the infectious population. The parameters of interest for the SEIR model were estimated employing a composite likelihood approach. Moreover, standard errors have been corrected for temporal dependence. The adoption of restrictive measures results in flatten epidemic curves, and the future evolution indicated a decrease in the number of cases.

A composite likelihood approach for inference under photometric redshift uncertainty

ABSTRACTObtaining accurately calibrated redshift distributions of photometric samples is one of the great challenges in photometric surveys like LSST, Euclid, HSC, KiDS, and DES. We present an inference methodology that combines the redshift information from the galaxy photometry with constraints from two-point functions, utilizing cross-correlations with spatially overlapping spectroscopic samples, and illustrate the approach on CosmoDC2 simulations. Our likelihood framework is designed to integrate directly into a typical large-scale structure and weak lensing analysis based on two-point functions. We discuss efficient and accurate inference techniques that allow us to scale the method to the large samples of galaxies to be expected in LSST. We consider statistical challenges like the parametrization of redshift systematics, discuss and evaluate techniques to regularize the sample redshift distributions, and investigate techniques that can help to detect and calibrate sources of systematic error using posterior predictive checks. We evaluate and forecast photometric redshift performance using data from the CosmoDC2 simulations, within which we mimic a DESI-like spectroscopic calibration sample for cross-correlations. Using a combination of spatial cross-correlations and photometry, we show that we can provide calibration of the mean of the sample redshift distribution to an accuracy of at least 0.002(1 + z), consistent with the LSST-Y1 science requirements for weak lensing and large-scale structure probes.