Conditional Likelihood Research Articles

MRF Models Based on a Neighborhood Adaptive Class Conditional Likelihood For Multimodal Change Detection

Statistical methods for automatic change detection, in heterogeneous bitemporal satellite images, remains a challenging research topic in remote sensing mainly because this research field involves the processing of image data with potentially very different statistical behaviors. In this paper, we propose a new Bayesian statistical approach, relying on spatially adaptive class conditional likelihoods which are also adaptive to the considered imaging modality pair and whose parameters are estimated in a first preliminary estimation step. Once that estimation is done, a second stage is dedicated to the change detection segmentation itself based on this likelihood model defined for each pixel and for each imaging modality. In this context, we compare and discuss the performance of different Markovian segmentation strategies obtained in the sense of several non-hierarchical or hierarchical Markovian estimators on real satellite images with different imaging multi-modalities. Based on our original pixel-wise likelihood model, we also compare these Markovian segmentation strategies over the existing state-of-the-art heterogeneous change detection algorithms proposed in the literature.

Marginal, conditional, and pseudo likelihood ratio approaches for biomarker combination to predict a binary disease outcome.

It is a common practice in public health research that multiple biomarkers are collected to diagnose or predict a disease outcome. A natural question is how to combine multiple biomarkers to improve the diagnostic accuracy. It has been shown by Neyman-Pearson lemma that the likelihood ratio statistic achieves the optimal AUC in theory. However, practical difficulty often lies in the estimation of the multivariate density functions. We propose three novel methods for the biomarker combination, with the idea of breaking down the joint densities to a series of univariate densities. The marginal likelihood ratio approach only assumes the marginal distribution of each biomarker. While the conditional likelihood ratio (CLR) and pseudo likelihood ratio (PLR) approaches assume the conditional distributions of a marker given others, and hence make use of the correlation structure to estimate the combination rules. The proposed methods make it much easier to assume and validate the univariate distributions of a biomarker than making multivariate distributional assumptions. Extensive simulation studies demonstrate that the CLR and the PLR approaches outperform many existing methods, and are therefore recommended for practical use. The proposed methods are motivated by and applied to a biomarker study to diagnose childhood autism/autism spectrum disorder.

The BerG generalized autoregressive moving average model for count time series

In this work, we present a new generalized autoregressive moving average model (GARMA), based on the Bernoulli-geometric (BerG) distribution, for modeling the conditional mean of count time series. The proposed model is able to deal with the equi, under or over-dispersed data. Our main contribution is to suggest a GARMA model with a response variable following a BerG distribution, which also accommodates zero inflated (or deflated) data. The proposed model combines the dispersion flexibility with the inclusion of covariates and lagged terms to model the conditional mean response, inducing an autocorrelation structure (usually relevant in time series). We exhibit the conditional maximum likelihood estimation, the hypothesis testing inference, the diagnostic analysis, and the out-of-sample forecasting procedure. Using the closed-form quantile function of the BerG distribution, the confidence intervals for out-of-sample forecasts are easily obtained. In particular, we provide the closed-form expressions for the conditional score vector and conditional Fisher information matrix. Moreover, we developed a computational study which confirmed that the maximum likelihood estimators are consistent for all dispersion scenarios. And finally, we illustrate the applicability of the postulated model by exploring two real data applications.

Continuous time-interaction processes for population size estimation, with an application to drug dealing in Italy.

We introduce a time-interaction point process where the occurrence of an event can increase (self-excitement) or reduce (self-correction) the probability of future events. Self-excitement and self-correction are allowed to be triggered by the same event, at different timescales; other effects such as those of covariates, unobserved heterogeneity, and temporal dependence are also allowed in the model. We focus on capture-recapture data, as our work is motivated by an original example about the estimation of the total number of drug dealers in Italy. To do so, we derive a conditional likelihood formulation where only subjects with at least one capture are involved in the inference process. The result is a novel and flexible continuous-time population size estimator. A simulation study and the analysis of our motivating example illustrate the validity of our approach in severalscenarios.

Constraining organic matter composition and dynamics as a dominant driver of hypoxic blackwater risk during river Murray floodplain inundation

AbstractThe ecology of floodplain ecosystems evolved according to the historical frequency and extent of inundation. In many dryland rivers, inundation frequency has reduced due to regulation, competition for water resources and climate change. In some rivers infrastructure has been constructed to enable temporary rises in water level and more frequent floodplain inundation, delivering environmental water to ecosystems that are dependent on surface water. During such events, the release of dissolved organic carbon (DOC) from inundated plant material may result in depletion of dissolved oxygen (DO). If the rate of DO depletion exceeds re‐aeration, hypoxic conditions can occur. Models have been developed to represent these processes, however, there is a wide range of chemical and biological interactions, and hence model parameters, involved. The aim of this research was: (1) identify the dominant parameters through sensitivity analysis, (2) design and implement a field monitoring program to quantify the inherent variability in those parameters, and (3) translate that input variability into the modelled DO, ultimately to support risk management decisions when planning delivery of environmental water. The results indicated that the mass of organic matter on a floodplain had the greatest impact on the modelled DO concentrations. Based on the field monitoring results, the steady state load of organic matter, that is, when the accumulation and decay rates are equal, was estimated, and vegetation mapping used to apply the field monitoring results across the floodplain for a 206 km reach of river of the River Murray, Australia. The model results from multiple, cumulative, operations identified one particular high‐risk operational site. The results are useful to prioritize monitoring effort to focus on the most sensitive model parameters and indicate that the likelihood of hypoxic conditions can be reduced through slower rates of inundation and timing events to coincide with periods with lower water temperature. The methodology developed can be transferred to other sites where hypoxic conditions are a potential outcome associated with delivery of environmental water.

Generative Probabilistic Wind Speed Forecasting: A Variational Recurrent Autoencoder Based Method

In this paper, a novel framework for probabilistic wind speed forecasting (PWSF) based on variational recurrent autoencoders (VRAEs) via a generative perspective is proposed. Compared with a traditional optimization objective maximizing the conditional likelihood of the target wind speed directly, a novel optimization objective maximizing the likelihood of the complete wind speed sequence is proposed to better model the temporal relationship within the complete wind speed sequence. As directly maximizing the proposed objective is intractable, we show that it can be alternatively achieved via the help of the VRAE learning principle. The framework of the proposed VRAE based PWSF is composed of two phases, training a VRAE with maximizing the variational lower bound of the likelihood of the complete wind speed sequence and forecasting the target wind speed from the generative perspective through the approximate posterior learned by the VRAE. Computational results demonstrate that the proposed method outperforms other benchmarking deterministic and probabilistic forecasting models in terms of the negative form of continuous ranked probability score (CRPS*). Compared with other benchmarking models for probabilistic forecasting, the proposed method achieves better sharpness and overall quality of prediction intervals (PIs) as well as a comparable reliability. Results verify advantages of the proposed VARE based PWSF method.

Heart Disease Detection Using Machine Learning Techniques

According to a recent World Health Organization survey, 17.9 million people die each year as a result of heart-related disorders, and the number is continuously growing. With a rising population and sickness, it is becoming more difficult to diagnose disease and provide pr oper therapy at the appropriate time. However, there is a ray of optimism in that recent technological breakthroughs have expedited the public health sector by generating sophisticated functional biomedical solutions.The purpose of this paper is to examine the different data mining techniques, namely Naive Bayes, Random Forest Classification, Decision Tree, and Support Vector Machine, using a qualified dataset for Heart disease prediction, which includes attributes such as gender, age, chest pain type, blood pressure, blood sugar, and so on. The research entails determining the correlations between the different qualities of the dataset using typical data mining techniques and then using the attributes to forecast the likelihood of a cardiac condition. These machine learning algorithms need less time to forecast disease with more precision, reducing the loss of priceless lives all across the world.

2-D Rayleigh autoregressive moving average model for SAR image modeling

Two-dimensional (2-D) autoregressive moving average (ARMA) models are commonly applied to describe real-world image data, usually assuming Gaussian or symmetric noise. However, real-world data often present non-Gaussian signals, with asymmetrical distributions and strictly positive values. In particular, SAR images are known to be well characterized by the Rayleigh distribution. In this context, the ARMA model tailored for 2-D Rayleigh-distributed data is introduced—the 2-D RARMA model. The 2-D RARMA model is derived and conditional likelihood inferences are discussed. The proposed model was submitted to extensive Monte Carlo simulations to evaluate the performance of the conditional maximum likelihood estimators. Moreover, in the context of SAR image processing, two comprehensive numerical experiments were performed comparing anomaly detection and image modeling results of the proposed model with traditional 2-D ARMA models and competing methods in the literature.

Nonshared environmental factors in the aetiology of autism and other neurodevelopmental conditions: a monozygotic co-twin control study

BackgroundA significant proportion of variation in likelihood of neurodevelopmental conditions (NDCs) has been attributed to nonshared environmental (NSE) factors, although it remains unclear which NSE factors pose specific risks for certain NDCs.MethodsA monozygotic co-twin design was applied in a sample of 224 twins (mean age = 17.70 years, SD = 6.28) controlling for confounders such as genes and shared environment. Generalized estimating equation models were fitted, using perinatal and postnatal indications of NSEs as exposure, operationalized both as separate risk factors and as cumulative risk loads. Categorical and dimensional operationalizations of autism spectrum disorder (ASD), attention-deficit/hyperactivity disorder (ADHD), intellectual disability and other NDCs were used as outcomes.ResultsBirth weight discordance was associated with dimensional autism and ADHD for the smaller twin, and medication during infancy was associated with dimensional autism. Among postnatal factors scarlet fever during early childhood was associated with lower IQ. Especially autism was associated with a greater cumulative perinatal or postnatal risk load.LimitationsWhen exploring the associations between each condition and specific NSEs the risk of being statistically underpowered increases. Hence, we limit the reported findings on specific indicators of NSEs to trait levels and present descriptive data for categorical NDCs.ConclusionsThe findings support previous research by indicating an association between exposure to perinatal and postnatal risks and subsequent NDCs within twin pairs and suggest that autism may be especially linked to accumulative early environmental risks. The findings are potentially important for developmental outcomes prognoses and may inform targeted prevention and early interventions.

Assessing Rasch measurement estimation methods across R packages with yes/no vocabulary test data

Instrument measurement conducted with Rasch analysis is a common process in language assessment research. A recent systematic review of 215 studies involving Rasch analysis in language testing and applied linguistics research reported that 23 different software packages had been utilized. However, none of the analyses were conducted with one of the numerous R-based Rasch analysis software packages, which generally employ one of the three estimation methods: conditional maximum likelihood estimation (CMLE), joint maximum likelihood estimation (JMLE), or marginal maximum likelihood estimation (MMLE). For this study, eRm, a CMLE-based R package, was utilized to conduct a dichotomous Rasch analysis of a Yes/No vocabulary test based on the academic word list. The resulting parameters and diagnostic statistics were compared with the equivalent results from four other R-based Rasch measurement software packages and Winsteps. Finally, all of the packages were utilized in the analysis of 1000 simulated datasets to investigate the extent to which results generated from the contrasting estimation methods converged or diverged. Overall, the differences between the results produced with the three estimation methods were negligible, and the discrepancies observed between datasets were attributable to the software choice as opposed to the estimation method.

Evaluation of Machine Learning Techniques to Predict the Likelihood of Mental Health Conditions Following a First mTBI.

ObjectiveLimited research has evaluated the utility of machine learning models and longitudinal data from electronic health records (EHR) to forecast mental health outcomes following a traumatic brain injury (TBI). The objective of this study is to assess various data science and machine learning techniques and determine their efficacy in forecasting mental health (MH) conditions among active duty Service Members (SMs) following a first diagnosis of mild traumatic brain injury (mTBI).Materials and MethodsPatient demographics and encounter metadata of 35,451 active duty SMs who have sustained an initial mTBI, as documented within the EHR, were obtained. All encounter records from a year prior and post index mTBI date were collected. Patient demographics, ICD-9-CM and ICD-10 codes, enhanced diagnostic related groups, and other risk factors estimated from the year prior to index mTBI were utilized to develop a feature vector representative of each patient. To embed temporal information into the feature vector, various window configurations were devised. Finally, the presence or absence of mental health conditions post mTBI index date were used as the outcomes variable for the models.ResultsWhen evaluating the machine learning models, neural network techniques showed the best overall performance in identifying patients with new or persistent mental health conditions post mTBI. Various window configurations were tested and results show that dividing the observation window into three distinct date windows [−365:−30, −30:0, 0:14] provided the best performance. Overall, the models described in this paper identified the likelihood of developing MH conditions at [14:90] days post-mTBI with an accuracy of 88.2%, an AUC of 0.82, and AUC-PR of 0.66.DiscussionThrough the development and evaluation of different machine learning models we have validated the feasibility of designing algorithms to forecast the likelihood of developing mental health conditions after the first mTBI. Patient attributes including demographics, symptomatology, and other known risk factors proved to be effective features to employ when training ML models for mTBI patients. When patient attributes and features are estimated at different time window, the overall performance increase illustrating the importance of embedding temporal information into the models. The addition of temporal information not only improved model performance, but also increased interpretability and clinical utility.ConclusionPredictive analytics can be a valuable tool for understanding the effects of mTBI, particularly when identifying those individuals at risk of negative outcomes. The translation of these models from retrospective study into real-world validation models is imperative in the mitigation of negative outcomes with appropriate and timely interventions.

Flexible binomial AR(1) processes using copulas

In order to accurately and flexibly capture the correlation structure between two random coefficients in the binomial AR(1) process, we propose a new class of models with copula. We derive some basic properties of the process. Then we discuss the conditional least squares (CLS) and conditional maximum likelihood (CML) estimators, as well as their asymptotic properties. We also investigate the finite-sample performance of the proposed method in simulation studies. Finally, a real data example is provided to illustrate the model.

Design and analysis of two-phase studies with multivariate longitudinal data.

Two-phase studies are crucial when outcome and covariate data are available in a first-phase sample (e.g., a cohort study), but costs associated with retrospective ascertainment of a novel exposure limit the size of the second-phase sample, in whom the exposure is collected. For longitudinal outcomes, one class of two-phase studies stratifies subjects based on an outcome vector summary (e.g., an average or a slope over time) and oversamples subjects in the extreme value strata while undersampling subjects in the medium-value stratum. Based on the choice of the summary, two-phase studies for longitudinal data can increase efficiency of time-varying and/or time-fixed exposure parameter estimates. In this manuscript, we extend efficient, two-phase study designs to multivariate longitudinal continuous outcomes, and we detail two analysis approaches. The first approach is a multiple imputation analysis that combines complete data from subjects selected for phase two with the incomplete data from those not selected. The second approach is a conditional maximum likelihood analysis that is intended for applications where only data from subjects selected for phase two are available. Importantly, we show that both approaches can be applied to secondary analyses of previously conducted two-phase studies. We examine finite sample operating characteristics of the two approaches and use the Lung Health Study (Connett etal. (1993), Controlled Clinical Trials, 14, 3S-19S) to examine genetic associations with lung function decline overtime.

The Role of Conditional Likelihoods in Latent Variable Modeling

In psychometrics, the canonical use of conditional likelihoods is for the Rasch model in measurement. Whilst not disputing the utility of conditional likelihoods in measurement, we examine a broader class of problems in psychometrics that can be addressed via conditional likelihoods. Specifically, we consider cluster-level endogeneity where the standard assumption that observed explanatory variables are independent from latent variables is violated. Here, “cluster” refers to the entity characterized by latent variables or random effects, such as individuals in measurement models or schools in multilevel models and “unit” refers to the elementary entity such as an item in measurement. Cluster-level endogeneity problems can arise in a number of settings, including unobserved confounding of causal effects, measurement error, retrospective sampling, informative cluster sizes, missing data, and heteroskedasticity. Severely inconsistent estimation can result if these challenges are ignored.

Associations between muscle-strengthening exercise and prevalent chronic health conditions in 16,301 adults: Do session duration and weekly volume matter?

ObjectivesMuscle-strengthening exercise (MSE) has multiple health benefits and is part of the global physical activity guidelines. However, with epidemiological research largely focussing on participation frequency (times/week), little is known about the health associations of other parameters. Hence, this study aimed to determine if MSE duration and volume are associated with prevalent chronic health conditions. DesignCross-sectional. MethodsCross-sectional data (n = 16,301 adults ≥16 years) were pooled from the Health Survey for England (2012, 2016). Respondents self-reported MSE mode (own-bodyweight, gym-based), duration and volume, and the prevalence of five chronic conditions (diabetes, anxiety/depression, heart, respiratory, or musculoskeletal condition). Poisson regressions with robust error variance were used to calculate the prevalence ratios (PR) of each chronic condition (outcome variable) across MSE parameters [exposure variables: duration (0 [reference]; 10–20; 21–59; ≥60 min/session); and volume (0 [reference]; low <mean; high ≥mean minutes/week)] for each mode and the modes combined. ResultsMost adults (81.5%) did no MSE. Undertaking any MSE regardless of mode, duration or volume was associated with a reduced likelihood of diabetes (APRs 0.25–0.39), heart (APRs 0.32–0.60), respiratory (APRs 0.49–0.67), and musculoskeletal conditions (APRs 0.43–0.63), and anxiety/depression (APRs 0.46–0.68). Associations remained after adjustment for potential socio-demographic and behavioural confounders. ConclusionsWhile participation in own-bodyweight or gym-based-strength MSE is low, irrespective of mode, duration or volume, MSE was associated with a lower prevalence of chronic health conditions. Studies with longitudinal study designs are needed to confirm these cross-sectional findings.

Financial Condition and Bankruptcy Likelihood in Aviation on the Example of the Aeroflot Company

Abstract This study analyses theoretical aspects of bankruptcy and financial analysis. Analysis of bankrupt cy diagnostics is the most important condition for successful company management since the results of economic activity depend on the availability and efficiency of the use of financial resources. The study of the institution of bankruptcy is essential for high-quality business conduct. Thus, as a practical part this study implemented analyses of financial condition and bankruptcy likelihood in aviation on the example of one of the biggest airlines – PJSC Aeroflot. Research resulted in findings confirming the instability of the company’s financial condition and downward trend on the Z index related to decrease in demand, mostly due to the pandemic of COVID-19.

It Could Be Worse...It Could Be Raining: Ambulance Response Time and Health Outcomes

Ambulance response time to emergency calls is a key indicator of a health system's efficiency although its impact on health is not precisely known. This causal relation is identified by exploiting rainfall at the time of the ambulance run as a shock to responsiveness. The elasticity of the likelihood of a severe cardiovascular condition with respect to response time is 0.9 and that of the likelihood of death before reaching the hospital is 5. Finally, the economic value of time is quantified, and it is shown that improving the ambulance's ability to locate the scene would substantially increase efficiency.

Racial inequities in emergency department wait times for pregnancy-related concerns.

Emergency department care is common among US pregnant women. Given the increased likelihood of serious and life-threatening pregnancy-related health conditions among Black mothers, timeliness of emergency department care is vital. The objective of this study was to evaluate racial/ethnic variations in emergency department wait times for receiving obstetrical care among a nationally representative population. The study used pooled 2016-2018 data from the National Hospital Ambulatory Medical Care Survey, a nationally representative sample of emergency department visits. Regression models were estimated to determine whether emergency department wait time was associated with the race/ethnicity of the perinatal patient. Adjusted models controlled for age, obesity status, insurance type, whether the patient arrived by ambulance, triage status, presence of a patient dashboard, and region. There were a total of 821 reported pregnancy-related visits in the National Hospital Ambulatory Medical Care Survey sample of emergency department visits. Of those 821 visits, 40.6% were among White women, 27.7% among Black women, and 27.5% among Hispanic women. Mean wait times differed substantially by race/ethnicity. After adjusting for potential confounders, Black women waited 46% longer than White women with emergency department visits for pregnancy problems (p < .05). Those reporting another race waited 95% longer for pregnancy problems in the emergency department than White women (p < .05). Findings from this study document significant racial/ethnic differences in wait times for perinatal emergency department care. Although inequities in wait times may emerge across the spectrum of care, documenting the factors influencing racial disparities in wait times are critical to promoting equitable perinatal health outcomes.

A Conditional One-Output Likelihood Formulation for Multitask Gaussian Processes

Multitask Gaussian processes (MTGP) are the Gaussian process (GP) framework's solution for multioutput regression problems in which the $T$ elements of the regressors cannot be considered conditionally independent given the observations. Standard MTGP models assume that there exist both a multitask covariance matrix as a function of an intertask matrix, and a noise covariance matrix. These matrices need to be approximated by a low rank simplification of order $P$ in order to reduce the number of parameters to be learnt from $T^2$ to $TP$. Here we introduce a novel approach that simplifies the multitask learning by reducing it to a set of conditioned univariate GPs without the need for any low rank approximations, therefore completely eliminating the requirement to select an adequate value for hyperparameter $P$. At the same time, by extending this approach with both a hierarchical and an approximate model, the proposed extensions are capable of recovering the multitask covariance and noise matrices after learning only $2T$ parameters, avoiding the validation of any model hyperparameter and reducing the overall complexity of the model as well as the risk of overfitting. Experimental results over synthetic and real problems confirm the advantages of this inference approach in its ability to accurately recover the original noise and signal matrices, as well as the achieved performance improvement in comparison to other state of art MTGP approaches. We have also integrated the model with standard GP toolboxes, showing that it is computationally competitive with state of the art options.

Meta-Analysis of Multi-Arm Trials Using Binomial Approach

Most meta-analysis has concentrated on combining of treatment effect measures based on comparisons of two treatments. Meta-analysis of multi-arm trials is a key component of submission to summarize evidence from all possible studies. In this paper, an exact binomial model is proposed by using logistic regression model to compare different treatment in multi-arm trials. Two approaches such as unconditional maximum likelihood and conditional maximum likelihood have been determined and compared for the logistic regression model. The proposed models are performed using the data from 27 randomized clinical trials (RCTs) which determine the efficacy of antiplatelet therapy in reduction venous thrombosis and pulmonary embolism.