Full Maximum Likelihood Research Articles

Efficiency gains in value-at-risk and expected shortfall estimation by using copulas and full maximum likelihood

We provide Monte Carlo evidence on the efficiency gains obtained in GARCH-based estimations of value-at-risk (VaR) and expected shortfall (ES) by incorporating dependence information through copulas and subsequently using full maximum likelihood (FML) estimates. First, we consider an individual returns series; in this case, the efficiency gain stems from exploiting the relationship with another returns series using a copula model. Second, we consider a portfolio returns series obtained as a linear combination of returns series related through a copula model; in this case, the efficiency gain stems from using FML estimates instead of two-stage ML estimates. We consider three copulas models in order to analyze the effect of the type and degree of tail dependence on the results. Our results show that, in these situations, using copula models and FML leads to a substantial reduction in the mean squared error of the VaR and ES estimates when there is a relatively high degree of dependence between returns (up to 70% in the presence of lower-tail dependence) and a notable improvement in the performance of backtesting procedures.

A REML method for the evidence-splitting model in network meta-analysis.

Checking for possible inconsistency between direct and indirect evidence is an important task in network meta-analysis. Recently, an evidence-splitting (ES) model has been proposed, that allows separating direct and indirect evidence in a network and hence assessing inconsistency. A salient feature of this model is that the variance for heterogeneity appears in both the mean and the variance structure. Thus, full maximum likelihood (ML) has been proposed for estimating the parameters of this model. Maximum likelihood is known to yield biased variance component estimates in linear mixed models, and this problem is expected to also affect the ES model. The purpose of the present paper, therefore, is to propose a method based on residual (or restricted) maximum likelihood (REML). Our simulation shows that this new method is quite competitive to methods based on full ML in terms of bias and mean squared error. In addition, some limitations of the ES model are discussed. While this model splits direct and indirect evidence, it is not a plausible model for the cause of inconsistency.

A comparison of likelihood-based methods for size-biased sampling

Three likelihood approaches to estimation under informative sampling are compared using a special case for which analytic expressions are possible to derive. An independent and identically distributed population of values of a variable of interest is drawn from a gamma distribution, with the shape parameter and the population size both assumed to be known. The sampling method is selection with probability proportional to a power of the variable with replacement, so that duplicate sample units are possible. Estimators of the unknown parameter, variance estimators and asymptotic variances of the estimators are derived for maximum likelihood, sample likelihood and pseudo-likelihood estimation. Theoretical derivations and simulation results show that the efficiency of the sample likelihood approaches that of full maximum likelihood estimation when the sample size n tends to infinity and the sampling fraction f tends to zero. However, when n tends to infinity and f is not negligible, the maximum likelihood estimator is more efficient than the other methods because it takes the possibility of duplicate sample units into account. Pseudo-likelihood can perform much more poorly than the other methods in some cases. For the special case when the superpopulation is exponential and the selection is probability proportional to size, the anticipated variance of the pseudo-likelihood estimate is infinite.

Luteodorsum huanglongense (Gomphaceae, Gomphales), a New Genus and Species of Gomphoid Fungus from the Loess Plateau, Northwest China.

During an investigation of the macrofungal flora in the Huanglong Mountains of the Loess Plateau, northwest China, a unique gomphoid fungus was discovered and collected. After morphological identification and molecular phylogenetic analyses, a new genus named Luteodorsum and its type species, L. huanglongense, were proposed. Phylogenetic analyses were conducted using datasets of nuclear ribosomal DNA 28S large subunit (LSU), mitochondrial (mt) adenosine triphosphatase (ATPase) subunit 6 (atp6), and mt small-subunit rDNA (mtSSU). The results confirmed that L. huanglongense forms an independent clade within Gomphales, with full maximum likelihood bootstrap support (MLBS), maximum parsimony bootstrap support (MPBS), and Bayesian posterior probability (BPP). L. huanglongense is characterized by its sandy-brown, orange-brown, or coffee-brown color; clavate to infundibuliform shape; wrinkled and ridged hymenophore; ellipsoid to obovoid warted basidiospores; cylindrical to clavate flexuous pleurocystidia; and crystal basal mycelium. Overall, this study contributes to the growing body of knowledge on the diversity and evolution of Gomphales and provides valuable insights into the unique fungal flora found in the Huanglong Mountains.

Does Facebook intensity matter for academic self-efficacy? A path analytic approach

There is mixed evidence about the educational impacts of Facebook with some research indicating how using Facebook facilitates academic outcomes while other investigations showing the link of Facebook usage to maladaptive educational outcomes such as reduced academic self-efficacy and performance. Prior studies also paid much attention to the academic-related consequences of this social networking in Western societies such as the United States which might have limited generalizability to students from non-Western countries. This study contributes to this line evidence by exploring whether Facebook use intensity dimensions would predict academic self-efficacy and study habits in selected Filipino undergraduate students using a path analytic approach. A survey packet comprising questionnaires about Facebook use and academic self-efficacy was administered to 566 Filipino undergraduate students. Results of path analysis via full maximum likelihood estimation approach demonstrated that whereas self-expression positively predicted academic self-efficacy, overuse negatively predicted this outcome. Boredom positively predicted study habits. This research has implications for understanding how different motives of using social media platforms can influence academic behaviors in higher education contexts.

COVID-19 Pandemic Associations on Mental and Physical Health in African Americans Participating in a Behavioral Intervention.

The COVID-19 pandemic has had disproportionate effects on communities of color, with higher death rates among African Americans (AA). The purpose of this study was to assess associations in African Americans' mental and physical health with the COVID-19 pandemic. Data for this study came from a larger nutrition intervention of AAs in the Southeastern United States, the Nutritious Eating with Soul study. Data collected before and after March 15, 2020 (the day when local South Carolina schools and businesses closed), were analyzed to assess the association of the pandemic on participants' stress, control of healthy eating, physical activity, and body mass index. Repeated measures analysis of covariance using full maximum likelihood estimation to handle missing data was used. At the onset of the COVID-19 pandemic, 150 participants were enrolled in the study (48.2 ± 10.6years old, 79% female, 75% with college degree or higher). Participants' reporting of stress did not show statistically significant change over time. Cognitive control increased 1.43 points (F = 20.60, p < 0.0001) and body mass index increased 0.72kg/m2 (F = 10.68, p = 0.001). Future longitudinal studies should investigate how the COVID-19 pandemic continues to present challenges to understanding and improving health among African Americans. The study is registered at www.clinicaltrials.gov NCT03354377.

Constructing a Multilevel Modeling to High-Resolution CT (HRCT) Lung in Patients with COVID-19 Infection

The coronavirus disease, also called COVID-19 is caused by the SARS-CoV-2 virus. Most the people contaminated with the virus will experience mild to moderate symptoms of respiratory diseases. The aim of this paper is constructing a model by multilevel modeling for these patients who sufferers by coronaviruses, we got seven hospitals which totals (636) patients in private and public that 27% from Erbil, 26% from Sulaimani, 23% from Duhok and 24% from Halabja from the period (September 1th, 2019 to February 1th, 2022). In these modelling of multilevel restricted maximum likelihood estimation (RMLE) and full maximum likelihood (FML) acclimate estimate the parameters of multilevel models (fixed and random). The application was on the HRCT lungs of patients, seven hospitals were selected randomly among the county in Kurdistan region of Iraq. The result shows that all three variables are significant at the hospital level, but in the two final models add level-2 predictor (Doctor Experience) that interaction with level-1 predictor (smoker), which is far from significant. However, there is a significant relationship between being a diabetic and having a CT scan, but the relationship between smoking and having a CT scan is not significant.

Application of Poisson's Hierarchical Regression Model to the Deaths of Covid-19 in Mosul City Hospitals

This research deals with the study of the partial hierarchical Poisson regression model (with a random intercept), where this model is one of the most important models widely applied in analyzing data that is characterized by the fact that the observations take a hierarchical form. Where it the full maximum likelihood (FML) method is used to estimate the model parameters. The model was applied to the covid-9 deaths in Mosul city, were recorded during the period (1/1/202 - 1/9/2021), where four major hospitals in the city were selected to represent the group of second level of data (Ibn Sina Hospital, Al Salam Hospital, Shifa Hospital, General Mosul Hospital). *طالب دبلوم عالی/ قسم الاحصاء والمعلوماتیة/ کلیة علوم الحاسوب والریاضیات/ جامعة الموصل. **استاذ مساعد/ قسم الاحصاء والمعلوماتیة/ کلیة علوم الحاسوب والریاضیات/ جامعة الموصل. تاریخ استلام البحث: 4/3/2022 تاریخ القبول: 9/4/2022 تاریخ النشر: 1/12/2022 The research found the adequate of the model for this type of data, as it was found that there are some factors that contribute to the increase in the number of deaths in the epidemic, such as the advanced age of the patient, the length of stay in the hospital, the percentage of oxygen in the patient's blood, in addition to the incidence of some chronic diseases such as asthma. The study recommended a more in-depth study of other types of these models, and the use of other estimation methods, in addition to paying attention to the methods of data recording by the city health department.

P61. Digital rehabilitation for acute low back pain: a prospective longitudinal cohort study

<h3>BACKGROUND CONTEXT</h3> Low back pain (LBP) has a lifetime prevalence of 70-80%. Access to timely and personalized, evidence-based care is key to prevent chronification [1-3]. Digital solutions may increase accessibility to treatment, while reducing healthcare-related costs [4, 5]. <h3>PURPOSE</h3> To assess the outcomes and engagement of a fully remote multimodal digital care program (DCP) on a real-world cohort of patients with acute LBP stratified by pain level at baseline. <h3>STUDY DESIGN/SETTING</h3> Interventional, single-arm, cohort study of individuals with acute LBP who received a home-based DCP. This study is part of a trial that was prospectively approved by the New England Institutional Review Board (number 120190313) and registered on ClinicalTrials.gov (NCT04092946). <h3>PATIENT SAMPLE</h3> A total of 406 patients at program start, 332 (81.8%) completed the intervention. <h3>OUTCOME MEASURES</h3> Primary outcome was the mean change in disability (Oswestry Disability Index - ODI) until the end of the program. Secondary outcomes included change in pain (NPRS), analgesic consumption, surgery likelihood, depression (PHQ-9), anxiety (GAD-7), fear-avoidance beliefs (FABQ-PA), work productivity (WPAI) and engagement. <h3>METHODS</h3> This DCP integrates an FDA-listed class II medical device comprised of two inertial motion trackers, a mobile app on a dedicated tablet, and a cloud-based portal which interfaces between the patient and an assigned physical therapist, who monitors the patient and performs the necessary adjustments during intervention. The DCP combines exercise and education, including major components of cognitive behavioral therapy. Outcomes changes were modeled using Latent growth curve analysis with full maximum likelihood estimation for missing data. Three risk subgroups were created based on pain levels at baseline, according to the pain thresholds proposed by Miró et al.,[6]: (i) mild (<3), (ii) moderate (4-6) and (iii) severe (7). <h3>RESULTS</h3> A significant disability reduction of 55.1% (14.93, 95%CI 13.95; 15.91) was observed, corresponding to an 76.1% responder rate (30% cut-off). Disability reduction strongly correlated with improvements in pain (61.0%), depression (55.4%) and productivity (65.6%). Surgery likelihood (59.1%), fear-avoidance beliefs (46.3%), anxiety (59.5%), and analgesic consumption (from 35.7% at baseline to 10.8% at program end) were similarly reduced. Patient satisfaction score was 8.7/10.0 (SD 1.4). Significant improvements in all LBP risk subgroups were seen after the DCP, with higher reductions in pain, ODI, analgesics intake, and productivity impairment in the high-risk subgroup, suggesting that higher risk individuals are not less likely to respond this treatment, as has been reported in other studies [7]. <h3>CONCLUSIONS</h3> This study demonstrated the utility of a multimodal DCP for patients with acute LBP. Very high adherence rates and patient satisfaction were observed, alongside clinically significant reductions in all assessed outcomes, consistent with the growing body of evidence supporting the management of acute LBP with DCPs[7]. 1. Lancet 1999;354:581-5. 2. Best Pract Res Clin Rheumatol 2010;24:769-81. 3. Bull World Health Organ 2003;81:646-56. 4. J Med Internet Res 2017;19:e179. 5. J Med Internet Res 2016;18:e139. 6. Disabil Rehabil 2017;39:1131-1135. 7. Am J Phys Med Rehabil 2019;98:850-858. <h3>FDA DEVICE/DRUG STATUS</h3> This abstract does not discuss or include any applicable devices or drugs.

Spanish Adaptation of Meaning-Centered Psychotherapy for Participants With Cancer: Study Protocol of a Randomized Control Trial.

BackgroundMeaning-Centered Psychotherapy (MCP) is effective in improving meaning in life, hope, optimism, self-efficacy, well-being, and quality of life, and in reducing stress in people with cancer. However, all the studies on the application of MCP in cancer patients have been carried out in Anglo-Saxon samples. Therefore, it is necessary to adapt and verify the efficacy of MCP in populations that speak languages other than English, such as Spanish. Moreover, to expand the data supporting the efficacy of MCP for cancer patients, it would be necessary to compare MCP to other active therapies such as Cognitive Behavioral Therapy (CBT).MethodsThe aims of the proposed study are: the first objective is to verify the efficacy of the MCP intervention for Spanish participants with cancer in a randomized control trial (RCT) comparing it to CBT. The second objective is to analyze the feasibility and acceptance of MCP in Spanish participants with cancer. The third objective is to analyze whether the changes produced in the meaning in life dimensions (presence, search, comprehension, purpose, and mattering) will predict changes in anxiety, depression, quality of life, etc. Our research team adapted MCP for Spanish participants with cancer. This paper presents the study protocol. The study design consists of a two-arm RCT with two conditions: MCP and CBT, where participants will be randomized to one of the two groups. Eligible participants will be adults with stage I, II, and III cancer who were treated with curative intent and had completed their main medical treatment (surgery, radiotherapy, or chemotherapy). Participants will be assessed at pretreatment, post-treatment, and 6-month follow-up. The intention-to-treat principle will be used when analyzing data, using mixed-effects models with full information and maximum likelihood estimation.DiscussionThis study will provide results that confirm the efficacy of the MCP in Spanish participants with cancer.Trial RegistrationClinicalTrials.gov; https://register.clinicaltrials.gov/prs/app/template/Home.vm?uid=U0005WS9&ts=4&sid=S000BOTT&cx=bvr2ue, identifier NCT05197348

Hybrid maximum likelihood inference for stochastic block models

Stochastic block models have known a flowering interest in the social network literature. They provide a tool for discovering communities and identifying clusters of individuals characterized by similar social behaviors. In this framework, full maximum likelihood estimates are not achievable due to the intractability of the likelihood function. For this reason, several approximate solutions are available in the literature. In this respect, a new and more efficient approximate method for estimating model parameters is introduced. This has a hybrid nature, in the sense that it exploits different features of existing methods. The proposal is illustrated by an intensive Monte Carlo simulation study and an application to a real-world network.

Champions during Crises Scenarios: High Growth and Persistent High Growth Firms

Our paper aims to participate to the growing policy discussion on high-growth firms (HGFs) by analyzing persistence of high growth patterns over crisis. During downturn periods, such as post pandemic one, policy makers seek sources to maintain competitiveness and accelerate growth. Being dynamic players in economic growth and job creation, persistent high-growth firms are notable candidates for assuming that role under such circumstances. Therefore, in this study we explore the determinants and characteristics of HGFs and persistent high-growth firms (PHGF) in a crisis scenario.We use a sample of 190,247 firms from 2007 to 2014. We estimate a multinomial probit model with independent idiosyncratic components across the different categories (i.e. HGFs, PHGFs and other firms) using full maximum likelihood. In a second phase we explore which characteristics of HGFs affect the probability of being a PHGFs.HGFs are characterized by higher productivity and leverage, and PHGFs systematically differ from other HGFs only in what regards degree of international involvement. HGFs probability of maintaining high growth rates is very low.HGFs are essentially one-hit wonders and it is debatable whether policymakers can enhance economic results by targeting them. Policy makers should be directed towards those firms which have in principal the potential to be winners, but only through policy intervention these aided firms can realize their great potential (i.e. pick and build winner).

Inducing a desired value of correlation between two point-scale variables: a two-step procedure using copulas

Focusing on point-scale random variables, i.e. variables whose support consists of the first m positive integers, we discuss how to build a joint distribution with pre-specified marginal distributions and Pearson’s correlation rho . After recalling how the desired value rho is not free to vary between -1 and +1, but generally ranges a narrower interval, whose bounds depend on the two marginal distributions, we devise a procedure that first identifies a class of joint distributions, based on a parametric family of copulas, having the desired margins, and then adjusts the copula parameter in order to match the desired correlation. The proposed methodology addresses a need which often arises when assessing the performance and robustness of some new statistical technique, i.e. trying to build a huge number of replicates of a given dataset, which satisfy—on average—some of its features (for example, the empirical marginal distributions and the pairwise linear correlations). The proposal shows several advantages, such as—among others—allowing for dependence structures other than the Gaussian and being able to accommodate the copula parameter up to an assigned level of precision for rho with a very small computational cost. Based on this procedure, we also suggest a two-step estimation technique for copula-based bivariate discrete distributions, which can be used as an alternative to full and two-step maximum likelihood estimation. Numerical illustration and empirical evidence are provided through some examples and a Monte Carlo simulation study, involving the CUB distribution and three different copulas; an application to real data is also discussed.

The size\u2013growth relationship in the social services sector in Austria

The social services sector is among the fastest-growing industries, but it has gained little attention in the debate regarding firm growth. This article analyzes firm growth in relation to firm size using payroll expenses as our indicator for both firm growth and firm size. We apply structural equation modeling and full maximum likelihood estimation using Austrian data comprising all non-profit social service providers. After 2013, fewer firms have been entering and more have been exiting the sector; however, we find that growing in size is still not associated with higher growth rates. Our study emphasizes the role of small organizations in remaining a growth sector.

Learning under ambiguity: An experiment in gradual information processing

This experiment studies belief updating under ambiguity, using subjects' bid and ask prices for an asset with ambiguous payoff distribution. Bid and ask quotes allow for distinguishing between the two main paradigms of updating under ambiguity–full Bayesian updating and maximum likelihood updating. We find substantial heterogeneity in subjects' reaction to information. The majority of subjects (54%) chose quotes that were in line with full Bayesian updating, while another, non-negligible, group (35%) behaved like maximum likelihood updaters.

On the classical estimation of bivariate copula-based Seemingly unrelated tobit models through the proposed inference function for augmented margins method

This paper extends the analysis of the bivariate Seemingly Unrelated (SUR) Tobit by modeling its nonlinear dependence structure through copula and assuming non-normal marginal error distributions. For model estimation, the use of copula methods enables the use of the (classical) Inference Function for Margins (IFM) method by Joe and Xu (1996), which is more computationally attractive (feasible) than the full maximum likelihood approach. However, our simulation study shows that the IFM method provides a biased estimate of the copula parameter in the presence of censored observations in both margins. In order to obtain an unbiased estimate of the copula association parameter, we propose/develop a modified version of the IFM method, which we refer to as Inference Function for Augmented Margins (IFAM). Since the usual asymptotic approach, that is the computation of the asymptotic covariance matrix of the parameter estimates, is troublesome, we propose the use of resampling procedures (bootstrap methods) to obtain confidence intervals for the copula-based SUR Tobit model parameters. The satisfactory results from the simulation and empirical studies indicate the adequate performance of our proposed model and methods. We illustrate our procedure using bivariate data on consumption of salad dressings and lettuce by U.S. individuals.

LINEAR, GENERALIZED, HIERARCHICAL, BAYESIAN AND RANDOM REGRESSION MIXED MODELS IN GENETICS/GENOMICS IN PLANT BREEDING

This paper presents the state of the art of the statistical modelling as applied to plant breeding. Classes of inference, statistical models, estimation methods and model selection are emphasized in a practical way. Restricted Maximum Likelihood (REML), Hierarchical Maximum Likelihood (HIML) and Bayesian (BAYES) are highlighted. Distributions of data and effects, and dimension and structure of the models are considered for model selection and parameters estimation. Theory and practical examples referring to selection between models with different fixed effects factors are given using the Full Maximum Likelihood (FML). An analytical FML way of defining random or fixed effects is presented to avoid the subjective or conceptual usual definitions. Examples of the applications of the Hierarchical Maximum Likelihood/Hierarchical Generalized Best Linear Unbiased Prediction (HIML/HG-BLUP) procedure are also presented. Sample sizes for achieving high experimental quality and accuracy are indicated and simple interpretation of the estimates of key genetic parameters are given. Phenomics and genomics are approached. Maximum accuracy under the truest model is the key for achieving efficacy in plant breeding programs.

Empirical and conditional likelihoods for two‐phase studies

AbstractTwo‐phase, response‐dependent sampling is often used in regression settings that involve expensive covariate measurements. Conditional maximum likelihood (CML) is an attractive approach in many cases as it avoids modelling of the covariate distribution, unlike full maximum likelihood. Scott &amp; Wild (2011) introduced an augmented CML approach which is semi‐parametric efficient in certain settings with a discrete response variable. We consider general regression models and show the Scott–Wild estimator of covariate effects has the same asymptotic efficiency as two empirical likelihood estimators, and that these estimators dominate the CML estimator. We compare the efficiencies of various estimators in simulation studies and illustrate the methodology in a two‐phase genetics study.

CR‐QRM‐MLD for SD‐SM Hybrid MIMO systems

AbstractRecently, multiple‐input multiple‐output (MIMO) is studied actively such as a key technology for wireless communications. Space division (SD) multiplexing and spatial modulation (SM) have been proposed as the transmission technique of MIMO systems. In the full maximum likelihood detection (MLD), the QR decomposition with M‐algorithm MLD (QRM‐MLD), and the channel ranking QRM‐MLD (CR‐QRM‐MLD) for the SD‐MIMO, there are the trade‐off between the system performance and the computational complexity. Also, in the SM‐MIMO, the transmission rate is deteriorated due to a small number of transmitted signals. To solve these problems, in this article, we propose the CR‐QRM‐MLD for SD‐SM Hybrid MIMO (SD‐SM‐MIMO) systems. From the computer simulation results, the proposed method shows the reduction of the computational complexity and the good bit error rate performance.

Estimation of a dynamic stochastic frontier model using likelihood‐based approaches

SummaryThis paper considers a panel stochastic production frontier model that allows the dynamic adjustment of technical inefficiency. In particular, we assume that inefficiency follows an AR(1) process. That is, the current year's inefficiency for a firm depends on its past inefficiency plus a transient inefficiency incurred in the current year. Interfirm variations in the transient inefficiency are explained by some firm‐specific covariates. We consider four likelihood‐based approaches to estimate the model: the full maximum likelihood, pairwise composite likelihood, marginal composite likelihood, and quasi‐maximum likelihood approaches. Moreover, we provide Monte Carlo simulation results to examine and compare the finite‐sample performances of the four above‐mentioned likelihood‐based estimators of the parameters. Finally, we provide an empirical application of a panel of 73 Finnish electricity distribution companies observed during 2008–2014 to illustrate the working of our proposed models.