Random Effects Coefficients Research Articles

Exponential Dispersion accelerated degradation modelling and reliability assessment considering initial value and processes heterogeneity

In the production and operation, inherent variability and uncertainty necessitate addressing unit-to-unit heterogeneity in initial performance values and degradation processes. This article presents a bi-stochastic exponential dispersion process (BS-ED) designed to account for heterogeneity in both initial performance values and degradation processes. First, based on the ED process, the time and acceleration covariates are introduced to form a nonlinear accelerated ED process, and a random effect coefficient associated with the accelerated stress is incorporated to consider the heterogeneity of the process. Meanwhile, through the modelling of degradation time-shift, a degradation model considering the stochastic initial value of the product performance is developed. To effectively conduct the statistic inference of the BS-ED process, an improved stochastic EM algorithm is proposed, and the information matrix and Ito calculus are combined to estimate the confidence intervals. Finally, the stability of the method is verified by simulation and analyzed by two real cases.

Research on Quantile Regression Method for Longitudinal Interval-Censored Data Based on Bayesian Double Penalty

The increasing prominence of the problem of censored data in various fields has made studying how to perform parameter estimation and variable selection in censored mixed-effects models one of the hotspots of current research. In this paper, considering the situation that the response variable is restricted by the bilateral limit, a double-penalty Bayesian Tobit quantile regression model was constructed to carry out parameter estimation and variable selection in the interval-censored mixed-effects model, and at the same time, the fixed-effects and random effects coefficients are compressed in Tobit’s mixed-effects model, so as to reduce the estimation error of the model at the same time as the variable selection of the model is carried out. The posterior distribution of each unknown parameter was derived using the conditional Laplace prior and the mixed truncated normal distribution of interval-censored data, and then the Gibbs sampling algorithm for unknown parameter estimation was constructed. Through Monte Carlo simulation, it was found that the new method is more advantageous than the classical method in terms of variable selection and parameter estimation accuracy in various situations, such as different model sparsity, different data censoring ratios and different random error distributions, and the model is able to realize automatic variable selection. Finally, the new method is used to analyze the correlation between the crime rate and various economic indicators in China.

#367 PROTECT and NefIgArd two-year proteinuria and eGFR outcomes in adults with IgA nephropathy: matching-adjusted indirect comparison

Abstract Background and Aims Immunoglobulin A (IgA) nephropathy is a rare kidney disorder characterized by deposition of IgA in the glomeruli causing progressive loss of kidney function and increased risk of kidney failure. In the absence of a head-to-head trial, this study used unanchored matching-adjusted indirect comparison (MAIC) of clinical trial data to compare two-year efficacy outcomes between Sparsentan in PROTECT and targeted-release formulation (TRF) budesonide plus real-world optimized and stable renin-angiotensin system inhibition (RASi) standard-of-care (SoC) in NefIgArd. Method We conducted an unanchored MAIC using individual patient level data from the PROTECT trial and aggregate data from the NefIgArd trial. Patients in the sparsentan arm of PROTECT were weighted to match key baseline characteristics of patients in the targeted-release formulation (TRF) budesonide + RASi SoC arm of NefIgArd based on publicly accessible, clinically pertinent baseline characteristics and prognostic factors using the method of moments. After weighting, percentage reduction of urine protein-creatinine ratio (UPCR) relative to baseline and two-year eGFR total slope (based on available data, chronic slope estimates are currently not available from NefIgArd) were estimated. A mixed model for repeated measures (MMRM) was used for UPCR relative percentage reduction and a random effect coefficient model for eGFR total slope. A two-tailed z-test with a pooled standard error was conducted for the indirect comparison. Results After assessing PROTECT and NefIgArd cross-trial characteristics on key outcome definitions, inclusion and exclusion criteria, and patient population, the two trials were considered sufficiently similar for unanchored MAIC. After weighting individual patient data from PROTECT, all matched baseline patient characteristics were well-balanced between arms of the two trials. Comparative results showed patients treated with sparsentan in PROTECT (−43.2% relative reduction in UPCR) exhibited a greater mean percentage reduction in proteinuria at two-years compared to TRF budesonide + RASi SoC (−30.7% relative reduction in UPCR), a relative percentage reduction of 18.1% (p = 0.03; Fig. 1A). For eGFR total slope, patients treated with sparsentan exhibited a slower decline in kidney function compared to TRF budesonide + RASi SoC, a difference of 0.54 ml/min/1.73 m2 per year; however, this difference was not statistically significant (p = 0.35; Fig. 1B). Conclusion Aligned to an earlier analysis of percentage reduction in proteinuria at 9-months (−37%, p < 0.0001 favoring sparsentan), our MAIC results show that sparsentan in PROTECT was associated with a greater relative percentage reduction in proteinuria at two-years compared to TRF budesonide plus real-world optimized and stable RASi SoC in NefIgArd. eGFR total slope for sparsentan in PROTECT was comparable to that reported for TRF budesonide plus real-world optimized and stable RASi SoC in NefIgArd. Results comparing chronic slope may provide a better indication of the long-term nephroprotective value of both therapies.

Don’t listen to mom: no maternal influence on consistent nest and latrine site choice by their offspring in meadow voles

Abstract Where does an animal build a nest? At a large scale, habitat preference can be informed by ‘natal habitat preference induction’, where an animal’s early environment impacts what habitat it finds suitable later in life. Other preferences may be present within a chosen habitat. We tracked the location angle of nests and latrines within the home cages of captive meadow voles, Microtus pennsylvanicus. Nests and latrines were separated from each other by an angle of approximately 180°, perhaps to reduce disease transmission. Meadow voles’ nest and latrine site choices were individually consistent across time. Only nest site choices were consistent between siblings, as assessed by a random effect coefficient, and these choices were repeatable. However, nest site choices at maturity were independent of their mother’s nest choice. We posit that the nest and latrine site choice is a socially learned preference developed through the consensus of siblings after weaning.

Reliability of the Preliminary OMERACT Juvenile Idiopathic Arthritis MRI Score (OMERACT JAMRIS-SIJ).

This study reports the reliability of the juvenile idiopathic arthritis magnetic resonance imaging scoring system (JAMRIS-SIJ). The study comprised of eight raters—two rheumatologists and six radiologists—and 30 coronal T1 and Short-Tau Inversion Recovery (STIR) MRI scans of patients with enthesitis-related juvenile spondylarthritis. The median age of patients was 15 years with a mean disease duration of 5 years and 22 (73.3%) of the sample were boys. The inter-rater agreement of scores for each of the JAMRIS-SIJ items was calculated using a two-way random effect, absolute agreement, and single rater intraclass correlation coefficient (ICC 2.1). The ICC was interpreted together with kurtosis, since the ICC is also affected by the distribution of scores in the sample. The eight-rater, single measure inter-rater ICC (and kurtosis) values for JAMRIS-SIJ inflammation and damage components were the following: bone marrow edema (BME), 0.76 (1.2); joint space inflammation, 0.60 (1.8); capsulitis, 0.58 (9.2); enthesitis, 0.20 (0.1); ankylosis, 0.89 (35); sclerosis, 0.53 (4.6); erosion, 0.50 (6.5); fat lesion, 0.40 (21); backfill, 0.38 (38). The inter-rater reliability for BME and ankylosis scores was good and met the a priori set ICC threshold, whereas for the other items it was variable and below the selected threshold. Future directives should focus on refinement of the scores, definitions, and methods of interpretation prior to validation of the JAMRIS-SIJ through the assessment of its measurement properties.

Modelling and analyzing spatial clusters of leptospirosis based on satellite-generated measurements of environmental factors in Thailand during 2013-2015

This study statistically identified the association of remotely sensed environmental factors, such as Land Surface Temperature (LST), Night Time Light (NTL), rainfall, the Normalised Difference Vegetation Index (NDVI) and elevation with the incidence of leptospirosis in Thailand based on the nationwide 7,495 confirmed cases reported during 2013-2015. This work also established prediction models based on empirical findings. Panel regression models with random-effect and fixed-effect specifications were used to investigate the association between the remotely sensed environmental factors and the leptospirosis incidence. The Local Indicators of Spatial Association (LISA) statistics were also applied to detect the spatial patterns of leptospirosis and similar results were found (the R2 values of the random-effect and fixed-effect models were 0.3686 and 0.3684, respectively). The outcome thus indicates that remotely sensed environmental factors possess statistically significant contribution in predicting this disease. The highest association in 3 years was observed in LST (random- effect coefficient = -9.787, P<0.001; fixed-effect coefficient = -10.340, P=0.005) followed by rainfall (random-effect coefficient = 1.353, P<0.001; fixed-effect coefficient = 1.347, P<0.001) and NTL density (random-effect coefficient = -0.569, P=0.004; fixed-effect coefficient = -0.564, P=0.001). All results obtained from the bivariate LISA statistics indicated the localised associations between remotely sensed environmental factors and the incidence of leptospirosis. Particularly, LISA's results showed that the border provinces in the northeast, the northern and the southern regions displayed clusters of high leptospirosis incidence. All obtained outcomes thus show that remotely sensed environmental factors can be applied to panel regression models for incidence prediction, and these indicators can also identify the spatial concentration of leptospirosis in Thailand.

PENGARUH PROFITABILITAS, RESIKO BISNIS, LIKUIDITAS DAN TANGIBILITY TERHADAP STRUKTUR MODAL

The purpose of this study is to analyze and examine the effect of profitability, business risk, liquidity and tangibility on the capital structure of manufacturing companies listed on the Indonesia Stock Exchange (IDX) in the period 2015-2017. Samples taken using purposive sampling method. Sampling of manufacturing companies that meet the criteria for use in this study are 66 companies. The test in this study consisted of descriptive statistical analysis, common effect model test, fixed effect model test, random effect model test, chow test, hausman test, F test, t test and coefficient of determination test. The results of the t test using Eviews version 10 show that profitability and liquidity have a significant effect on capital structure. Business risk and tangibility have no significant effect on capital structure. the results of the F test obtain results that are all independent variables simultaneously influencing the capital structure as the dependent variable.

Determining the dependence of marine pile driving sound levels on strike energy, pile penetration, and propagation effects using a linear mixed model based on damped cylindrical spreading

Acoustic recordings were made during the installation of four offshore wind turbines at the Block Island Wind Farm, Rhode Island, USA. The turbine foundations have four legs inclined inward in a pyramidal configuration. Four bottom mounted acoustic recorders measured received sound levels at distances of 541-9067 m during 24 pile driving events. Linear mixed models based on damped cylindrical spreading were used to analyze the data. The model's random effects coefficients represented useful information about variability in the acoustic propagation conditions. The received sound levels were dependent on the angle between pile and seabed, strike energy, and pile penetration (PP). Deeper PPs increased sound levels in a frequency dependent manner. The estimated area around the piles where auditory injury and disturbance to marine life could occur were not circular and changed by up to an order of magnitude between the lowest and highest sound level cases. The study extends earlier results showing a linear relationship between the peak sound pressure level and per-strike sound exposure level. Recommendations are made for how to collect and analyze pile driving data. The results will inform regulatory mitigations of the effects of pile driving sound on marine life, and contribute to developing improved pile driving source models.

%JM: A SAS Macro to Fit Jointly Generalized Mixed Models for Longitudinal Data and Time-to-Event Responses

In clinical research subjects are usually observed during a period of time. Primary and secondary endpoints are often either responses measured longitudinally over time or the time at which an event of interest occurs. Joint modeling is increasingly being used for multiple purposes such as to adjust the analysis of the longitudinal response for informative dropout mechanisms. In this paper we present %JM, a SAS macro that fits jointly generalized mixed models for longitudinal data and proportional hazards models for time-to-event responses. The macro fits normal, binary, binomial and Poisson longitudinal responses and allows choosing among a range of options to fit the trajectories of the longitudinal response over time: a linear function, splines, natural cubic splines and B-splines. For the time-to-event response, that might be right-censored, the macro fits parametric, stratified or not, proportional hazards models with the following baseline risk functions: exponential, Weibull, piecewise exponential and the generalizations of the Weibull and the Gompertz models based on splines. %JM offers several options to connect the longitudinal model and the time-to-event model: current-value-dependent and slope-dependent shared parameters, lagging effects, cumulative effects, random effects coefficients as shared parameters and interaction effects.

The ALFAM2 database on ammonia emission from field-applied manure: Description and illustrative analysis

Ammonia (NH3) emission from animal manure contributes to air pollution and ecosystem degradation, and the loss of reactive nitrogen (N) from agricultural systems. Estimates of NH3 emission are necessary for national inventories and nutrient management, and NH3 emission from field-applied manure has been measured in many studies over the past few decades. In this work, we facilitate the use of these data by collecting and organizing them in the ALFAM2 database. In this paper we describe the development of the database and summarise its contents, quantify effects of application methods and other variables on emission using a data subset, and discuss challenges for data analysis and model development. The database contains measurements of emission, manure and soil properties, weather, application technique, and other variables for 1895 plots from 22 research institutes in 12 countries. Data on five manure types (cattle, pig, mink, poultry, mixed, as well as sludge and “other”) applied to three types of crops (grass, small grains, maize, as well as stubble and bare soil) are included. Application methods represented in the database include broadcast, trailing hose, trailing shoe (narrow band application), and open slot injection. Cattle manure application to grassland was the most common combination, and analysis of this subset (with dry matter (DM) limited to <15%) was carried out using mixed- and fixed-effects models in order to quantify effects of management and environment on ammonia emission, and to highlight challenges for use of the database. Measured emission in this subset ranged from <1% to 130% of applied ammonia after 48 h. Results showed clear, albeit variable, reductions in NH3 emission due to trailing hose, trailing shoe, and open slot injection of slurry compared to broadcast application. There was evidence of positive effects of air temperature and wind speed on NH3 emission, and limited evidence of effects of slurry DM. However, random-effects coefficients for differences among research institutes were among the largest model coefficients, and showed a deviation from the mean response by more than 100% in some cases. The source of these institute differences could not be determined with certainty, but there is some evidence that they are related to differences in soils, or differences in application or measurement methods. The ALFAM2 database should be useful for development and evaluation of both emission factors and emission models, but users need to recognize the limitations caused by confounding variables, imbalance in the dataset, and dependence among observations from the same institute. Variation among measurements and in reported variables highlights the importance of international agreement on how NH3 emission should be measured, along with necessary types of supporting data and standard protocols for their measurement. Both are needed in order to produce more accurate and useful ammonia emission measurements. Expansion of the ALFAM2 database will continue, and readers are invited to contact the corresponding author for information on data submission. The latest version of the database is available at http://www.alfam.dk.

A Skew‐normal copula‐driven GLMM

This paper presents a method for fitting a copula‐driven generalized linear mixed models. For added flexibility, the skew‐normal copula is adopted for fitting. The correlation matrix of the skew‐normal copula is used to capture the dependence structure within units, while the fixed and random effects coefficients are estimated through the mean of the copula. For estimation, a Monte Carlo expectation–maximization algorithm is developed. Simulations are shown alongside a real data example from the Framingham Heart Study.

A Combined Cognitive Stimulation and Physical Exercise Programme (MINDVital) in Early Dementia: Differential Effects on Single- and Dual-Task Gait Performance

Background: Gait disorders are common in early dementia, with particularly pronounced dual-task deficits, contributing to the increased fall risk and mobility decline associated with cognitive impairment. Objective: This study examines the effects of a combined cognitive stimulation and physical exercise programme (MINDVital) on gait performance under single- and dual-task conditions in older adults with mild dementia. Methods: Thirty-nine patients with early dementia participated in a multi-disciplinary rehabilitation programme comprising both physical exercise and cognitive stimulation. The programme was conducted in 8-week cycles with participants attending once weekly, and all participants completed 2 successive cycles. Cognitive, functional performance and behavioural symptoms were assessed at baseline and at the end of each 8-week cycle. Gait speed was examined under both single- (Timed Up and Go and 6-metre walk tests) and dual-task (animal category and serial counting) conditions. A random effects model was performed for the independent effect of MINDVital on the primary outcome variable of gait speed under dual-task conditions. Results: The mean age of patients enroled in the rehabilitation programme was 79 ± 6.2 years; 25 (64.1%) had a diagnosis of Alzheimer's dementia, and 26 (66.7%) were receiving a cognitive enhancer therapy. There was a significant improvement in cognitive performance [random effects coefficient (standard error) = 0.90 (0.31), p = 0.003] and gait speed under both dual-task situations [animal category: random effects coefficient = 0.04 (0.02), p = 0.039; serial counting: random effects coefficient = 0.05 (0.02), p = 0.013], with reduced dual-task cost for gait speed [serial counting: random effects coefficient = -4.05 (2.35), p = 0.086] following successive MINDVital cycles. No significant improvement in single-task gait speed was observed. Improved cognitive performance over time was a significant determinant of changes in dual-task gait speed [random effects coefficients = 0.01 (0.005), p = 0.048, and 0.02 (0.005), p = 0.003 for category fluency and counting backwards, respectively]. Conclusion: A combined physical and cognitive rehabilitation programme leads to significant improvements in dual-task walking in early dementia, which may be contributed by improvement in cognitive performance, as single-task gait performance remained stable.

Individual-tree diameter growth models for black spruce and jack pine plantations in northern Ontario

Individual-tree distance independent diameter growth models were developed for black spruce and jack pine plantations. Data used in this study came via stem analysis on 1170 black spruce ( Picea mariana [Mill.] B.S.P.) and 800 jack pine ( Pinus banksiana Lamb.) trees sampled from 75 stands of 25 even-aged monospecific plantations for each species in the Canadian boreal forest region of northern Ontario. Of the 75 stands, 50 were randomly selected for each species and all trees from these stands were used for model development. Trees from the remaining stands were used for model evaluation. A nonlinear mixed-effects approach was applied in fitting the diameter growth models. The predictive accuracy of the models was improved by including random effects coefficients. Four selection criteria – random, dominant or codominant, tree size close to quadratic mean diameter, and small sized – were evaluated for accuracy in predicting random effects for a new stand using the developed models. Random effects predicted based on trees selected using the random selection criterion provided more accurate diameter predictions than those using trees obtained via other selection criteria for both species. The models developed here are very important to forest managers as the diameters predicted by these models or, their stand-level summaries (i.e., basal area, average diameter), are used as inputs in any forest growth and yield models. In addition, individual-tree diameter growth models can be used to directly forecast changes in diameter distribution of stands.

Functional Somatic Symptoms and Psychological States: An Electronic Diary Study

To investigate the links between functional physical symptoms and psychological states in a sample of patients with persistent medically unexplained symptoms. Despite the epidemiological evidence for links between physical symptoms and mental processes, prior diary studies have shown inconsistent associations and generally been limited to single symptom and psychological variable pairs. Twenty-six patients with at least three functional physical symptoms completed twice daily self-report measures of symptoms, fatigue, anxiety, stress, mood, and symptom concern using electronic diaries over 12 weeks. Associations between physical symptoms and psychological variables were measured by linear mixed effects models at the levels of diary entry and individual. Despite high baseline questionnaire scores for depression and anxiety, diary ratings of anxiety and stress were relatively low. Fixed effects regression coefficients varied between symptoms and psychological variables; for instance, the fixed effects regression coefficient (95% Confidence Intervals) for fatigue as the outcome variable was 0.39 (0.31-0.47) with low mood and 0.05 (-0.01-0.10) with stress as the predictor. Random effects coefficients showed less variation between individuals for fatigue and musculoskeletal pain than for other symptoms. Self-reported mood and symptom concern were more strongly associated with functional physical symptoms than anxiety or stress. We suggest that one reason patients with functional somatic symptoms reject psychosomatic explanations is because they do not experience sufficient correlation between symptoms and psychological states.

Consistent Estimation of Censored Demand Systems Using Panel Data

AbstractWe derive a joint continuous/censored commodity demand system for panel data applications. Unobserved heterogeneity is controlled for using a correlated random effects specification and a generalized method of moments framework used to estimate the model. While relatively small differences in elasticity estimates are found between a flexible random effects specification and one that restricts the random effect coefficient to be time invariant, larger differences are observed when comparing the flexible model to a pooled cross‐sectional estimator. The results suggest the limited ability of such estimators to control for preference heterogeneity and unit‐value endogeneity leads to parameter bias.

A generalized linear mixed model analysis of a multi-vessel fishery resource survey

A generalized linear mixed model (GLMM) that treats year and spatial cell as fixed effects while treating vessel as a random effect is used to examine fishing power among chartered industry-based vessels and a research trawler, the FRV Miller Freeman, for bottom trawl surveys on the upper continental slope of U.S. West coast. A Bernoulli distribution is used to model the probability of a non-zero haul and the gamma distribution to model the non-zero catch rates of four groundfish species. The use of vessel as a random effect allows the data for the various vessels to be combined and a single continuous time-series of biomass indices to be developed for stock assessment purposes. The GLMMs fit the data reasonably well. Among the different models examined, the GLMM incorporating a random vessel × year effect had the smallest ΔAIC and was thus chosen as the best model. Also, estimated random effects coefficients associated with the industry-based vessels and the FRV Miller Freeman for each year suggests that these vessels can be assumed to be from a common random effects distribution. These results suggest that combining data from the chartered industry-based vessels and from the research trawler may be appropriate to develop indices of abundance for stock assessment purposes. Finally, an evaluation of variances associated with abundance indices from the different models indicate that analyzing these data as a fixed effect GLM may underestimate the level of variability due to ignoring the grouped nature of tows within vessels. As such, use of a mixed model approach with vessel as a random effect is a reasonable approach to developing abundance indices and their variances.

Maximum likelihood estimation of limited and discrete dependent variable models with nested random effects

Abstract Gauss–Hermite quadrature is often used to evaluate and maximize the likelihood for random component probit models. Unfortunately, the estimates are biased for large cluster sizes and/or intraclass correlations. We show that adaptive quadrature largely overcomes these problems. We then extend the adaptive quadrature approach to general random coefficient models with limited and discrete dependent variables. The models can include several nested random effects (intercepts and coefficients) representing unobserved heterogeneity at different levels of a hierarchical dataset. The required multivariate integrals are evaluated efficiently using spherical quadrature rules. Simulations show that adaptive quadrature performs well in a wide range of situations.

Mathematics and the Gender Gap: A Met-Analysis of Recent Studies on Sex Differences in Mathematical Tasks

This paper is a meta-analysis of studies that have taken place between 1974 and mid-1987 on sex differences in mathematical tasks. The methods used are estimations of (a) parameters for a random effects model and (b) coefficients for a linear regression equation, all based on effect sizes calculated from each study. These results are compared with meta-analyses of the studies on quantitative skill collected by Maccoby and Jacklin. These comparisons, together with ad hoc comparisons of Scholastic Aptitude Test effect sizes over the years, yield two conclusions. First, the average sex difference is very small; a confidence interval for it covers zero, though the interval lies mainly on the side of male advantage. Second, sex differences in performance are decreasing over the years.