Indirect estimation of poverty indicators at poviat level

The availability of detailed and precise data on poverty at a low level of spatial aggregation is important when pursuing an effective cohesion policy. In Poland, this type of information is gathered during household surveys conducted by Statistics Poland and is made available at country, region, and selected socio-economic group level. Direct estimates relating to domains not included in a survey are burdened with a serious estimation error. In a situation of a limited (or in extreme cases zero) sample size, an estimation becomes possible through the application of small area estimation methods – indirect estimation. These techniques use variables which are strongly correlated with the researched phenomenon and which come from a census or from an administrative register. The aim of the study discussed in the article is to estimate two indicators: the rate of poverty and the depth of poverty at a poviat level, with the application of the Empirical Bayes (EB) method. The first indicator provides information on the scale of the phenomenon and the other one on its intensity, and so they constitute complementary measures of poverty. The study used data from the European Union Statistics on Income and Living Conditions of 2011 and the National Census of Population and Housing 2011. Information about the scale and intensity of poverty at the poviat level was obtained through the adaptation of the EB method based on the linear mixed model and Monte Carlo simulations. The indicators estimated this way allow for an assessment of the diversity of poverty at a local level. In addition, they are more precise and consistent with administrative registers in comparison to direct estimation results.

Download Full-text

Abstract P121: Post-resuscitation Ionized Hypocalcemia Revisited

Circulation ◽

10.1161/circ.118.suppl_18.s_1471-d ◽

2008 ◽

Vol 118 (suppl_18) ◽

Author(s):

Ted Heyming ◽

Scott Youngquist ◽

John P Rosborough ◽

James T Niemann

Keyword(s):

Cardiac Arrest ◽

Mixed Model ◽

Linear Mixed Model ◽

Base Excess ◽

Strong Association ◽

Balloon Occlusion ◽

Strongly Correlated ◽

Arterial Lactate ◽

Unit Increase ◽

Exogenous Calcium

Objective : Hypocalcemia during cardiac arrest has been reported. However, hypotheses for the decrease in ionized calcium (iCa) vary and its importance unknown. The objective of this study was to assess the relationships of iCa, pH, and base excess (BE) in two porcine cardiac arrest models, and to determine the effect of exogenous calcium on postresuscitation hemodynamics. Methods : Swine were instrumented and VF was induced either electrically (EVF, n=49) or spontaneously, ischemically induced (IVF) with balloon occlusion of the LAD (n=37). Animals were resuscitated after 7 minutes of VF. BE, iCa, and pH, were determined prearrest and at 15, 30, 60 min after ROSC. Arterial lactate was also measured in 10 pigs. In three animals, 1 gm of CaCl 2 was infused over 20 min after ROSC. Results: iCa, BE, and pH declined significantly over the 60 min following ROSC, regardless of VF type (figure ). Lactate was strongly correlated with BE (r = −0.83, p<0.0001). In a multivariate generalized linear mixed model, iCa was 0.007 mg/dL higher for every one unit increase in BE (95% CI 0.005– 0.008, p<0.0001), while controlling for type of induced VF. CaCl 2 improved post-ROSC hemodynamics when compared to saline infusion (figure ). Conclusions : Ionized hypocalcemia occurs following ROSC. This may be due to binding by lactate as evidenced by its strong association with the decline in base excess. CaCl 2 improves post-ROSC hemodynamics suggesting that hypocalcemia may play adial dysfunction.

Download Full-text

Small area estimation and childhood obesity surveillance using electronic health records

PLoS ONE ◽

10.1371/journal.pone.0247476 ◽

2021 ◽

Vol 16 (2) ◽

pp. e0247476

Author(s):

Ying-Qi Zhao ◽

Derek Norton ◽

Larry Hanrahan

Keyword(s):

Information Exchange ◽

Mixed Model ◽

Local Community ◽

Linear Mixed Model ◽

Kernel Smoothing ◽

Local Level ◽

Data Repository ◽

Obesity Prevalence ◽

Lower Estimation ◽

Prevalence Estimates

There is an urgent need for childhood surveillance systems to design, implement, and evaluate interventions at the local level. We estimated obesity prevalence for individuals aged 5–17 years using a southcentral Wisconsin EHR data repository, Public Health Information Exchange (PHINEX, 2007–2012). The prevalence estimates were calculated by aggregating the estimated probability of each individual being obese, which was obtained via a generalized linear mixed model. We incorporated the random effects at the area level into our model. A weighted procedure was employed to account for missingness in EHR data. A non-parametric kernel smoothing method was used to obtain the prevalence estimates for locations with no or little data (<20 individuals) from the EHR. These estimates were compared to results from newly available obesity atlas (2015–2016) developed from various EHRs with greater statewide representation. The mean of the zip code level obesity prevalence estimates for males and females aged 5–17 years is 16.2% (SD 2.72%); 17.9% (SD 2.14%) for males and 14.4% (SD 2.00%) for females. The results were comparable to the Wisconsin Health Atlas (WHA) estimates, a much larger dataset of local community EHRs in Wisconsin. On average, prevalence estimates were 2.12% lower in this process than the WHA estimates, with lower estimation occurring more frequently for zip codes without data in PHINEX. Using this approach, we can obtain estimates for local areas that lack EHRs data. Generally, lower prevalence estimates were produced for those locations not represented in the PHINEX database when compared to WHA estimates. This underscores the need to ensure that the reference EHRs database can be made sufficiently similar to the geographic areas where synthetic estimates are being created.

Download Full-text

Empirical performance of estimation methods in Beta mixed models with application to ecological data

Afrika Statistika ◽

10.16929/as/2020.2279.159 ◽

2020 ◽

Vol 15 (2) ◽

pp. 2279-2293

Author(s):

Saliou Diouf ◽

Bruno Enagnon Lokonon ◽

Freedath Djibril Moussa ◽

GLèLè KAKAï

Keyword(s):

Mixed Models ◽

Mixed Model ◽

Linear Mixed Model ◽

Real Life ◽

Estimation Methods ◽

Simulation Design ◽

Ecological Data ◽

Factors Affecting ◽

Real Life Data ◽

Empirical Performance

This study uses a Monte Carlo simulation design to assess the performance of Beta and linear mixed models on bounded response variables through comparison of four estimation methods. Four factors affecting the performance of the estimation methods were considered: the number of groups, the number of observations per group, the variance and distribution of the random effects. Our results showed that, for small number of groups (less than 30), the Beta mixed model outperformed the linear mixed model whatever the size of the groups. In the case of a large number of groups (superior or equal to 30), both approaches showed relatively close performance. The results from the simulation study have been illustrated with real life data.

Download Full-text

A Fast and Powerful Empirical Bayes Method for Genome-Wide Association Studies

Animals ◽

10.3390/ani9060305 ◽

2019 ◽

Vol 9 (6) ◽

pp. 305

Author(s):

Tianpeng Chang ◽

Julong Wei ◽

Mang Liang ◽

Bingxing An ◽

Xiaoqiao Wang ◽

...

Keyword(s):

Efficient Method ◽

Statistical Power ◽

Empirical Bayes ◽

Mixed Model ◽

Linear Mixed Model ◽

Association Studies ◽

Eigenvalue Decomposition ◽

Genome Wide Association Studies ◽

Bayes Method ◽

Empirical Bayes Method

Linear mixed model (LMM) is an efficient method for GWAS. There are numerous forms of LMM-based GWAS methods. However, improving statistical power and computing efficiency have always been the research hotspots of the LMM-based GWAS methods. Here, we proposed a fast empirical Bayes method, which is based on linear mixed models. We call it Fast-EB-LMM in short. The novelty of this method is that it uses a modified kinship matrix accounting for individual relatedness to avoid competition between the locus of interest and its counterpart in the polygene. This property has increased statistical power. We adopted two special algorithms to ease the computational burden: Eigenvalue decomposition and Woodbury matrix identity. Simulation studies showed that Fast-EB-LMM has significantly increased statistical power of marker detection and improved computational efficiency compared with two widely used GWAS methods, EMMA and EB. Real data analyses for two carcass traits in a Chinese Simmental beef cattle population showed that the significant single-nucleotide polymorphisms (SNPs) and candidate genes identified by Fast-EB-LMM are highly consistent with results of previous studies. We therefore believe that the Fast-EB-LMM method is a reliable and efficient method for GWAS.

Download Full-text

Logit-normal mixed model for Indian monsoon precipitation

Nonlinear Processes in Geophysics ◽

10.5194/npg-21-939-2014 ◽

2014 ◽

Vol 21 (5) ◽

pp. 939-953

Author(s):

L. R. Dietz ◽

S. Chatterjee

Keyword(s):

Mixed Model ◽

Linear Mixed Model ◽

Indian Monsoon ◽

Extreme Rainfall ◽

Estimation Methods ◽

Underlying Structure ◽

Normal Model ◽

Monsoon Precipitation ◽

Tuning Parameters ◽

Climatic Event

Abstract. Describing the nature and variability of Indian monsoon precipitation is a topic of much debate in the current literature. We suggest the use of a generalized linear mixed model (GLMM), specifically, the logit-normal mixed model, to describe the underlying structure of this complex climatic event. Four GLMM algorithms are described and simulations are performed to vet these algorithms before applying them to the Indian precipitation data. The logit-normal model was applied to light, moderate, and extreme rainfall. Findings indicated that physical constructs were preserved by the models, and random effects were significant in many cases. We also found GLMM estimation methods were sensitive to tuning parameters and assumptions and therefore, recommend use of multiple methods in applications. This work provides a novel use of GLMM and promotes its addition to the gamut of tools for analysis in studying climate phenomena.

Download Full-text

Parametric and semi-parametric bootstrap-based confidence intervals for robust linear mixed models

Methodology ◽

10.5964/meth.6607 ◽

2021 ◽

Vol 17 (4) ◽

pp. 271-295

Author(s):

Fabio Mason ◽

Eva Cantoni ◽

Paolo Ghisletta

Keyword(s):

Longitudinal Data ◽

Confidence Intervals ◽

Robust Estimation ◽

Mixed Model ◽

Linear Mixed Model ◽

Parametric Bootstrap ◽

Estimation Methods ◽

Low Probability ◽

Coverage Rates ◽

Comprehensive Study

The linear mixed model (LMM) is a popular statistical model for the analysis of longitudinal data. However, the robust estimation of and inferential conclusions for the LMM in the presence of outliers (i.e., observations with very low probability of occurrence under Normality) is not part of mainstream longitudinal data analysis. In this work, we compared the coverage rates of confidence intervals (CIs) based on two bootstrap methods, applied to three robust estimation methods. We carried out a simulation experiment to compare CIs under three different conditions: data 1) without contamination, 2) contaminated by within-, or 3) between-participant outliers. Results showed that the semi-parametric bootstrap associated to the composite tau-estimator leads to valid inferential decisions with both uncontaminated and contaminated data. This being the most comprehensive study of CIs applied to robust estimators of the LMM, we provide fully commented R code for all methods applied to a popular example.

Download Full-text

SMALL AREA ESTIMATION METHOD WITH EMPIRICAL BAYES BASED ON BETA BINOMIAL MODEL IN GENERATED DATA

MEDIA STATISTIKA ◽

10.14710/medstat.14.1.1-9 ◽

2020 ◽

Vol 14 (1) ◽

pp. 1-9

Author(s):

Ferra Yanuar ◽

Rahmatika Fajriyah ◽

Dodi Devianto

Keyword(s):

Binary Data ◽

Small Area ◽

Empirical Bayes ◽

Small Area Estimation ◽

Estimation Method ◽

Estimation Methods ◽

Auxiliary Variables ◽

Indirect Estimation ◽

Area Estimation ◽

Direct Estimation

Small Area Estimation is one of the methods that can be used to estimate parameters in an area that has a small population. This study aims to estimate the value of the binary data parameter using the direct estimation method and an indirect estimation method by using the Empirical Bayes approach. To illustrate the method, we consider three conditions: direct estimator, empirical Bayes (EB) with auxiliary variables, and empirical Bayes without auxiliary variables. The smaller value of Mean Square Error is used to determine the better method. The results showed that the indirect estimation methods (EB method) gave the parameter value that was not much different from the direct estimation value. Then, the MSE values of indirect estimation with an auxiliary variable are smaller than the direct estimation method.

Download Full-text

Using empirical Bayes predictors from generalized linear mixed models to test and visualize associations among longitudinal outcomes

Statistical Methods in Medical Research ◽

10.1177/0962280218758357 ◽

2018 ◽

Vol 28 (5) ◽

pp. 1399-1411 ◽

Cited By ~ 1

Author(s):

Susan K Mikulich-Gilbertson ◽

Brandie D Wagner ◽

Gary K Grunwald ◽

Paula D Riggs ◽

Gary O Zerbe

Keyword(s):

Random Effects ◽

Mixed Models ◽

Empirical Bayes ◽

Mixed Model ◽

Linear Mixed Model ◽

Maximum Likelihood Estimates ◽

Parameter Estimates ◽

P Values ◽

Association Analyses ◽

Second Stage

Medical research is often designed to investigate changes in a collection of response variables that are measured repeatedly on the same subjects. The multivariate generalized linear mixed model (MGLMM) can be used to evaluate random coefficient associations (e.g. simple correlations, partial regression coefficients) among outcomes that may be non-normal and differently distributed by specifying a multivariate normal distribution for their random effects and then evaluating the latent relationship between them. Empirical Bayes predictors are readily available for each subject from any mixed model and are observable and hence, plotable. Here, we evaluate whether second-stage association analyses of empirical Bayes predictors from a MGLMM, provide a good approximation and visual representation of these latent association analyses using medical examples and simulations. Additionally, we compare these results with association analyses of empirical Bayes predictors generated from separate mixed models for each outcome, a procedure that could circumvent computational problems that arise when the dimension of the joint covariance matrix of random effects is large and prohibits estimation of latent associations. As has been shown in other analytic contexts, the p-values for all second-stage coefficients that were determined by naively assuming normality of empirical Bayes predictors provide a good approximation to p-values determined via permutation analysis. Analyzing outcomes that are interrelated with separate models in the first stage and then associating the resulting empirical Bayes predictors in a second stage results in different mean and covariance parameter estimates from the maximum likelihood estimates generated by a MGLMM. The potential for erroneous inference from using results from these separate models increases as the magnitude of the association among the outcomes increases. Thus if computable, scatterplots of the conditionally independent empirical Bayes predictors from a MGLMM are always preferable to scatterplots of empirical Bayes predictors generated by separate models, unless the true association between outcomes is zero.

Download Full-text

Modeling determinants of anemia among pre-school children in Ethiopia: application of marginal and subject-specific models

Journal of Public Health in Africa ◽

10.4081/jphia.2015.521 ◽

2016 ◽

Vol 6 (2) ◽

Author(s):

Ashenafi Abebe Gaenemo ◽

Nebiyu Dereje Abebe ◽

Kebede Alemu Eliso

Keyword(s):

School Children ◽

Mixed Model ◽

Linear Mixed Model ◽

Research Question ◽

Correlated Data ◽

Strongly Correlated ◽

Disease Clustering ◽

Subject Specific ◽

Alternating Logistic Regression ◽

Different Levels

Anemia is a chronic disease that seriously affects young children and pregnant women. Knowledge of disease clustering is important because it may provide insights into the etiology of disease and risk factors operating within different levels of the clusters. In this study, we tried to identify determinants of anemia among pre-school children aged 6-59 months in the 11 regions of Ethiopia, with higher probability of occurrence of these determinant factors would be inferred to be most likely to experience anemia. To answer the objective of the research question, models that handle the complexities of correlated data were employed. Hence, both marginal and subject-specific models are employed. The models used were: Generalized Estimating Equations, Alternating Logistic Regression, Proportional Odds Model and Generalized Linear Mixed Model. Statistical findings revealed that the risk of being anemic reduced with age in girls, while boys showed higher risk. Children in rural were found to be less likely to be anemic. Children in large households were found to be more having a higher risk of anemia. Similarly, malaria occurrence was strongly correlated to anemia

Download Full-text

Preweaning Calf Survival of a Nellore Beef Cattle Population

Journal of Agricultural Science ◽

10.5539/jas.v9n8p51 ◽

2017 ◽

Vol 9 (8) ◽

pp. 51

Author(s):

Jairo Azevedo Junior ◽

Juliana Petrini ◽

Gerson Barreto Mourão ◽

José Bento Sterman Ferraz

Keyword(s):

Beef Cattle ◽

Mixed Model ◽

Linear Mixed Model ◽

Estimation Methods ◽

Linear Distribution ◽

Continuous Trait ◽

Categorical Trait ◽

Calf Survival ◽

Nellore Cattle ◽

Cattle Rearing

The preweaning calf survival (SW) is one of the main economic bottlenecks of beef cattle rearing systems, however there is still few quantitative studies approaching this issue. Being a binary trait, genetic parameters for SW can be estimated considering continuous or categorical data under frequentist and Bayesian methods providing support for the selection and mating of animals in breeding programs. Therefore, the objectives in this study were to obtain and compare the variance component estimates for preweaning calf survival of calves in single-trait analyses and their correlations with a continuous trait in two-trait analyses. An amount of 25 218 data of the categorical trait of calf survival until weaning (SW) and the continuous trait of weaning weight (WW) were collected between the years of 2000 and 2012 in six herds of Nellore cattle. Methods III of Henderson, Maximum Restricted Likelihood (REML), Bayesian Inference and Generalized Linear Mixed Model (GLMM) were tested. Variance components obtained in one-trait analyses were similar to those obtained in two-trait analyses. Estimates of heritability (h2) obtained with different models for SW ranged from 0.0206 to 0.2644. The comparison between different estimation methods in single or two-trait analysis models allows the conclusion that the most appropriate method for SW analysis was the Bayesian estimation under an animal model and assuming linear distribution for phenotypes of SW trait.

Download Full-text