1,721,055 research outputs found
Small area estimation in the era of machine learning and alternative data sources: opportunities, challenges and outlook
No full textBias Adjusted Estimation for Small Areas with Outlying Values
No full textSmall area estimation techniques typically rely on regression models that use both covariates and random effects to explain between domain variation. Chambers and Tzavidis (2006) describe a novel approach to small area estimation that is based on modelling quantile-like parameters of the conditional distribution of the target variable given the covariates. This is an outlier robust approach that avoids conventional Gaussian assumptions and the problems associated with specification of random effects, allowing inter-domain differences to be characterized by the variation of area-specific M-quantile coefficients. These authors observed, however, that M-quantile estimates of small area means are biased with the magnitude of the bias being related to the presence of outliers in the data. In this paper we propose a bias adjustment to the M-quantile small area estimator of the mean that is based on representing this estimator as a functional of the small area distribution function. The method is then generalized for estimating other quantiles of the distribution function in a small area. The effect of this bias adjustment on small area estimation with random effects models in the presence of model misspecification is also examined
Psychopathology and prosocial behavior in adolescents from socio-economically disadvantaged families: the role of proximal and distal adverse life events
Full text linkThe study investigated if proximal contextual risk (number of adverse life events experienced in the last year) or distal contextual risk (number of adverse life events experienced before the last year) is a better predictor of adolescent psychopathology and prosocial behavior. It also tested for the specificity, accumulation and gradient of contextual risk in psychopathology and prosocial behavior, and for the interaction between proximal and distal contextual risk in psychopathology and prosocial behavior. The sample was 199 11-18 year old children from a socio-economically disadvantaged area in North- East London. The Strengths and Difficulties Questionnaire (SDQ), which measures four difficulties (hyperactivity, emotional symptoms, conduct problems, and peer problems) and prosocial behavior, was used. Confounders were age, gender, and maternal educational qualifications. To model the relationship between the five SDQ scales and contextual risk multivariate response regression models and multivariate response logistic regression models that allow the error terms of the scale specific models to be correlated were fitted. This study highlighted the importance of proximal contextual risk in predicting both broad and externalizing psychopathology, and the importance of considering risk accumulation rather than specificity in predicting psychopathology. By showing that the number of proximal adverse life events experienced had a steady, additive effect on broad and externalizing psychopathology, it also highlighted the need to protect adolescents experiencing current risk from further risk exposure. By showing that the number of distal adverse life events experienced did not affect the proximal risk’s impact on either broad or externalizing psychopathology, it highlighted the need to protect all adolescents, irrespective of experience of early life adversities, from risk
Estimating regional income indicators under transformations and access to limited population auxiliary information
Full text linkSpatially disaggregated income indicators are typically estimated by using model-based methods that assume access to auxiliary information from population micro-data. In many countries like Germany and the UK population micro-data are not publicly available. In this work we propose small area methodology when only aggregate population-level auxiliary information is available. We use data-driven transformations of the response to satisfy the parametric assumptions of the used models. In the absence of population micro-data, appropriate bias-corrections for small area prediction are needed. Under the approach we propose in this paper, aggregate statistics (means and covariances) and kernel density estimation are used to resolve the issue of not having access to population micro-data. We further explore the estimation of the mean squared error using the parametric bootstrap. Extensive model-based and design-based simulations are used to compare the proposed method to alternative methods. Finally, the proposed methodology is applied to the 2011 Socio-Economic Panel and aggregate census information from the same year to estimate the average income for 96 regional planning regions in German
Multivariate Mixed Hidden Markov Model for joint estimation of multiple quantiles
No full textThis paper develops a Mixed Hidden Markov Model for joint estimation of multiple quantiles in a multivariate linear regression for longitudinal data. This method accounts for association among multiple responses and study how the relationship between dependent and explanatory variables may vary across different quantile levels of the conditional distribution of the multivariate response variable. Unobserved heterogeneity sources and serial dependence are jointly modeled through the introduction of individual-specific, time-constant random coefficients and time-varying parameters that evolve over time with a Markovian structure, respectively. Estimation is carried out via a suitable EM algorithm without parametric assumptions on the random effects distribution. We assess the empirical behaviour of the proposed methodology through the analysis of the Millennium Cohort Study data
Directional M-quantile regression for multivariate dependent outcomes
No full textIn the present work we generalize the univariate M-quantile regression to the analysis of multivariate dependent outcomes. Extending the notion of directional quantiles, we introduce directional M-quantiles which are obtained as projections of the original data on a specified unit norm direction. In order to take into consideration the correlation within grouped measurements and to increase efficiency, we develop a marginal M-Quantile regression model extending the well known generalized estimating equations approach. We build M-quantile regions and contours which allow us to investigate the effect of the covariates on the location, spread and shape of the distribution of the responses. To identify potential outliers and provide a simple visual representation of the variability of the M quantile contours estimator, we construct confidence envelope via nonparametric bootstrap. The validity of our method is analyzed through the study of the wages data from the National Longitudinal Survey of Youth
Non-verbal reasoning ability and academic achievement as moderators of the relation between adverse life events and emotional and behavioural problems in early adolescence: the importance of moderator and outcome specificity
No full textThis study was carried out to model the functional form of the effect of contextual risk (number of adverse life events) on emotional and behavioural problems in early adolescence, and to test how intelligence and academic achievement compare as moderators of this effect. The effect of number of adverse life events on emotional and behavioural problems was non-quadratic. Intelligence rather than academic achievement moderated the association between contextual risk and children's emotional and behavioural problems. However, the interaction effect was significant only on peer problems. These findings suggest that both moderator and outcome specificity should be considered when evaluating the role of intellectual competence in the association between contextual risk and children's emotional and behavioural problems. <br/
Robust estimation of the Theil index and the Gini coefficient for small areas
Full text linkSmall area estimation is receiving considerable attention due to the high demand for small area statistics. Small area estimators of means and totals have been widely studied in the literature. Moreover, in the last years also small area estimators of quantiles and poverty indicators have been studied. In contrast, small area estimators of inequality indicators, which are often used in socio-economic studies, have received less attention. In this article we propose a robust method based on the M-quantile regression model for small area estimation of the Theil index and the Gini coefficient, two popular inequality measures. To estimate the mean squared error a non-parametric bootstrap is adopted. A robust approach is used because often inequality is measured using income or consumption data, which are often non-normal and affected by outliers. The proposed methodology is applied to income data to estimate the Theil index and the Gini coefficient for small domains in Tuscany (provinces by age groups), using survey and Census micro-data as auxiliary variables. In addition, a design-based simulation is carried out to study the behaviour of the proposed robust estimators. The performance of the bootstrap mean squared error estimator is also investigated in the simulation stud
M-Quantile Models for Small Area Estimation
Full text linkSmall area estimation techniques are employed when sample data are insufficient for acceptably precise direct estimation in domains of interest. These techniques typically rely on regression models that use both covariates and random effects to explain variation between domains. However, such models also depend on strong distributional assumptions, require a formal specification of the random part of the model and do not easily allow for outlier robust inference. We describe a new approach to small area estimation that is based on modelling quantile-like parameters of the conditional distribution of the target variable given the covariates. This avoids the problems associated with specification of random effects, allowing inter-domain differences to be characterized by the variation of area-specific M-quantile coefficients. The proposed approach is easily made robust against outlying data values and can be adapted for estimation of a wide range of area specific parameters, including that of the quantiles of the distribution of the target variable in the different small areas. Results from two simulation studies comparing the performance of the M-quantile modelling approach with more traditional mixed model approaches are also provided
- …
