Sampling Methods | 20-November-2017
The mean squared error reflects only the average prediction accuracy while the distribution of squared prediction error is positively skewed. Hence, assessing or comparing accuracy based on the MSE (which is the mean of squared errors) is insufficient and even inadequate because we should be interested not only in the average but in the whole distribution of prediction errors. This is the reason why we propose to use different than MSE measures of prediction accuracy in small area estimation
Tomasz Żądło
Statistics in Transition New Series, Volume 18 , ISSUE 3, 413–432
Article | 06-July-2017
census, the total population counts. Further, the design should also adequately support the application of small area estimation methods. Some empirical results are given to provide an assessment of selected methods. The research was conducted within the German Census Sampling and Estimation research project, financially supported by the German Federal Statistical Office.
Ralf Münnich,
Jan Pablo Burgard,
Siegfried Gabler,
Matthias Ganninger,
Jan-Philipp Kolb
Statistics in Transition New Series, Volume 17 , ISSUE 1, 25–40
Research paper | 01-November-2017
The aim of the paper is to present some experiences in teaching Small Area Estimation (SAE). SAE education experiences and challenges are analysed from the academic side and from the NSI side. An attempt was undertaken to discuss SAE issues in a wider perspective of teaching statistics. In particular, the topics refer to Polish conditions, but they are presented against the background of selected international experiences and practices. Information comes from a special inquiry - a survey
Elżbieta Gołata
Statistics in Transition New Series, Volume 16 , ISSUE 4, 611–630
Research paper | 01-November-2017
The increasing interest in applying small area estimation methods urges the needs for training in small area estimation. To better understand the behaviour of small area estimators in practice, simulations are a feasible way for evaluating and teaching properties of the estimators of interest. By designing such simulation studies, students gain a deeper understanding of small area estimation methods. Thus, we encourage to use appropriate simulations as an additional interactive tool in teaching
Jan Pablo Burgard,
Ralf Münnich
Statistics in Transition New Series, Volume 16 , ISSUE 4, 603–610
Article | 15-September-2020
The paper is an attempt to trace some of the early developments of small area estimation. The basic papers such as the ones by Fay and Herriott (1979) and Battese, Harter and Fuller (1988) and their follow-ups are discussed in some details. Some of the current topics are also discussed.
Malay Ghosh
Statistics in Transition New Series, Volume 21 , ISSUE 4, 1–22
Research paper | 01-November-2017
Forough Karlberg
Statistics in Transition New Series, Volume 16 , ISSUE 4, 541–562
Article | 06-July-2017
Jan Kubacki,
Alina Jędrzejczak
Statistics in Transition New Series, Volume 17 , ISSUE 3, 365–390
Research paper | 31-October-2017
This paper develops allocation methods for stratified sample surveys in which small area estimation is a priority. We assume stratified sampling with small areas as the strata. Similar to Longford (2006), we seek efficient allocation that minimizes a linear combination of the mean squared errors of composite small area estimators and of an estimator of the overall mean. Unlike Longford, we define mean-squared error in a model-assisted framework, allowing a more natural interpretation of results
W. B. Molefe,
D. K. Shangodoyin,
R. G. Clark
Statistics in Transition New Series, Volume 16 , ISSUE 2, 163–182
Article | 06-July-2017
We review main small area estimation methods for the estimation of general nonlinear parameters focusing on FGT family of poverty indicators introduced by Foster, Greer and Thorbecke (1984). In particular, we consider direct estimation, the Fay-Herriot area level model (Fay and Herriot, 1979), the method of Elbers, Lanjouw and Lanjouw (2003) used by the World Bank, the empirical Best/Bayes (EB) method of Molina and Rao (2010) and its extension, the Census EB, and finally the hierarchical Bayes
María Guadarrama,
Isabel Molina,
J. N. K. Rao
Statistics in Transition New Series, Volume 17 , ISSUE 1, 41–66
Research paper | 01-November-2017
Small area estimation (SAE) has seen a rapid growth over the past 10 years or so. Earlier work is covered in the author's book (Rao 2003). The main purpose of this paper is to highlight some new developments in model-based SAE since the publication of the author's book. A large part of the new theory addressed practical issues associated with the model-based approach, and we present some of those methods for area level and unit level models. We also briefly mention some new work on synthetic
J. N. K. Rao
Statistics in Transition New Series, Volume 16 , ISSUE 4, 491–510
Article | 05-September-2021
relative bias and greater efficiency. Moreover, they prove more consistent than the existing classical synthetic estimator. The further evaluation carried out using the coefficient of variation provides additional confirmation of the calibrated estimator’s advantage over the existing ones in relation to small area estimation.
Matthew Joshua Iseh,
Ekaette Inyang Enang
Statistics in Transition New Series, Volume 22 , ISSUE 3, 15–30
Research paper | 01-November-2017
If the implementation of small area estimation methods to multiple editions of a repeated sample survey is considered, then the question arises which covariates to use in the models. Applying standard model selection procedures independently to the different editions of the survey may identify different sets of covariates for each edition. If the small area predictions are sensitive to the different models, this is undesirable in official statistics since monitoring change over time of
Jan A. van den Brakel,
Bart Buelens
Statistics in Transition New Series, Volume 16 , ISSUE 4, 523–540
Research paper | 01-November-2017
In this paper, we first develop a triple-goal small area estimation methodology for simultaneous estimation of unemployment rates for U.S. states using the Current Population Survey (CPS) data and a two-level random sampling variance normal model. The main goal of this paper is to illustrate the utility of the triple-goal methodology in generating a single series of unemployment rate estimates for three separate purposes: developing estimates for individual small area means, producing
Daniel Bonnéry,
Yang Cheng,
Neung Soo Ha,
Partha Lahiri
Statistics in Transition New Series, Volume 16 , ISSUE 4, 511–522
Article | 06-July-2017
. Next, before discussing general issues of small area estimation (SAE) in official statistics, the author reminds: the methods of sampling surveys, data collection, estimation procedures, and data quality assessment used for official statistics. Statistical information is published in different breakdowns with stable or even decreasing budget while being legally bound to control the response burden. Special attention is paid, from a practitioner point of view, to synthetic development of small area
Jan Kordos
Statistics in Transition New Series, Volume 17 , ISSUE 1, 105–132
Research Article | 24-August-2017
of unwanted births ends in childbirths, and which are related to deaths and injuries for both mother and child. Due to lack of availability of reliable data at the small level (area-wise) specifically in developing countries like India. In this article the small area estimation technique is used for the estimation of met and unmet need for contraception for 187 towns of Rajasthan state of India and for empirical analysis. Data is taken from the District Level Household Survey (DLHS): 2002-04 and
Piyush Kant Rai,
Sarla Pareek,
Hemlata Joshi
Statistics in Transition New Series, Volume 18 , ISSUE 2, 329–360
Research paper | 01-November-2017
Linear area level models for small area estimation, such as the Fay-Herriot model, face challenges when applied to discrete survey data. Such data commonly arise as direct survey estimates of the number of persons possessing some characteristic, such as the number of persons in poverty. For such applications, we examine a binomial/logit normal (BLN) model that assumes a binomial distribution for rescaled survey estimates and a normal distribution with a linear regression mean function for
Carolina Franco,
William R. Bell
Statistics in Transition New Series, Volume 16 , ISSUE 4, 563–584
Article | 06-July-2017
, within spatio temporal domains subdivided by the mode of fishing. Because many of these domains have small sample sizes, small area estimation methods are developed. Bayesian inference for the circular distributions on the 24-hour clock is conducted, based on a large set of observed daily departure times from another National Marine Fisheries Service study, the Coastal Household Telephone Survey. A novel variational/Laplace approximation to the posterior distribution allows fast comparison of a large
Daniel Hernandez-Stumpfhauser,
F. Jay Breidt,
Jean D. Opsomer
Statistics in Transition New Series, Volume 17 , ISSUE 1, 91–104
Research Article | 13-June-2021
The EU Statistics on Income and Living Conditions (EU-SILC) has provided annual esti mates of the number of labour market indicators for EU countries since 2003, with an almost exclusive focus on national rates. However, it is impossible to obtain reliable direct estimates of labour market statistics at low levels based on the EU-SILC survey. In such cases, model based small area estimation can be used. In this paper, the low work intensity indicator for the spatial domains in Poland between
Łukasz Wawrowski,
Maciej Beręsewicz
Statistics in Transition New Series, Volume 22 , ISSUE 2, 155–172
Article | 18-March-2020
The paper presents an empirical study designed to test a small area estimation method. The aim of the study is to apply a robust version of the Fay-Herriot model to the estimation of average wages in the small business sector. Unlike the classical Fay-Herriot model, its robust version makes it possible to meet the assumption of normality of random effects under the presence of outliers. Moreover, the use of this version of the Fay-Herriot model helps to improve the precision of estimates
Grażyna Dehnel,
Łukasz Wawrowski
Statistics in Transition New Series, Volume 21 , ISSUE 1, 137–157
Article | 22-January-2018
Alina Jędrzejczak,
Jan Kubacki
Statistics in Transition New Series, Volume 18 , ISSUE 4, 725–742
Article | 15-September-2020
Song Cai,
J. N. K. Rao,
Laura Dumitrescu,
Golshid Chatrchi
Statistics in Transition New Series, Volume 21 , ISSUE 4, 68–83
Research paper | 31-October-2017
Nicholas T. Longford
Statistics in Transition New Series, Volume 16 , ISSUE 1, 65–82
Article | 13-December-2019
Alina Jędrzejczak,
Jan Kubacki
Statistics in Transition New Series, Volume 20 , ISSUE 4, 113–134
Article | 15-September-2020
Julie Gershunskaya
Statistics in Transition New Series, Volume 21 , ISSUE 4, 23–29
Article | 15-September-2020
Isabel Molina
Statistics in Transition New Series, Volume 21 , ISSUE 4, 40–44
Article | 15-September-2020
Ying Han
Statistics in Transition New Series, Volume 21 , ISSUE 4, 30–34
Article | 15-September-2020
David Newhouse
Statistics in Transition New Series, Volume 21 , ISSUE 4, 45–50
Article | 15-September-2020
J. N. K. Rao
Statistics in Transition New Series, Volume 21 , ISSUE 4, 53–58
Article | 15-September-2020
Danny Pfeffermann
Statistics in Transition New Series, Volume 21 , ISSUE 4, 51–52
Article | 15-September-2020
Yan Li
Statistics in Transition New Series, Volume 21 , ISSUE 4, 35–39
Article | 06-July-2017
Adrijo Chakraborty,
Gauri Sankar Datta,
Abhyuday Mandal
Statistics in Transition New Series, Volume 17 , ISSUE 1, 67–90
Research Article | 01-June-2020
Empirical Best Predictors (EBPs) are widely used for small area estimation purposes. In the case of longitudinal surveys, this class of predictors can be used to predict any given population or subpopulation characteristic for any time period, including future periods. Generally, the value of an EBP is computed by means of Monte Carlo algorithms, while its MSE is usually estimated using the parametric bootstrap method. Model-based simulation studies of the properties of the predictors require
Adam Chwila,
Tomasz Żądło
Statistics in Transition New Series, Volume 21 , ISSUE 2, 35–60
Article | 15-September-2020
produce estimates with acceptable precision for service activities in the North, Northeast and Midwest regions of the country. Therefore, the use of small area estimation models may provide acceptable precise estimates, especially if they take into account temporal dynamics and sector similarity. Besides, skew normal models can handle business data with asymmetric distribution and the presence of outliers. We propose models with domain and time random effects on the intercept and slope. The results
André Felipe Azevedo Neves,
Denise Britz do Nascimento Silva,
Fernando Antônio da Silva Moura
Statistics in Transition New Series, Volume 21 , ISSUE 4, 84–102
Article | 22-January-2018
estimation methods, which rely on information from outside the subpopulation of interest, which usually increases estimation precision. The main aim of this paper is to show results of estimation of the poverty indicator at a lower level of spatial aggregation than the one used so far, that is at the level of subregions in Poland (NUTS 3) using the small area estimation methodology (SAE), i.e. a model–based technique – the EBLUP estimator based on the Fay–Herriot model. By optimally
Marcin Szymkowiak,
Andrzej Młodak,
Łukasz Wawrowski
Statistics in Transition New Series, Volume 18 , ISSUE 4, 609–635
Article | 20-September-2020
Typically survey data have responses with gaps, outliers and ties, and the distributions of the responses might be skewed. Usually, in small area estimation, predictive inference is done using a two-stage Bayesian model with normality at both levels (responses and area means). This is the Scott-Smith (S-S) model and it may not be robust against these features. Another model that can be used to provide a more robust structure is the two-stage Dirichlet process mixture (DPM) model, which has
Jiani Yin,
Balgobin Nandram
Statistics in Transition New Series, Volume 21 , ISSUE 3, 1–19