Skew normal small area time models for the Brazilian annual service sector survey

Publications

Share / Export Citation / Email / Print / Text size:

Statistics in Transition New Series

Polish Statistical Association

Central Statistical Office of Poland

Subject: Economics , Statistics & Probability

GET ALERTS

ISSN: 1234-7655
eISSN: 2450-0291

DESCRIPTION

6
Reader(s)
14
Visit(s)
0
Comment(s)
0
Share(s)

SEARCH WITHIN CONTENT

FIND ARTICLE

Volume / Issue / page

Related articles

VOLUME 21 , ISSUE 4 (August 2020) > List of articles

Special Issue

Skew normal small area time models for the Brazilian annual service sector survey

André Felipe Azevedo Neves / Denise Britz do Nascimento Silva / Fernando Antônio da Silva Moura

Keywords : Annual Service Sector Survey, hierarchical Bayesian model

Citation Information : Statistics in Transition New Series. Volume 21, Issue 4, Pages 84-102, DOI: https://doi.org/10.21307/stattrans-2020-032

License : (CC BY-NC-ND 4.0)

Received Date : 31-January-2020 / Accepted: 30-June-2020 / Published Online: 15-September-2020

ARTICLE

ABSTRACT

Small domain estimation covers a set of statistical methods for estimating quantities in domains not previously considered by the sample design. In such cases, the use of a model-based approach that relates sample estimates to auxiliary variables is indicated. In this paper, we propose and evaluate skew normal small area time models for the Brazilian Annual Service Sector Survey (BASSS), carried out by the Brazilian Institute of Geography and Statistics (IBGE). The BASSS sampling plan cannot 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, based on 10-year survey data (2007-2016), show substantial improvement in the precision of the estimates, albeit with presence of some bias.

Content not available PDF Share

FIGURES & TABLES

REFERENCES

ARORA, V., LAHIRI, P., (1997). On the superiority of the Bayesian methods over the BLUP in small area estimation problems. Statistica Sinica 7, pp. 1053–1063.

AZZALINI, A., (1985). A class of distributions which includes the normal ones. Scandinavian Journal of Statistics, 12, 171–178.

BATTESE, G. E., HARTER, R. M., FULLER, W.A., (1988). An error-components model for prediction of county crop areas using survey and satellite data. Journal of the American Statistical Association, Mar/1988, Vol.83, 401, pp. 28–36.

DATTA, G. S, LAHIRI, P., MAITI, T. and LU, K. L., (1999). Hierarchical Bayes estimation of unemployment rates for the U.S. states. Journal of the American Statistical Association, 94, pp. 1074–1082.

FAY, R. E., HERRIOT, R. A., (1979). Estimates of income for small places: an application of James-Stein procedures to census data. Journal of the American Statistical Association, Vol. 74, 366, pp. 269–277.

FERRAZ, V. R. S., MOURA, F. A. S., (2012). Small area estimation using skew normal models. Computational Statistics & Data Analysis 56(10), pp. 2864–2874.

GELMAN, A., (2006). Prior distributions for variance parameters in hierarchical models (Comment on Article by Browne and Draper). Bayesian Analysis 3, pp. 515–534.

GELMAN, A., RUBIN, D. B., (1992). Inference from Iterative Simulation Using Multiple Sequences. Statistical Science 7(4), pp. 457–472.

GENTON, M. G., (2004). Skew-elliptical distributions and their applications: a journey beyond normality. Chapman & Hall/CRC.

GERSHUNSKAYA, J., SAVITSKY, T. D., (2019). Model-based screening for robust estimation in the presence of deviations from linearity in small domain models. Journal of Survey Statistics and Methodology, 8, 2, pp. 181–205.

IBGE – Instituto Brasileiro de Geografia e Estat´ıstica. Pesquisa Anual de Servi¸cos 2016. Diretoria de Pesquisas, Coordena¸c˜ao de Servi¸cos e Com´ercio. Rio de Janeiro, 2018.

MENG, X.-L., (1994). Posterior predictive p-values. Annals of Statistics, 22, pp. 1142– 1160.

MOURA, F. A. S., HOLT, D., (1999). Small area estimation using multilevel models. Survey Methodology, June 1999, 73, Vol. 25, 1, pp. 73–80, Statistics Canada, Catalogue No. 12-001.

MOURA, F. A. S., NEVES, A. F. A., SILVA, D. B. N., (2017). Small area models for skewed Brazilian business survey data. Journal of Royal Statistical Society, 180,Part 4, pp. 1039–1055, serie A.

NEVES, A. F. A., (2012). Small domain estimation applied to Annual Service Sector Survey 2008. Master dissertation of National School of Statistical Sciences (originally in Portuguese). Rio de Janeiro, jul/2012.

NEVES, A. F. A.,SILVA, D. B. N.,CORREA, S. T., (2013). Small domain estimation ˆ for the Brazilian Service Sector Survey. Estad´ıstica, 65, 185, pp. 13–37, Instituto Interamericano de Estad´ıstica).

RAO, J. N. K., MOLINA, I., (2015). Small area estimation, 2nd ed., New York, Wiley.

RAO, J. N. K., YU, M., (1994). Small-Area Estimation by Combining Time-Series and Cross-Sectional Data. The Canadian Journal of Statistics, 22, 4, pp. 511–528.

SPIEGELHALTER, D. J., BEST, N. G., CARLIN, B. P., LINDE, A. V., (2002). Bayesian measures of model complexity and fit. Journal of Royal Statistical Society, B 64, Part 4, pp. 583–639.

SUGDEN, R., SMITH, T., JONES, R., (2000). Cochran’s rule for simple random sampling. Journal of the Royal Statistical Society: Series B 62, pp. 787–793.

 

EXTRA FILES

COMMENTS