Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

Results found: 6

first rewind previous Page / 1 next fast forward last

Search results

help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
1
Publication available in full text mode
Content available

On Misspecification of Spatial Weight Matrix for Small Area Estimation in Longitudinal Analysis

100%
Żądło T.
Comparative Economic Research. Central and Eastern Europe
|
2012
|
vol. 15
|
issue 4
305-318
EN
The problem of prediction of subpopulation (domain) total is studied as in Rao (2003). Considerations are based on spatially correlated longitudinal data. The domain of interest can be defined after sample selection what implies its random sample size. The special case of the General Linear Mixed Model is proposed where two random components obey assumptions of spatial and temporal moving average process respectively. Moreover, it is assumed that the population may change in time and elements’ affiliations to subpopulation may change in time as well. The proposed model is a generalization of longitudinal models studied by e.g. Verbeke, Molenberghs (2000) and Hedeker, Gibbons (2006). The best linear unbiased predictor (BLUP) is derived. It may be used even if the sample size in the subpopulation of interest in the period of interest is zero. In the Monte Carlo simulation study the accuracy of the empirical version of the BLUP will be studied in the case of correct and incorrect specification of the spatial weight matrix. Two cases of model misspecification are studied. In the first case the misspecified spatial weight is used. In the second case independence of random components is assumed but the variable which is used to compute elements of spatial weight matrix in the correct case will be used as auxiliary variable in the model.
2
Publication available in full text mode
Content available

On Some Problems of Prediction of Domain Total in Longitudinal Surveys when Auxiliary Information is Available

100%
Żądło T.
Studia Ekonomiczne
|
2013
|
vol. 133
86-106
PL
W artykule wyprowadzono postacie najlepszych liniowych nieobciążonych predyktorów przy założeniu pewnych modeli będących uogólnieniami na przypadek danych przekrojowo-czasowych modeli znanych z literatury statystyki małych obszarów. Ponadto wyprowadzono postacie błędów średniokwadratowych empirycznych wersji tych predyktorów oraz zaproponowano ich estymatory. W symulacji Monte Carlo porównywano dokładność zaproponowanego predyktora z dwoma ogólnymi estymatorami regresyjnymi po planie losowania i po modelu nadpopulacji (także w różnych przypadkach złej specyfikacji modelu). Ponadto analizowano obciążenia zaproponowanych estymatorów błędu średniokwadratowego.
3
Publication available in full text mode
Content available

On the generalisation of Quatember's bootstrap

100%
Żądło T.
Statistics in Transition new series
|
2021
|
vol. 22
|
issue 1
163-178
EN
The problem of the estimation of the design-variance and the design-MSE of different estimators and predictors is considered. Bootstrap algorithms applicable to complex sampling designs are used. A generalisation of the bootstrap procedure studied by Quatember (2014) is proposed. In most of the cases considered in our simulation study it leads to more accurate estimates (or to very similar ones in remaining cases) of the designMSE and the design-variance compared with the original algorithm and its other counteparts.
4
Publication available in full text mode
Content available

On Accuracy of Calibration Estimators Supported by Auxiliary Variables from Past Periods Based on Simulation Analyses

63%
Stachurski T., Żądło T.
Acta Universitatis Lodziensis. Folia Oeconomica
|
2017
|
vol. 4
|
issue 330
PL
W badaniach reprezentacyjnych nierzadko zachodzi potrzeba szacowania nie tylko parametrów populacji, ale także parametrów podpopulacji (domen). W artykule rozważany jest problem estymacji wartości globalnej w domenach. W takim przypadku może być stosowany estymator Horvitza‑Thompsona. Niemniej jednak nie uwzględnia on informacji dodatkowych o elementach populacji, które zazwyczaj są dostępne. Dlatego podjęto próbę zbadania własności estymatorów kalibrowanych, w których będą wykorzystywane informacje o zmiennych dodatkowych z bieżącego oraz przeszłych okresów.
EN
In sample surveys there is often a need to estimate not only population characteristics, but subpopulation characteristics as well. We consider the problem of estimating the total value in domains (subpopulations). In this case, the Horvitz‑Thompson estimator could be used. Nevertheless, it does not use any additional information about population units, which are usually known. To increase estimation accuracy we propose to use calibration estimators with auxiliary variables from the current and past periods. In the simulation studies based on real and generated data, we show the influence of using auxiliary information from past periods on the accuracy, and compare properties of two calibration estimators of domain totals in longitudinal surveys.
5
Publication available in full text mode
Content available

On Some Tests of Variance Components for Linear Mixed Models

63%
Krzciuk M., Żądło T.
Studia Ekonomiczne
|
2014
|
vol. 189
77-85
EN
In the paper three permutation tests of significance of variance components in the linear mixed model are presented. Two of them are permutation versions of classic tests. The third one is based on log-likelihood. In the Monte Carlo simulation studies properties of the permutation tests are compared with properties of the classic likelihood ratio test and Wald test.
6
Publication available in full text mode
Content available

On the choice of the number of Monte Carlo iterations and bootstrap replicates in Empirical Best Prediction

63%
Chwila A., Żądło T.
Statistics in Transition new series
|
2020
|
vol. 21
|
issue 2
35-60
EN
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 numerous repetitions of the random generation of population data. This leads to a question about the dependence between the number of iterations in all the procedures and the stability of the results. The aim of the paper is to show this dependence and to propose methods of choosing the appropriate number of iterations in practice, using a set of real economic longitudinal data available at the United States Census Bureau website.
first rewind previous Page / 1 next fast forward last
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.