On two sampling techniques for estimation of quantiles
AbstractThe balanced sampling design, which is defined by the property that Horvitz-Thompson estimators of the population totals of a set of auxiliary variables equal the known totals of these variables, is a good method for decreasing the variability of estimators of totals of variables of interest. Similar idea can be utilized in the context of estimation of quantiles. If the sample is drawn in a way that simple estimators of quantiles or cumulative distribution functions of a set of auxiliary variables equal the known quantiles or cumulative distribution functions of these variables, than estimators of quantiles of variables of interest should be less variable. Simulation experiments were carried out which indicate that this is a justified supposition.
|Journal series||Zarządzanie i Finanse, ISSN 2084-5189, (B 10 pkt)|
|No||4, cz. 3|
|Publication size in sheets||0.7|
|Keywords in English||quantile estimation, sampling algorithms, balanced sampling, cumulative distribution function|
|Score||= 10.0, 06-03-2020, ArticleFromJournal|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.