{"id":605,"date":"2017-09-28T05:04:00","date_gmt":"2017-09-28T05:04:00","guid":{"rendered":"http:\/\/jsr.isrt.ac.bd\/?post_type=article&p=605"},"modified":"2017-09-28T05:04:07","modified_gmt":"2017-09-28T05:04:07","slug":"comparing-ratio-estimators-based-systematic-samples","status":"publish","type":"article","link":"http:\/\/jsr.isrt.ac.bd\/article\/comparing-ratio-estimators-based-systematic-samples\/","title":{"rendered":"Comparing ratio estimators based on systematic samples"},"content":{"rendered":"
The purpose of this study is to evaluate competitive ratio estimators, and introduce
\na new approach to estimation when a systematic sample of size with
\na random start is used. The competitive ratio estimators are the mean of ratios,
\nratio of means, and the conditional best linear unbiased estimator. These
\nestimators are used to measure the population proportion of the total of a variable
\n with respect to another variable, . A new approach is suggested, a
\nbootstrap estimate using a non-linear additive regression technique, in which a
\nMonte-Carlo simulation is done using the predicted values from the fitted model
\nto find estimates for the variances. This new approach has yielded small mean
\nsquare errors.<\/p>\n