{"id":286,"date":"2017-03-14T20:21:06","date_gmt":"2017-03-14T20:21:06","guid":{"rendered":"http:\/\/jsr.isrt.ac.bd\/?post_type=article&p=286"},"modified":"2017-03-14T20:21:06","modified_gmt":"2017-03-14T20:21:06","slug":"several-simple-linear-models-measurement-errors-parallelism-hypothesis","status":"publish","type":"article","link":"http:\/\/jsr.isrt.ac.bd\/article\/several-simple-linear-models-measurement-errors-parallelism-hypothesis\/","title":{"rendered":"Several Simple Linear models with measurement errors: parallelism hypothesis"},"content":{"rendered":"
The problem of estimation of the regression parameters in several simple regression models
\nwith measurement errors is considered when it is suspected that the regression lines may
\nbe parallel with some degree of uncertainty. In this regard we propose five estimators,
\nnamely, (i) the unrestricted estimator, (ii) the restricted estimator, (iii) the preliminary test
\nestimator, (iv) the Stein-type estimator and (v) the positive-rule Stein-type estimator as
\nin Saleh (2006). Properties of these estimators are studied in an asymptotic set up and
\nthe asymptotic distributional bias, MSE matrices, and risk under a quadratic loss function
\nare obtained based on a sequence of local alternatives and dominance properties of these
\nestimators are provided.<\/p>\n