{"id":479,"date":"2017-09-24T05:06:36","date_gmt":"2017-09-24T05:06:36","guid":{"rendered":"http:\/\/jsr.isrt.ac.bd\/?post_type=article&p=479"},"modified":"2017-09-24T05:06:51","modified_gmt":"2017-09-24T05:06:51","slug":"linearity-truncated-bivariate-normal-distribution","status":"publish","type":"article","link":"http:\/\/jsr.isrt.ac.bd\/article\/linearity-truncated-bivariate-normal-distribution\/","title":{"rendered":"On the linearity truncated bivariate normal distribution"},"content":{"rendered":"
Motivated by a problem in archaeological data analysis, we examine through
\nsimulation the effect of linear truncation on density estimation in the bivariate
\nnormal distribution. It is shown that the estimation procedure performs poorly
\nwhen the truncation line is parallel to the minor axis of the elliptical contours
\nof the distribution. The estimation also worsens with increasing correlation and
\nincreasing disparity in the values of the variances in the distribution. Reconstruction
\nof the bivariate normal distribution is best achieved when truncation is
\nparallel to the major axis and there is only about 10% of the data that is missing.<\/p>\n
<\/p>\n