mintu das - Academia.edu (original) (raw)
Related Authors
Indian Agricultural Statistics Research Institute
Uploads
Papers by mintu das
Indian Journal of Applied Research, May 1, 2015
Here we try to explain the use of graphical displays for outlying and influential observations in... more Here we try to explain the use of graphical displays for outlying and influential observations in regression analysis. An attempt has been made to classify the observations with the help of some two dimensional plots, which will be comprised of four quadrants.Depending upon the location of the observations, these will be labeled either as good or bad observations. The observations falling in the upper left and lower right quadrants will be subjected for further scrutiny. Also the findings are compared with robust regression. For ensuring proper use of such plots we use some well-referred datasets.
IARJSET, 2015
This paper aims to compare the empirical powers of some statistics for detecting multiple upper o... more This paper aims to compare the empirical powers of some statistics for detecting multiple upper outliers in exponential samples under slippage alternative. In addition to that we also investigate masking effect for various degree of discordancy parameter. The results which are based on simulation study, indicate that the maximum likelihood ratio test statistic is better than the other statistics followed by Dixon type test statistics to deal with upper outliers in exponential samples. Also in case of combating masking the maximum likelihood ratio test statistic is better and the test proposed by Lalitha and Kumar (2012) precede Dixon type test.
Indian Journal of Applied Research, May 1, 2015
Here we try to explain the use of graphical displays for outlying and influential observations in... more Here we try to explain the use of graphical displays for outlying and influential observations in regression analysis. An attempt has been made to classify the observations with the help of some two dimensional plots, which will be comprised of four quadrants.Depending upon the location of the observations, these will be labeled either as good or bad observations. The observations falling in the upper left and lower right quadrants will be subjected for further scrutiny. Also the findings are compared with robust regression. For ensuring proper use of such plots we use some well-referred datasets.
IARJSET, 2015
This paper aims to compare the empirical powers of some statistics for detecting multiple upper o... more This paper aims to compare the empirical powers of some statistics for detecting multiple upper outliers in exponential samples under slippage alternative. In addition to that we also investigate masking effect for various degree of discordancy parameter. The results which are based on simulation study, indicate that the maximum likelihood ratio test statistic is better than the other statistics followed by Dixon type test statistics to deal with upper outliers in exponential samples. Also in case of combating masking the maximum likelihood ratio test statistic is better and the test proposed by Lalitha and Kumar (2012) precede Dixon type test.