Testing equality of two intercepts for the parallel regression model with non-sample prior information

Pratikno, Budi and Khan, Shahjahan (2017) Testing equality of two intercepts for the parallel regression model with non-sample prior information. Communications in Statistics: Theory and Methods, 46 (6). pp. 3099-3110. ISSN 0361-0926

[img]
Preview
Text (Accepted Version)
Pratikto_Khan_AV.pdf

Download (247Kb) | Preview

Abstract

This paper proposes tests for equality of intercepts of two simple regression models when non-sample prior information (NSPI) is available on the equality of two slopes. For three different scenarios on the values of the slope, namely (i) unknown (unspecified), (ii) known (specified), and (iii) suspected, we derive the unrestricted test (UT), restricted test (RT) and pre-test test (PTT) for testing equality of intercepts. The test statistics, their sampling distributions, and power functions of the tests are obtained. Comparison of power function and size of the tests reveal that the PTT has a reasonable dominance over the UT and RT.


Statistics for USQ ePrint 28125
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Additional Information: Accepted Version deposited in accordance with the copyright policy of the publisher. Published online only.
Faculty / Department / School: Current - Faculty of Health, Engineering and Sciences - School of Agricultural, Computational and Environmental Sciences
Date Deposited: 07 Dec 2015 07:26
Last Modified: 07 Nov 2018 01:14
Uncontrolled Keywords: linear regression; intercept and slope parameters; pre- test test; non-sample prior information; and power function
Fields of Research : 01 Mathematical Sciences > 0104 Statistics > 010499 Statistics not elsewhere classified
01 Mathematical Sciences > 0104 Statistics > 010405 Statistical Theory
Socio-Economic Objective: E Expanding Knowledge > 97 Expanding Knowledge > 970101 Expanding Knowledge in the Mathematical Sciences
Identification Number or DOI: 10.1080/03610926.2015.1054941
URI: http://eprints.usq.edu.au/id/eprint/28125

Actions (login required)

View Item Archive Repository Staff Only