Homogeneity Test for Multiple Semicontinuous Data with the Density Ratio Model

Yufan Wang and Xingzhong Xu ()
Additional contact information
Yufan Wang: School of Mathematics and Statistics, Beijing Institute of Technology, Beijing 100081, China
Xingzhong Xu: School of Mathematical Science, Shenzhen University, Shenzhen 518060, China

Mathematics, 2023, vol. 11, issue 17, 1-28

Abstract: The density ratio model has been widely used in many research fields. To test the homogeneity of the model, the empirical likelihood ratio test (ELRT) has been shown to be valid. In this paper, we conduct a parametric test procedure. We transform the hypothesis of homogeneity to one on the equality of mean parameters of the exponential family of distributions. Then, we propose a modified Wald test and give its asymptotic power. We further apply it to the semicontinuous case when there is an excess of zeros in the sample. The simulation studies show that the new test controls the type-I error better than ELRT while retaining competitive power. Benefiting from the simple closed form of the test statistic, the computational cost is small. We also use a real data example to illustrate the effectiveness of our test.

Keywords: density ratio model; homogeneity test; multiple semicontinous data; exponential family of distributions (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/17/3789/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/17/3789/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:17:p:3789-:d:1232327

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().