T-Statistics for Weighted Means in Credit Risk Modelling

We present a generalization of the two sample t-test for the equality of means to the case where the sample values have unequal weights. This is a natural situation in financial risk modelling where some samples are considered more reliable than others in predicting a common mean. We describe pooled and unpooled weighted t-tests, and show with an example of real credit data that using the standard unweighted t-test can lead to the wrong statistical conclusion

MoreLess

Year of publication:	[2008]
Authors:	Kercheval, Alec N.
Other Persons:	Goldberg, Lisa R. (contributor) ; Lee, Kiseop (contributor)
Publisher:	[2008]: [S.l.] : SSRN

Extent:	1 Online-Ressource (22 p)
Type of publication:	Book / Working Paper
Notes:	In: Journal of Risk Finance, Forthcoming
Classification:	C22 - Time-Series Models ; C51 - Model Construction and Estimation ; C52 - Model Evaluation and Testing
Source:	ECONIS - Online Catalogue of the ZBW

Persistent link: https://www.econbiz.de/10012774407