Pitfalls of estimating the marginal likelihood using the modified harmonic mean

Publication Type:
Journal Article
Economics Letters, 2015, 131 pp. 29 - 33
Issue Date:
Full metadata record
Files in This Item:
Filename Description Size
1-s2.0-S0165176515001378-main.pdfPublished Version369.49 kB
Adobe PDF
© 2015 Elsevier B.V. The modified harmonic mean is widely used for estimating the marginal likelihood. We investigate the empirical performance of two versions of this estimator: one based on the observed-data likelihood and the other on the complete-data likelihood. Through an empirical example using US and UK inflation, we show that the version based on the complete-data likelihood has a substantial bias and tends to select the wrong model, whereas the version based on the observed-data likelihood works well.
Please use this identifier to cite or link to this item: