This study examines the small-sample properties of some commonly used tests of equal forecast accuracy. The paper considers the size and power of dierent tests and the performance of dierent heteroscedasticity and autocorrelation-consistent (HAC) variance estimators. Monte Carlo experiments show tha
Small sample properties of quarterly forecast errors
โ Scribed by S. Sankaran
- Publisher
- John Wiley and Sons
- Year
- 1987
- Tongue
- English
- Weight
- 486 KB
- Volume
- 6
- Category
- Article
- ISSN
- 0277-6693
No coin nor oath required. For personal study only.
๐ SIMILAR VOLUMES
Using Monte Carlo simulations we study the small sample performance of the traditional TSLS, the LIML and four new jackknife IV estimators when the instruments are weak. We ยฎnd that the new estimators and LIML have a smaller bias but a larger variance than the TSLS. In terms of root mean square erro
In this paper, we extend results from the finance literature that explores small sample bias, due to persistent variables, in tests of present value asset pricing models. Using a Monte Carlo simulation approach, we investigate the finite sample behaviour of standard tests of the expectations hypothe
For the analysis of combinations of 2 x 2 non-contingency tablea 88 obtuined from density followup studiea (relating a number of evente to a number of person-years of follow-up) an analogue of theMante1-Haenszel test for 2 ~2 contingency tables is widely u d . In this paper the small sample properti
The paper deeh with the effects of incorrectly omitted regreesor variables in a parametric proportional hazard regremion model. By studying condition8 for equality between the eetirnetorn of oorrect end incorrect models i t is demonstrated analytically that euoh canes are not to be expected in pract