Testing the rationality of survey data using the weighted double-bootstrapped method of moments
Article Abstract:
The 90-day US Treasury Bill rate is used to test the rationality of forecasts that apply a distribution-free method of moments estimation to calculate parameters and a weighted double bootstrap method. Two separate forecasts on the 90-day US T-bill rate are assimilated and integrated with the actual T-bill rate. Results indicate that the weighted bootstrap was the best technique, correcting problems on standard errors when the data is subjected to heteroskedasticity and size distortions if asymptotic critical values are used.
Publication Name: Review of Economics and Statistics
Subject: Mathematics
ISSN: 0034-6535
Year: 1996
User Contributions:
Comment about this article or add new information about this topic:
A system of demand equations satisfying effectively global regularity conditions
Article Abstract:
A mathematical parametric representation was created to reflect an indirect utility function by expenditure and two unit cost functions (or price indexes). Empirical application was tested using a sample from Australian data. Results indicate that the model may not need to be globally regular, but it can be limited to be regular over an unbounded region which includes all points in any given data sample and all values of nominal expenditure and prices which produce higher real expenditure values.
Publication Name: Review of Economics and Statistics
Subject: Mathematics
ISSN: 0034-6535
Year: 1996
User Contributions:
Comment about this article or add new information about this topic:
Estimating the correlation in censored probit models
Article Abstract:
Approximations of censored probit models or probit models with selection can result in an approximated correlation between the disturbances approaching -1.0 or +1.0. This holds when a majority of the observations are selected into the sample and the outcomes are not equally distributed. Outcomes of 0 can result in an estimated correlation of -1.0 and outcomes of 1 can result in an estimated correlation of +1.0.
Publication Name: Review of Economics and Statistics
Subject: Mathematics
ISSN: 0034-6535
Year: 1996
User Contributions:
Comment about this article or add new information about this topic:
- Abstracts: Testing the rationality of forecast revisions made by the IMF and the OECD. Political maneuverings as sources of measurement errors in forecasts
- Abstracts: Testing the rationality of forecast revisions made by the IMF and the OECD. part 2 Are 16-month-ahead forecasts useful? A directional analysis of Japanese GDP forecasts
- Abstracts: Report of the treasurer. Analysis of a numerical dynamic programming algorithm applied to economic models
- Abstracts: Firm size and the nature of innovation within industries: the case of process and product R&D. The objective function of simulation estimators near the boundary of the unstable region of the parameter space
- Abstracts: Testing the convergence hypothesis: a comment. Employment effects of immigration to Germany: an analysis based on local labor markets