Benchmarks
Here are some standard benchmark datasets and models for testing
the accuracy of TSP.
For an updated and expanded set of benchmarks, please see
the current version of this page:
http://www.stanford.edu/~clint/bench
It includes a high accuracy Klein-I FIML benchmark, more
AR(1) benchmarks, many ARIMA models (exact ML), GARCH(1,1),
Probit, Logit, Poisson, Negative Binomial, Ordered Probit.
- Longley, JASA (1967) -- linear regression
- Klein I model
- Grunfeld investment data -- analyzed in Theil (1971)
- grunsur.tsp computes the following:
- OLS
- SUR - Seemingly Unrelated Regressions
- iterated SUR
- (iterated) SUR with cross-equation constraints
- Bartlett pears data -- analyzed by Hildreth and Lu, and by Henshaw
- pears.tsp computes the following:
- OLS
- Durbin-Watson statistic and its exact P-value
- AR(1) conditional ML via grid search (Hildreth-Lu)
- AR(1) conditional ML via full iteration (Cochran-Orcutt)
- AR(1) exact ML via full iteration (Beach-MacKinnon)
Wilkinson's "Statistics Quiz"
National Institutes of Standards and Technology (NIST)
"Statistical Reference Datasets"
NIST StRD web page
Contains many test problems and certified results for univariate
statistics, anova, linear regression, and nonlinear regression.
- Univariate statistics
- Table of results for Sun 4
TSP obtains at least 8 correct digits for mean,
standard deviation, and first order autocorrelation
for 7 data series.
- uni.tsp Code to run 7 series
- ANOVA
- Ordinary Least Squares
- Nonlinear Least Squares
If you have any questions or comments about TSP please send an
email to info@tspintl.com. Comments or questions about this website
should be sent to the webmaster. Lost? Please consult the site map.