Summary
Statistical reference datasets from the National Institute of Standards and Technology were used to evaluate the accuracy and precision of two web-based statistical packages, WebStat (found at http://www.stat.sc.edu/webstat/) and Statlets (found at http://www.statlets.com/statletsindex.htm). This evaluation revealed that both packages performed reasonably well in the analysis of lower difficulty datasets, with decreasing accuracy as difficulty increases. The decrease in accuracy for datasets of higher difficulty can often be contributed to the dataset storage format (which seems to be single precision in Statlets and is double precision in WebStat). For most statistical analysis needs, the level of accuracy found in Web-Stat and Statlets would likely be unsatisfactory. Limitations of the packages are discussed and comparisons of accuracy with commercially available statistical packages are presented. WebStat and Statlets are user-friendly packages that are amenable to use as teaching tools. Thus we advise that the statistics packages we evaluated be restricted to use in teaching situations. They should not be used for the analysis of datasets with higher difficulty levels.
Similar content being viewed by others
References
Gentle, J. E. (1998), Numerical linear algebra for applications in statistics, Springer, New York, NY.
Kötter, T. (1997a), “Interactive interfaces of statistical software for the internet”, in Advances in Statistical Software 6, W. Bandilla, and F. Faulbaum, eds., Stuttgart: Lucius & Lucius, 153–158.
Kötter, T. (1997b), “Implementation of networked applications for statistical computing”, Bulletin of the International Statistical Institute, 51st Session Istanbul 1997, Proceedings Book 2, 47–50.
McCullough, B. D. (1998), “Assessing reliability of statistical software: Part I”, The American Statistician, 52, 358–366.
McCullough, B. D. (1999a), “Assessing reliability of statistical software: Part II”, The American Statistician, 53, 149–159.
McCullough, B. D. (1999b), “The reliability of econometric software: Eviews, LIMDEP, SHAZAM, and TSP”, Journal of Applied Econometrics, 14, 191–202.
McCullough, B. D. (1999c), “Experience with the StRD: application and interpretation”, Computing Science and Statistics, 31, 16–21.
McCullough, B. D. (2000), “The accuracy of Mathematica 4 as a statistical package”, Computational Statistics, 15, 279–299.
McCullough, B. D., and Wilson, B. (1999), “On the accuracy of statistical procedures in Microsoft Excel 97”, Computational Statistics & Data Analysis, 31(1), 27–37.
McCullough, B. D., and Vinod, H. D. (1999), “The numerical reliability of econometric software”, Journal of Economic Literature, 37, 633–665.
Müller, M. (1998), “Computer-assisted statistics teaching in network environments”, in COMPSTAT — Proceedings in Computational Statistics, 13thSymposium held in Bristol, Great Britain, 1998, R. Payne, and P. Green, eds., Heidelberg: Physica-Verlag, 77–88.
Rogers, J., Filliben, J., Gill, L., Guthrie, W., Lagergren, E., and Vangel, M. (1998), “StRD: statistical reference datasets for assessing the numerical accuracy of statistical software,” NIST TN# 1396, National Institute of Standards and Technology, USA.
Sawitzki, G. (1994a), “Testing numerical reliability of data analysis systems”, Computational Statistics & Data Analysis, 18, 269–286.
Sawitzki, G. (1994b), “Report on the reliability of data analysis systems”, Computational Statistics & Data Analysis, 18, 289–301.
Schmelzer, S., Kötter, T., Klinke, S., and Härdle, W. (1996), “A new generation of a statistical computing environment on the net”, in COMPSTAT — Proceedings in Computational Statistics, 12thSymposium held in Barcelona, Spain, 1,996, A. Prat, ed., Heidelberg: Physica-Verlag, 135–148.
Simon, S. D., and Lesage, J. P. (1989), “Assessing the accuracy of ANOVA calculations in statistical software”, Computational Statistics & Data Analysis, 8, 325–332.
Vinod, H. D. (2000), “Review of Gauss for Windows, including its numerical accuracy”, Journal of Applied Econometrics, 15, 211–220.
West, R. W. (1997), “Statistical applications for the World Wide Web”, Bulletin of the International Statistical Institute, 51st Session Istanbul 1997, Proceedings Book 2, 7–10.
West, R. W., and Ogden, R. T. (1997), “Statistical analysis with WebStat, a Java applet for the World Wide Web”, Journal of Statistical Software, 2 (3), http://www.istatsoft.org/v02/i03.
West, R. W., and Ogden, R. T. (1998), “WebStat: An environment for statistical analysis on the World Wide Web”, Computing Science and Statistics, 29(1), 307–310.
West, R. W., Ogden, R. T., and Rossini, A. J. (1998), “Statistical tools on the World Wide Web”, The American Statistician, 52(3), 257–262.
Acknowledgements
The authors would like to thank the Co-Editor and an anonymous Associate Editor of Computational Statistics for their helpful comments. Thanks are also due to Webster West for his comments regarding WebStat.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kitchen, A.M., Drachenberg, R. & Symanzik, J. Assessing the reliability of web-based statistical software. Computational Statistics 18, 107–122 (2003). https://doi.org/10.1007/s001800300134
Published:
Issue Date:
DOI: https://doi.org/10.1007/s001800300134