- AoshimaM., HyakutakeH., and DudewiczE.J. (1996). An asymptotically optimal fixed-width confidence interval for the difference of two normal means. Sequential Analysis, 15, 61–70.
- BatherJ. (1996). A conversation with Herman Chernoff. Statistical Science, 11, 335–350.
- DudewiczE.J. and TanejaB.K. (1993). Exact solutions to the Behrens-Fisher problem. Chapter 27 in Multiple Comparisons, Selection, and Applications in Biometry, A Festschrift in Honor of Charles W. Dunnett, edited by HoppeF.M., Marcel Dekker, Inc., New York, 447–477.
- DudewiczE.J. and AhmedS.U. (1999). New exact and asymptotically optimal heteroscedastic statistical procedures and tables, II. American Journal of Mathematical and Management Sciences, 19, to appear.
- Additional References. We here list some recent references (which are indicative, rather than exhaustive), with some comments on their results. See the references cited in these papers for more of the literature.
- DeyiB.A., KosinskiA.S., and SnapinnS.M. (1998). Power considerations when a continuous outcome variable is dichotomized. Journal of Biopharmaceutical Statistics, 8, 337–352. This paper shows the current interest in the problem in biostatistical applications. Since biostatistical trials can be (and often are) run in stages, a two-stage procedure would be relatively easy to apply in that setting.
- MehrotraD.V. (1997). Improving the Brown-Forsythe solution to the generalized Behrens-Fisher problem. Communications in Statistics-Simulation, 26, 1139–1145. There are many papers continuing to study the approximate procedures; about none of them seem to be aware of the exact solutions (else, why would they bother?). Approximations may still be of interest when two stages is not a possibility, but that case is not as common as needed to justify the lack of consideration in these “approximation” papers. Also, one-stage versions of two-stage procedures are another line of research some are pursuing with some success. Such work for the procedure of the present paper we have presented is an open problem.
- Choose new content alerts to be informed about new research of interest to you
- Easy remote access to your institution's subscriptions on any device, from any location
- Save your searches and schedule alerts to send you new results
- Export your search results into a .csv file to support your research