We have developed computer code that performs simulations to estimate
the coverages of confidence intervals on treatment means given a
predictor sort allocation of specimens (blocking via a concomitant
variable). This simulation is based upon research reported in
Verrill (1999), "When Good
Confidence Intervals Go Bad: Predictor Sort Experiments and
ANOVA," The American Statistician, 53(1), 38-42
Kretschmann (2017a), "A Reminder about
Potentially Serious Problems with a Type of Blocked ANOVA
Analysis," USDA Forest Products Laboratory research paper FPL-RP-683
The simulation can be run over the Web at http://www1.fpl.fs.fed.us/psconf.html. The material below provides links to a FORTRAN version of this computer code.
Disclaimer of Warranties
The FORTRAN source for this code comes in seven files:
The program also depends upon DCDFLIB. DCDFLIB is a public domain library of "routines for cumulative distribution functions, their inverses, and their parameters." It was produced by Barry Brown, James Lovato, and Kathy Russell of the Department of Biomathematics, M.D. Anderson Cancer Center, The University of Texas. DCDFLIB can be found at https://biostatistics.mdanderson.org/SoftwareDownload/SingleSoftware.aspx?Software_id=21 .