Selected Papers Produced by the FPL Statistics Group

Eventually, this page will contain descriptions of and links to "classic" and recent papers produced by the FPL Statistics Group. Currently, it only includes references to Steve Verrill's predictor sort work, to Steve Verrill's power work, and to Bill Simpson and Steve Verrill's Drying Schedule work. (A complete list of Steve Verrill's papers can be found here.)


The predictor sort work

The predictor sort work helps an experimenter determine appropriate sample sizes, allocate specimens, and analyze results in the case in which a response predictor is used to sort the specimens prior to treatment.

(The sample size program can also be used to determine appropriate sample sizes in a standard [non-predictor sort] experiment simply by setting the correlation value to 0. Here is a link to the web version of the program.)

For example, one might be interested in the effects of three fire retardants on the mean bending strength of a sample of boards. One could simply randomly assign the boards to the three treatments. However, a researcher could significantly reduce sample sizes (or increase power) by non-destructively measuring the modulus of elasticity (MOE) of the boards prior to treatment. The researcher could then perform a randomized block experiment in which the blocks were composed of boards with similar MOEs. Since MOE is well correlated with bending strength, the experiment would be more sensitive to the differences that are due to the fire retardant treatments. Knowing the correlation between MOE and bending strength, one could quantify this increase in experimental sensitivity and identify an appropriate sample size.

The work consists of nine papers and related computer programs:


Power And Sample Size Calculations

We have written a WWW program, power, that enables a user to perform power and sample size calculations for balanced ANOVAs. The methods used in this program are documented in Verrill (2001), "Rolling Your Own: Linear Model Hypothesis Testing and Power Calculations via the Singular Value Decomposition," Statistical Computing and Graphics Newsletter, 12, No. 1, 15-18. This paper is also available here in both LaTeX and postscript form.

The Drying Schedule work

The Drying Schedule work helps a kiln operator choose an appropriate drying schedule for a species. Given the specific gravity of the species, the Drying Schedule computer program suggests appropriate drying schedules. The program only takes into account the specific gravity and the relative frequency with which different drying schedules are used. It ranks 40 schedules according to the relative likelihood that they would be appropriate. It reports a list of the 40 schedules along with their associated relative likelihoods. The schedule that the program recommends most highly is given a relative likelihood of 1. The other relative likelihoods range from 0 to 1. If a schedule's relative likelihood is low, it is not likely to be an appropriate schedule for the species in question. The work that led to the Drying Schedule program appears in two papers:

The Drying Schedule program implements the techniques described in the second paper. FORTRAN source code is available under a GNU copyright. Binary code is available for the DOS and Solaris 2.x operating systems. The Drying Schedule program may also be run over the Web.


For further information, please contact Steve Verrill at sverrill@fs.fed.us or 608-231-9375.
Last modified on 1/12/17.