Comparison of Exclusion Values for Lumber Strength

Authors

  • W. G. Warren

Keywords:

statistical analysis, models

Abstract

There exists a temptation to utilize the distribution-free methods of ASTM D2915-70T for the comparison of the strengths of lumber populations, a use outside the intent of the standard. It is shown that the precision of such procedure is highly dependent on the form of the parent distribution of strength. Since this form is in general unknown, the confidence to be ascribed to inferences concerning near-minimum values of two lumber populations is also unknown and may well be inadequate.

References

Blom, G. 1958. Statistical estimates and transformed beta-variables. J. Wiley and Sons, New York.nGupta, S. S. 1960. Order statistics from the gamma distribution. Technometrics 2:243-262.nHabermann, H. 1973. Tolerance intervals. I. Simulation studies of non-parametric tolerance intervals. Presented at meeting of Division 5, IUFRO, South Africa.nHanson, D. L., and L. H. Koopmans. 1964. Tolerance limits for hazard rates. Ann. Math. Stat. 35:1561-1570.nHarter, H. L. 1960. Tables of range and studentized range. Ann. Math. Stat. 31:1122-1147.nJennett, W. J., and B. L. Welch. 1939. The control of proportion defective as judged by a single quality characteristic varying on a continuous scale. J. Roy. Stat. Suppl. 6:80-88.nOwen, D. B. 1962. Handbook of statistical tables. Addison-Wesley, Reading, Mass.nSiegel, S. 1956. Non-parametric statistics for the behavioral sciences. McGraw Hill, New York.nWhite, J. S. 1967. The moments of log-Weibull order statistics. General Motors Corporation, Res. Publ. GMR-717, Warren, Mich.n

Downloads

Published

2007-06-05

Issue

Section

Research Contributions