Fitting Weibull and Lognormal Distributions to Medium-Density Fiberboard Fiber and Wood Particle Length

John Z. Lu, Charles J. Monlezun, Qinglin Wu, Quang V. Cao

Abstract


Fiber lengths were analyzed for random samples of medium-density fiberboard (MDF) fibers and wood particles taken from eleven different populations. For six of the samples, the lognormal distribution fit the data, while the Weibull distribution did not. For three of the samples, the Weibull fit the data, while the lognormal did not. For two of the samples, both the lognormal and Weibull fit the data. Conclusions were based on hypothesis tests imposing a bound of 0.05 on the probability of making a Type I error for each test. Tests were based on large sample 95% nonparametric simultaneous confidence bands for the underlying cumulative distribution functions of the data.

Keywords


Goodness of fit tests;MDF fiber;maximum likelihood estimation;non-parametric confidence bands;probability plots;statistical analyses

Full Text:

PDF

Refbacks

  • There are currently no refbacks.