Glossary of Terms

Alias: An effect in a fractionally replicated design that "looks like" or cannot be distinguished from another effect.
Alpha (?): The size of the type I error, or the probability of rejecting a hypothesis when true.
Autocorrelation Coefficient: A correlation between measures within the same sample in the order taken.

Beta (?): The size of the type II error, or the probability of accepting a hypothesis when some alternative hypothesis is true.

Canonical Form: A form of second-degree response surface equation that allows determination of the type of surface.
Completely Randomized Design: A design in which all treatments are assigned to the experimental units in a completely random manner.
Confidence Limits: Two values between which a parameter is said to lie with a specified degree of confidence.
Confounding: An experimental arrangement in which certain effects cannot be distinguished from others. One such effect is usually blocks.
Consistent Estimator: An estimator of a parameter whose values comes closer to the parameter as the sample size is increased.
Contrast: A linear combination of treatment totals or averages in which the sum of the coefficient is zero.
Correlation Coefficient (Pearson r): The square root of the proportion of total variation accounted for by simple linear regression, with the sign of the slope of the least squares line.
Correlation Index R: the square root of the proportion of total variation accounted for by the regression equation of the degree being fitted to the data.
Covariance Analysis: A...

< Previous Excerpt Next Excerpt >

Fundamental Concepts in the Design of Experiments, Fifth Edition