A MACINTOSH BASIC PROGRAM FOR FITTING LINEAR ADDITIVE-MODELS TO DATA BY WEIGHTED LEAST-SQUARES METHODS, WITH AUTOMATIC ELIMINATION OF REDUNDANT PARAMETERS FROM THE MODEL
H. Tyson, A MACINTOSH BASIC PROGRAM FOR FITTING LINEAR ADDITIVE-MODELS TO DATA BY WEIGHTED LEAST-SQUARES METHODS, WITH AUTOMATIC ELIMINATION OF REDUNDANT PARAMETERS FROM THE MODEL, Computer methods and programs in biomedicine, 39(3-4), 1993, pp. 311-322
A BASIC program for fitting linear additive models to data with weight
ed or unweighted least squares methods and matrix procedures is descri
bed. Written and compiled to run on Macintosh II type machines (68020/
68030/68040) with coprocessor (68881/68882), the program fits the mode
l supplied by the user as an X or design matrix and provides the optio
n of making the model's parameters orthogonal. Predicted values plus r
egression and residual terms are calculated. For the weighted fit, the
significance of the residual term is evaluated and redundant paramete
rs sequentially and automatically removed until a minimum adequate mod
el is achieved. An appropriate design matrix allows weighted fitting o
f models for multiway analyses of variance (e.g. factorial, nested and
split plot), simple or multiple linear or curvilinear regression, com
binations of these in covariance analyses, and genetic analyses (inclu
ding diallel cross analyses). Sums of squares for individual parameter
s and orthogonal comparisons can be calculated by the program.