Six sigma


GenStat has wide range of facilities to support the six-sigma approach to quality improvement. It can display many different types of control chart.


SPCCHART
plots c or u charts representing numbers of defective items

SPCUSUM
prints CUSUM tables for controlling a process mean

SPEWMA
plots exponentially weighted moving-average control charts

SPPCHART
plots p or np charts for binomial testing for defective items

SPSHEWHART
plots control charts for mean and standard deviation or range


It can test for Normality, display Pareto charts and calculate capability statistics.


NORMTEST
performs tests of univariate and/or multivariate normality

SPCAPABILITY
calculates capability statistics

TABSORT
sorts tables to put margins are in ascending or descending order for display as a Pareto chart


It also provides full statistical backup for wider-ranging investigations. The list below highlights some of the commands that may be useful.


AFRESPONSESURFACE
uses the BLKL algorithm to construct response-surface designs

AGBOXBEHNKEN
generates Box-Behnken designs

AGCENTRALCOMPOSITE
generates central composite designs

AGDESIGN
selects from a set of standard designs including factorials with interactions confounded with blocks

AGFRACTION
generates fractional factorial designs

AGMAINEFFECT
generates designs to estimate main effects of two-level factors (Plackett-Burman designs)

ANOVA
analyses y-variates by analysis of variance according to the model defined by earlier BLOCKSTRUCTURE, COVARIATE, and TREATMENTSTRUCTURE statements

AGRAPH
plots one- or two-way tables of means from ANOVA

APLOT
plots residuals from an ANOVA analysis

AMCOMPARISON
performs pairwise multiple comparison tests for ANOVA means

AUNBALANCED
performs analysis of variance for unbalanced designs

FIT
fits a linear, generalized linear, generalized additive, or generalized nonlinear model

FITCURVE
fits a standard nonlinear regression model

FITNONLINEAR
fits a nonlinear regression model or optimizes a function

FKEY
forms design keys for balanced designs with several error terms, allowing for confounded and aliased treatments

REML
fits an unbalanced linear mixed model and estimates variance components

RQUADRATIC
fits a quadratic surface and estimates its stationary point

YTRANSFORM
estimates the parameter lambda from various single-parameter transformations, includling power (Box-Cox), modulus, folded power, Guerrero-Johnson, Aranda-Ordaz and power logit