Stores results from a locally weighted regression (loess) with groups model fitted to data with groups (D.B. Baird).
Options
RMETHOD = string token |
Type of residuals to form if parameter RESIDUALS is set (deviance, simple); default devi |
SAVE = identifier |
Save structure from the analysis of a loess with groups model by RLOESSGROUPS; default uses the model fitted most recently by RLOESSGROUPS |
Parameters
RESIDUALS = variates |
Residuals, as specified by the RMETHOD option |
FITTEDVALUES = variates |
Fitted values |
LEVERAGES = variate |
Leverages of the units |
ESTIMATES = variates |
Estimates of parameters |
SE = variates |
Standard errors of the estimates |
VCOVARIANCE = symmetric matrix |
Variance-covariance matrix of the estimates |
CORRELATIONS = symmetric matrix |
Correlation matrix of the estimates |
DEVIANCE = scalars |
Residual ss or deviance |
DF = scalar |
Residual degrees of freedom |
ACCUMULATED = pointer |
Saves the accumulated analysis-of-variance (or deviance) table as a pointer with a variate or text for each column (source, d.f. etc) |
Description
RKLOESSGROUPS allows you save information from an analysis RLOESSGROUPS, which fits a locally weighted regression (loess) analysis with groups. You do not need to declare the data structures to save the information in advance; Genstat will declare them automatically to be of the correct type and length.
The RESIDUALS,FITTEDVALUES andLEVERAGES parameters save the standardized residuals, fitted values and leverages. TheRMETHOD option controls the type of residuals that are formed.
The ESTIMATES andSE parameters save the parameter estimates and their standard errors.RKLOESSGROUPS puts them into variates, in the same order as in the display produced by thePRINT option RLOESSGROUPS.
The VCOVARIANCE parameter saves the variance-covariance matrix of the estimates. These are formed by multiplying the inverse matrix by the relevant variance estimate based on the estimated dispersion, or on the dispersion that you have supplied in the original MODEL statement. The CORRELATIONS parameter saves the correlations matrix of the estimates.
The DEVIANCE parameter lets you save the residual sum of squares, or the deviancefor distributions other than Normal. TheDF parameter saves the residual degrees of freedom.
The ACCUMULATED parameter saves the accumulated analysis-of-variance (or deviance) table. The accumulated table is saved as a pointer with a variate or text for each of its columns (source, d.f. etc). Note that the suffixes ofACCUMULATED for the last 4 columns in the pointer depend on whether it is an analysis of variance ('s.s.', 'm.s.', 'v.r.', 'F pr.') or an analysis of deviance ('deviance', 'mean dev.', 'dev. r.', 'approx F pr.').
Options:
RMETHOD,SAVE.
Parameters:RESIDUALS,FITTEDVALUES,LEVERAGES,ESTIMATES,SE,VCOVARIANCE,CORRELATIONS,DEVIANCE,DF,ACCUMULATED.
See also
Directive: RKEEP.
Procedures: RLOESSGROUPS, RDLOESSGROUPS.
Commands for: Regression analysis.
Example
CAPTION 'RKLOESSGROUPS example',\
'Yield of sugar beet vs soil phosphate in 4 years'; STYLE=major,plain
FACTOR [LEVELS=4; VALUES=16(1...4)] Year
OPEN '%EXAMPLES%/GuidePart2/beet.dat'; CHANNEL=2
READ [PRINT=*; CHANNEL=2] Beetwt,%sugar,SoilP
CLOSE 2
CALCULATE Sugar = Beetwt * %sugar / 100
MODEL Sugar
RLOESSGROUPS SoilP; GROUP=Year; SMOOTH=2
RKLOESSGROUPS RESIDUALS=res; FITTEDVALUES=fit; LEVERAGE=lev; ESTIMATES=est; SE=se
PRINT Year,Sugar,SoilP,res,fit,lev; DEC=0,5(*)
PRINT est,se