Puts results from a regression, generalized linear or nonlinear model into a spreadsheet (R.W. Payne).
Options
DISPERSION = scalar |
Dispersion parameter to be used as estimate for variability in s.e.s; default as set in MODEL |
|---|---|
RMETHOD = string token |
Type of residual to use (deviance, Pearson, simple, deletion); default * i.e. as set in MODEL |
DMETHOD = string token |
basis of estimate of dispersion, if not fixed by DISPERSION option (deviance, Pearson); default * i.e. as set in MODEL |
SPREADSHEET = string tokens |
Which spreadsheets to form (summary, estimates, fittedvalues, accumulated); default summary, estimates, fittedvalues |
SPESTIMATES = string tokens |
What to include in the estimates spreadsheet (estimates, se, testimates, prestimates); default esti, se, test, pres |
SPFITTEDVALUES = string tokens |
What to include in the fitted-values spreadsheet (y, fittedvalues, residuals, leverages, sefittedvalues); default y, fitt, resi, leve |
SAVE = regression save structure |
Specifies which analysis to save; default * i.e. most recent regression |
Parameters
Y = variates |
Y-variate of the analysis to be saved |
|---|---|
RESIDUALS = variates |
Identifier of variate to save the residuals from each analysis; default residuals |
FITTEDVALUES = variates |
Identifier of variate to save the fitted values from each analysis; default fittedvalues |
LEVERAGES = variates |
Identifier of variate to save the leverages from each analysis; default leverages |
ESTIMATES = variates |
Identifier of variate to save the estimates from each analysis; default estimates |
SE = variates |
Identifier of variate to save s.e.’s of the estimates from each analysis; default se |
TESTIMATES = variates |
Identifier of variate to save the t-statistics of the estimates from each analysis; default t_statistics |
PRESTIMATES = variates |
Identifier of variate to save the t-probabilities of the estimates from each analysis; default t_probabilities |
SEFITTEDVALUES = variates |
Identifier of variate to save s.e.’s of the fitted values from each analysis; default sefittedvalues |
SUMMARY = pointers |
Identifier of pointer to save the summary analysis-of-variance (or deviance) from each analysis; default summary |
ACCUMULATED = pointers |
Identifier of pointer to save the accumulated analysis-of-variance (or deviance) from each analysis; default accumulated |
OUTFILENAME = texts |
Name of Genstat workbook file (.gwb) or Excel (.xls or .xlsx) file to create |
Description
RSPREADSHEET puts results from a regression, generalized linear or nonlinear model into a spreadsheet. By default the results are from the most recent regression, but you use the SAVE option to specify the save structure (from a MODEL statement) from some other analysis. You can use the Y parameter to indicate the y-variate, if the SAVE structure contains results from more than one.
The SPREADSHEET option specifies which pages of the spreadsheet to form, with settings:
summary |
summary analysis of variance (or deviance for a generalized linear model), |
|---|---|
estimates |
estimates with the standard errors etc., |
fittedvalues |
fitted values, y-variate, residuals etc., and |
accumulated |
summary analysis of variance (or deviance for a generalized linear model). |
By default, SPREADSHEET=summ,esti,fitt.
The SPESTIMATES option specifies which columns to include in the estimates spreadsheet, with settings:
estimates |
estimates, |
|---|---|
se |
standard errors of estimates, |
testimates |
t-statistics of of estimates, and |
prestimates |
t-probabilities of estimates. |
By default they are all included.
The SPFITTEDVALUES option specifies which columns to include in the estimates spreadsheet, with settings:
y |
y-variate, |
|---|---|
fittedvalues |
fitted values, |
residuals |
residuals, |
leverages |
leverages, and |
sefittedvalues |
standard errors of fitted values. |
By default SPFITTEDVALUES=y,fitt,resi,leve.
To help avoid clashes between the columns of the spreadsheets if you want to save results from more than one analysis, the parameters RESIDUALS, FITTEDVALUES, LEVERAGES, ESTIMATES, SE, TESTIMATES, PRESTIMATES, SEFITTEDVALUES, SUMMARY, ACCUMULATED allow you to specify identifiers for the columns (or sets of columns) that will store the corresponding results in the current spreadsheets. Their defaults are mainly the same as the parameter names, but in lower-case letters. The exceptions are that TESTIMATES and PRESTIMATES have defaults t_statistics and t_probabilities, respectively.
You can save the data in either a Genstat workbook (.gwb) or an Excel spreadsheet (.xls or .xlsx), by setting the OUTFILENAME option to the name of the file to create. If the name is specified without a suffix, '.gwb' is added (so that a Genstat workbook is saved). If OUTFILENAME is not specified, the data are put into a spreadsheet opened inside Genstat.
Options: DISPERSION, RMETHOD, DMETHOD, SPREADSHEET, SPESTIMATES, SPFITTEDVALUES, SAVE.
Parameters: Y, RESIDUALS, FITTEDVALUES, LEVERAGES, ESTIMATES, SE, TESTIMATES, PRESTIMATES, SEFITTEDVALUES, SUMMARY, ACCUMULATED, OUTFILENAME.
Action with RESTRICT
If the Y variate is restricted, that restriction will carry over into the fitted-values spreadsheet.
See also
Directive: SPLOAD.
Procedures: ADSPREADSHEET, ASPREADSHEET, AUSPREADSHEET, FSPREADSHEET, VSPREADSHEET.
Commands for: Regression analysis.
Example
CAPTION 'RSPREADSHEET example',\
!t('Model atmospheric pressure on boiling point',\
'(data from Atkinson, 1985, Plots, Transformations & Regression).');\
STYLE=meta,plain
VARIATE [NVALUES=17] Boil,Pressure
READ Boil,Pressure
194.50 20.79 194.25 20.79 197.90 22.40 198.43 22.67 199.45 23.15
199.95 23.35 200.93 23.89 201.15 23.99 201.35 24.02 201.30 24.105
203.55 25.14 204.60 26.57 209.47 28.49 208.57 27.760 210.72 29.040
211.95 29.879 212.18 30.064 :
CALCULATE LogPressure = 100*LOG10(Pressure)
MODEL LogPressure
FIT [PRINT=summary,accumulated,estimates,fittedvalues] Boil
RSPREADSHEET