regression

logisticScore

Description

The logisticScore action creates a table on the server that contains results from scoring observations by using a fitted model.

regression.logisticScore <result=results> <status=rc> / alpha=double, casOut={<casouttable>}, cBar="string", copyVars="ALL" | "ALL_NUMERIC" | {"variable-name-1" <, "variable-name-2", ...>}, difChisq="string", difDev="string", display={<displayTables>}, fitData=TRUE | FALSE, h="string", into="string", intoCutpt=double, ipred="string", lcl="string", lclm="string", level="string", obscat=TRUE | FALSE, outputTables={<outputTables>}, post="string", pred="string", predprobs=TRUE | FALSE, resChi="string", resDev="string", resLik="string", resRaw="string", restore={<castable>}, resWork="string", role="string", stdResChi="string", stdResDev="string", stdXBeta="string", table={<castable>}, ucl="string", uclm="string", xBeta="string";
Settings
ParameterDescription
alphaspecifies the significance level to use for the construction of confidence intervals. By default, this is set to the global significance level.
casOutspecifies the settings for an output table.
cBarnames the confidence interval displacement, which measures the overall change in the global regression estimates that can be attributed to deleting the individual observation.
copyVarsspecifies a list of one or more variables to be copied from the input table to the output table. You can alternatively specify the value ALL, or ALL_NUMERIC, which respectively copies all variables, or all numeric variables from the input table to the output table.
difChisqnames the change in the Pearson chi-square statistic that can be attributed to deleting the individual observation.
difDevnames the change in the deviance that can be attributed to deleting the individual observation.
displayspecifies a list of results tables to send to the client for display.
fitDatawhen set to True, specifies that the data to be scored were also used to fit the model.
hnames the leverage of the observation.
intonames the predicted response level.
intoCutptspecifies the predicted event probability that determines the predicted binary response level.
iprednames the individual predicted value for a cumulative link. If you do not specify any output statistics, then by default the predicted value is named _IPRED_.
lclnames the lower bound of a confidence interval for the linear predictor.
lclmnames the lower bound of a confidence interval for the mean.
levelnames the ordered response level.
obscatwhen set to True, computes multinomial output statistics at the observed response level.
outputTableslists the names of results tables to save as CAS tables on the server.
postnames the posterior predicted value.
prednames the predicted value. If you do not specify any output statistics, then by default the predicted value is named _PRED_.
predprobswhen set to True, displays requested multinomial predicted probabilities as separate variables.
resChinames the Pearson chi-square residual.
resDevnames the deviance residual.
resLiknames the likelihood residual (likelihood displacement).
resRawnames the raw residual.
restorerestores regression models from a binary large object (BLOB).
resWorknames the working residual.
roleidentifies the training, validation, and test roles for the observations.
stdResChinames the standardized Pearson chi-square residual.
stdResDevnames the standardized deviance residual.
stdXBetanames the standard error of the linear predictor.
tablespecifies the input data table.
uclnames the upper bound of a confidence interval for the linear predictor.
uclmnames the upper bound of a confidence interval for the mean.
xBetanames the linear predictor.

Examples

FAQ

What is the primary purpose of the logisticScore action?
What are the mandatory input parameters for the logisticScore action?
How do I specify the output table for the scoring results?
How can I include the original variables from the input table in my output score table?
What is the purpose of the 'fitData' parameter?
How can I obtain predicted probabilities and their confidence intervals?
What is the difference between the 'pred' and 'ipred' parameters?