RainbowStats™ · Regression commands

DISCOVER_MODEL

Run the existing genetic-search, forest and OLS pipeline.

Syntax

DISCOVER_MODEL(list[,namedOptions...])

Returned object

DiscoverModelOperator

Example

m=DISCOVER_MODEL(LIST(LOGDIFF(INDPRO),LOGDIFF(PAYEMS),LOGDIFF(CPIAUCSL)))
EXTRACT(m,"slideshow")

Interpretation and limitations

The first argument is LIST(Y,X1,...). Optional settings retain the existing named-argument parser: ARG(name,value), ARG_LIST, or NAME:value. Settings are validated by the existing model class. Inspect out-of-sample behavior and avoid interpreting predictive importance as causal evidence. The dispatcher returns the DiscoverModelOperator itself, so its model, forest, genetic and regression extracts remain available.

Available extracts

Save the command result in a variable, then use EXTRACT(result, "key"). Availability can depend on the input form and fitted model.

genetic
genetic_model
search
forest
random_forest
randomforest
regression
ols
model
data
selected_data
summary
genetic_summary
selected
variables
candidates
lags
test_chart
test_predicted
test_residuals
test_rmse
test_r_squared
benchmark
equation
rules
regimes
importance
forest_summary
forest_fitted
forest_residuals
oob
regression_slideshow
regression_results
coefficients
beta
betase
residuals
fitted
actual_vs_fitted
autocorrelation
slideshow

In indexed patterns such as beta:n, replace n with the required index.

Learn more

Detailed guide and examples