DIGRES <data>,<name of model>,L
estimates the parameters of a linear or a nonlinear digression model.
Parameter L is optional and gives the first line for the results in
the edit field.
The digression model has to be defined by a MODEL specification typed on
any two consecutive lines in the edit field as follows:
MODEL <name of model>
<Y>=<function 1> OR <Y>=function 2>
<data> may either be defined by the DATA specification in the edit
field or it may be a Survo data file.
The regressand and the regressors are notated by the names given as
labels for the columns in the DATA specification of the data set.
Unidentified words in the model are interpreted as parameters to be
estimated.
Examples:
http://www.survo.fi/demos/index.html#ex119
http://www.survo.fi/demos/index.html#ex120
The DIGRES program module is a limited modification of ESTIMATE.
Permitted numerical algorithms are
METHOD=H Hooke-Jeeves
METHOD=G Direct search in a grid of parameter space
The search values for each parameter A must given as
A=<lower_limit>,<upper_limit>,<step>
This last alternative exists mainly for searching for good
initial values of parameters to be estimated.
Default estimation criterion is OLS but also CRITERION=Lp is avalable.
1 = Estimation of linear and non-linear regression models
S = More information on statistical analysis
Help System (web edition)