[
https://issues.apache.org/jira/browse/MATH-411?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12907051#action_12907051
]
Phil Steitz commented on MATH-411:
----------------------------------
Fixed in r993574. Modified multiple regression newSample methods to ensure
that by default in all cases, regression models are estimated with intercept
terms. Prior to the fix for this issue, newXSampleData(double[][]),
newSampleData(double[], double[][]) and newSampleData(double[], double[][],
double[][]) all required columns of "1's to be inserted into the x[][] arrays
to create a model with an intercept term;while newSampleData(double[], int,
int) created a model including an intercept term without requiring the unitary
column. All methods have been changed to eliminate the need for users to add
unitary columns to specify regression models.
Leaving open until MATH-409 is resolved.
> Multiple Regression newSampleData methods inconsistently create / omit
> intercepts
> ---------------------------------------------------------------------------------
>
> Key: MATH-411
> URL: https://issues.apache.org/jira/browse/MATH-411
> Project: Commons Math
> Issue Type: Bug
> Affects Versions: 2.0, 2.1
> Reporter: Phil Steitz
> Fix For: 2.2
>
>
> The newSampleData(double[], nrows, ncols) method used in the unit tests adds
> a unitary column to the design matrix, resulting in an intercept term being
> estimated among the regression parameters. The other newSampleData methods
> do not do this, forcing users to add the column of "1"s to estimate models
> with intercept. Behavior should be consistent and users should not have to
> add the column.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
