Snorke ([info]snorke) rakstīja,
@ 2010-11-20 16:43:00

Previous Entry  Add to memories!  Tell a Friend!  Next Entry
es: The first step would be evaluation of correlation between predictors (deletion of 1 of those predictors who are significantly correlated)


viņš: This not correct!!!! Who told you that you must exclude by a model one predictor due the fact that is highly correlated with another? It is not correct at all!


(Lasīt komentārus) - (Ierakstīt jaunu komentāru)


[info]zum
2008-11-20 18:18 (saite)
Staistika varbūt Tev ir baisa. Bet mēs, kas mācījušies tos murgus nesenā pagatnē, gan tā neuzskatām.

(Atbildēt uz šo) (Iepriekšējais)


(Lasīt komentārus) -

Neesi iežurnalējies. Iežurnalēties?