# [R] what is the difference between using function predict() and coef() in prediction

David Winsemius dwinsemius at comcast.net
Sat Dec 10 19:44:57 CET 2011

```On Dec 10, 2011, at 11:48 AM, tony333 wrote:

>
> X8 = c(0.42808332,  0.14058333,  0.30558333,  0.09558333,  0.01808333,
> -0.09191666, -0.11441666, -0.12941666,  0.13808333, -0.31691666,
> 0.25308333
> ,-0.20941666 ,0.02808333, -0.04441667, -0.43691666)
>
> xy.lm =  lm(Y~X8)
> z = predict(xy.lm,list(X8=X8))
> sz = coef(xy.lm)+(coef(xy.lm))*X8
> is the same result in this step
> but when use the prediction as
> T8=c(-0.05691667, -0.09441666 , 0.31308333 ,-0.59941665 ,-0.33941666
> ,-0.64441665,-0.55691665 ,-0.01191667  ,0.22558333, -0.30691666  ,
> 0.97808331
> , 0.49808332,-0.30941666  ,0.41808332 , 0.42308332)
>
> zz = predict(xy.lm,list(T8=T8))

The first "T8" should be..^^ .... "X8"

> zz = predict(xy.lm,data.frame(X8=T8))
> ss = coef(xy.lm)+(coef(xy.lm))*T8

> identical(unname(zz), ss)
 TRUE

> ss = coef(xy.lm)+(coef(xy.lm))*T8
> here gives me different  value and  zz = z = sz i do not know the
> reason for
> that
> what i understand about predict() act exactly like using coef() but
> now do
> not know  the difference

If you give predict alist or data.fram whose name is different than
that of the origianl variable ist will be ignored.

> thank you for respond
>
> --
> View this message in context: http://r.789695.n4.nabble.com/what-is-the-difference-between-using-function-predict-and-coef-in-prediction-tp4173961p4180577.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help