<!doctype html public "-//w3c//dtd html 4.0 transitional//en">
<html>
Hello Everybody,
<p>I have a problem with the output of lm.
<br>In fact, when I compare the R output and the Splus output, the results
appears to be different :
<p>I have a dataframe with 5 factors , 16 rows and a response.
<br>First, I tried to fit this response to a linear model : lm(rep~(A+B+C+D+E),data).
<br>The results beetween SPlus and R are different.
<p>In a second time, I tried a new fit : lm(rep~(A+B+D+E+A:B),data).
<br>The estimation of the main effects in the model are the same as the
one
<br>obtained for the first fit for Splus,
<br>and are different for R.
<p>Here an exemple :
<p>
On R:
On Splus
<p> lm(rep~(A+B+C+D+E),data)
-> Intercept 12.6297
12.5573
<br>
A
0.0391
0.0195
<br>
B -0.0073
-0.0036
<br>
C
0.0443
0.0221
<br>
D -0.0321
-0.016
<br>
E -0.18887
-0.0944
<p> lm(rep~(A+B+D+E+A:B),data) -> Intercept
12.7937
12.5573
<br>
A -0.2445
0.0195
<br>
B -0.2910
-0.0036
<br>
D -0.03213
-0.016
<br>
E -0.18887
-0.0944
<br>
A:B 0.5672
0.1418
<p>Can someone explain what happens with these fitting procedure.
<p>Thanks
<br>
<p>Isabelle Zabalza-Mezghani
<br>
<br>
<br>
<br>
<pre>--
Isabelle Zabalza-Mezghani Tel : 01 47 52 61 99
Institut Français du Pétrole E-mail : isabelle.zabalza-mezghani@ifp.fr
1-4 Av. Bois Preau - Bat Lauriers
92852 Rueil Malmaison Cedex, France</pre>
</html>