Greetings,
I’m using a simple linear regression model with factors as
regressors, and am uncertain about the interpretation.
Specifically, I have the following regression specified:
l <- lm(log(price) ~ log(sfla) + log(land.sf) + bed + fbath +
recroom + as.factor(sf.type)
The results show coefficients for four of the five levels of the
sf.type variable, but report them as “as.factor(sf.type)1” …”as.factor(sf.type)4”
My question is which one is omitted? And, which of the five
types is “1”, “2”, etc? That is, how are the levels mapped and assigned? Is
there a rule that would make this easy to read?
I could create the dummy variables by hand, but this seems clumsy.
Thanks,
Chris.
From:
s-news-owner@lists.biostat.wustl.edu
[mailto:s-news-owner@lists.biostat.wustl.edu] On Behalf Of Lim Weiyang
Sent: Saturday, November 01, 2008 11:34 AM
To: s-news@lists.biostat.wustl.edu
Subject: [S] Create new category column in dataframe
I wonder whether I can create a new factor column with new
categories and names derived from a column with numeric values. For
example, I wish to have four categories of the following form and
names(firstcat, secondcat, thirdcat, fourthcat):
Between -1 and 1: firstcat
Between -2 and -1 or between 1 and 2: secondcat
Between -5 and -2 or between 2 and 5: thirdcat
Below -5 or more than 5: fourthcat
I have looked at functions cut, factor etc but do not know
how to use them for my purpose.
Sincerely hope to have some assistance.
|
New
Email names for you!
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!