[R] logistic regression using "glm",which "y" is set to be "1"

Marc Schwartz marc_schwartz at comcast.net
Thu Dec 6 03:47:53 CET 2007


On Wed, 2007-12-05 at 18:06 -0800, Bin Yue wrote:
> Dear friends :
>     using the "glm" function and setting family=binomial, I got a list of
> coefficients.
> The coefficients reflect the effects  of predicted variables on the
> probability of the response to be "1".
> My response variable consists of  "A" and "D" . I don't know which level of
> the response was set to be 1.
> is the first element of the response set to be 1?
>    Thank all in advance.
>    Regards,
> 
> -----
> Best regards,
> Bin Yue


As per the Details section of ?glm:

For binomial and quasibinomial families the response can also be
specified as a factor (when the first level denotes failure and all
others success) ...


So use:

  levels(response.variable)

and that will give you the factor levels, where the first level is 0 and
the second level is 1. 

If you work in a typical English based locale with default alpha based
level ordering, it will likely be A (Alive?) is 0 and D (Dead?) is 1.

HTH,

Marc Schwartz



More information about the R-help mailing list