[R] Fwd: Categorial Response Questions

[Frank E Harrell Jr]

andyer weng wrote:
> Sorry Guys, i press the wrong button to send out the uncompleted message.
> 
> let me do it again.
> 
> I have a data set containing :
> 
> pclass:  A factor giving the class of the passenger: one of 1st, 2nd, 3rd.
> age:      The age of the passenger in years.
> sex:      Passenger's gender: female or male
> age.group:        Passengers age group, one of 0‐9 , 10‐19, 20‐29,
> 30‐39, 40‐49, 50‐59, 60‐69,70‐79
> survived:            Passenger's survival (1=survived, 0=did not survive)
> 
> Ignoring the variable age,
> - I need to group the data into groups corresponding to each
> age‐group/sex/class combination,
> - I need to compute the logits for each combination.
> - Make a data frame containing the logits, and the categorical
> variables. I need to have one line in the data frame for each
> combination of the factor levels.
> 
> Can someone please help with the R code for above???!!!
> 
> Thanks millions!!
> 
> Cheers
> Andyer.
> 
> 
> ---------- Forwarded message ----------
> From: andyer weng <nzandyer at gmail.com>
> Date: 2008/10/18
> Subject: RE:Categorial Response Questions
> To: r-help at r-project.org
> 
> 
> Hi All,
> 
> I have a data set containing :
> pclass:  A factor giving the class of the passenger: one of 1st, 2nd, 3rd.
> age The age of the passenger in years.
> sex Passenger's gender: female or male
> age.group Passengers age group, one of 0‐9 , 10‐19, 20‐29, 30‐39,
> 40‐49, 50‐59, 60‐69,
> 70‐79
> survived Passenger's survival (1=survived, 0=did not survive)
> 

For that dataset, 10-19  is aa very heterogeneous group; those ages
should not
have been combined.
Frank


_______________________________
Frank E Harrell Jr   Professor and Chair           School of Medicine
                     Department of Biostatistics   Vanderbilt University