[R] lrm in Design
Hello everybody, I am trying to do a logistic regression model with lrm() from the design package. I am comparing to groups with different medical outcome which can either be "good" or "bad". In the help file it says that lrm codes al responses to 0,1,2,3, etc. internally and does so in alphabetical order. I would guess this means bad=0 and good=1. My question: I am trying to figure out the connection between my factors and my response. Which probability is being calculated that of good or bad (1 or 0, respectively). I'm not sure whether I made clear what I was trying to say but will be very grateful for all help. -- View this message in context: http://www.nabble.com/lrm-in-Design-tp25206737p25206737.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] lrm in Design
See: https://stat.ethz.ch/pipermail/r-help/2009-July/204192.html and also other posts in that thread. On Sat, Aug 29, 2009 at 6:02 PM, loch1 wrote: > > Hello everybody, > I am trying to do a logistic regression model with lrm() from the design > package. I am comparing to groups with different medical outcome which can > either be "good" or "bad". In the help file it says that lrm codes al > responses to 0,1,2,3, etc. internally and does so in alphabetical order. I > would guess this means bad=0 and good=1. > > My question: I am trying to figure out the connection between my factors and > my response. Which probability is being calculated that of good or bad (1 or > 0, respectively). > > I'm not sure whether I made clear what I was trying to say but will be very > grateful for all help. > -- > View this message in context: > http://www.nabble.com/lrm-in-Design-tp25206737p25206737.html > Sent from the R help mailing list archive at Nabble.com. > > __ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] lrm in Design
Thank you for your reply, it helped. That thread is about glm, I take it that lrm behaves in the same way?!? See: https://stat.ethz.ch/pipermail/r-help/2009-July/204192.html and also other posts in that thread. -- View this message in context: http://www.nabble.com/lrm-in-Design-tp25206737p25209958.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] lrm in Design
Presumably the same idea would apply to lrm if appropriately adapted. On Sun, Aug 30, 2009 at 5:19 AM, loch1 wrote: > > Thank you for your reply, it helped. That thread is about glm, I take it that > lrm behaves in the same way?!? > > > > See: > https://stat.ethz.ch/pipermail/r-help/2009-July/204192.html > > and also other posts in that thread. > > -- > View this message in context: > http://www.nabble.com/lrm-in-Design-tp25206737p25209958.html > Sent from the R help mailing list archive at Nabble.com. > > __ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] lrm in Design package, missing value problem
__ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] lrm in Design package, missing value problem
Hi,
This concerns lrm in the Design package, which I need for the clustered
errors option with panel data.
I have created a variable (using sign()) that has values -1, 0, and 1
(and some NAs). call this variable x3. lrm does not like
t = lrm(y ~ x1 + x2 + I(x3==-1) + I(x3==1), data=data,x=T,y=T)
I get the error message: Error in if (!length(fname) || !any(fname ==
zname)) { :
missing value where TRUE/FALSE needed
Running this on the subset of data with non missing x3 values doesn't help.
glm has no problem with this.
Thanks very much,
Jim Fearon
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] lrm in Design package, missing value problem
James Fearon wrote:
Hi,
This concerns lrm in the Design package, which I need for the clustered
errors option with panel data.
I have created a variable (using sign()) that has values -1, 0, and 1
(and some NAs). call this variable x3. lrm does not like
t = lrm(y ~ x1 + x2 + I(x3==-1) + I(x3==1), data=data,x=T,y=T)
I get the error message: Error in if (!length(fname) || !any(fname ==
zname)) { :
missing value where TRUE/FALSE needed
Running this on the subset of data with non missing x3 values doesn't help.
glm has no problem with this.
Thanks very much,
Jim Fearon
Right, Design does not like variables to be split up. Make x3 a factor
and use it just as the single term x3 in the model.
Frank
--
Frank E Harrell Jr Professor and Chair School of Medicine
Department of Biostatistics Vanderbilt University
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[R] lrm in Design package--missing value where TRUE/FALSE needed
Hi,
A error message arose while I was trying to fit a ordinal model with lrm() I am
using R 2.8 with Design package.
Here is a small set of mydata:
RC RS Sex CovACovBCovCCovDCovE
2 1 0 1 1 0 -0.0055752802
2 1 0 1 0 1 -0.0019595802
3 0 0 0 1 0 -0.0047258802
0 0 0 1 0 0 -0.0055048502
2 1 1 0 0 0 -0.0038801701
2 1 0 0 1 0 -0.0060742302
2 1 0 0 1 1 -0.0039639202
2 1 0 0 1 00.0006582302
2 1 0 1 0 1 -0.0020336102
0 0 0 0 0 1 -0.0077617702
0 0 0 0 1 1 -0.0009517842
Note: In the complete data, there are NAs. But the error messages showed in
both the complete and above sets.
>attach(mydata)
>lrm(RC~RS+Sex+CovA+CovB+CovC+CovD+CovE,data=mydata,na.action=na.pass)
singular information matrix in lrm.fit (rank= 8 ). Offending variable(s):
CovE
Error in j:(j + params[i] - 1) : NA/NaN argument
>detach(mydata)
>lrm(mydata$RC~ mydata$RS+ mydata$Sex+ mydata$CovA+ mydata$CovB+ mydata$CovC+
>mydata$CovD+ mydata$CovE,data=mydata,na.action=na.pass)
Error in if (!length(fname) || !any(fname == zname)) { :
missing value where TRUE/FALSE needed
I have debugged for a while, but no success. Does anyone know what happens?
Thanks,
Mike
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] lrm in Design package--missing value where TRUE/FALSE needed
The idea of estimating 7 parameters from 11 cases using mostly binary
variables just seems begging for a singular matrix.
On Sep 4, 2009, at 3:59 PM, Ping-Hsun Hsieh wrote:
Hi,
A error message arose while I was trying to fit a ordinal model with
lrm() I am using R 2.8 with Design package.
Here is a small set of mydata:
RC RS Sex CovACovBCovCCovDCovE
2 1 0 1 1 0 -0.0055752802
2 1 0 1 0 1 -0.0019595802
3 0 0 0 1 0 -0.0047258802
0 0 0 1 0 0 -0.0055048502
2 1 1 0 0 0 -0.0038801701
2 1 0 0 1 0 -0.0060742302
2 1 0 0 1 1 -0.0039639202
2 1 0 0 1 00.0006582302
2 1 0 1 0 1 -0.0020336102
0 0 0 0 0 1 -0.0077617702
0 0 0 0 1 1 -0.0009517842
Note: In the complete data, there are NAs. But the error messages
showed in both the complete and above sets.
attach(mydata)
lrm(RC~RS+Sex+CovA+CovB+CovC+CovD+CovE,data=mydata,na.action=na.pass)
singular information matrix in lrm.fit (rank= 8 ). Offending
variable(s):
CovE
Error in j:(j + params[i] - 1) : NA/NaN argument
detach(mydata)
lrm(mydata$RC~ mydata$RS+ mydata$Sex+ mydata$CovA+ mydata$CovB+
mydata$CovC+ mydata$CovD+ mydata$CovE,data=mydata,na.action=na.pass)
Error in if (!length(fname) || !any(fname == zname)) { :
missing value where TRUE/FALSE needed
I have debugged for a while, but no success. Does anyone know what
happens?
David Winsemius, MD
Heritage Laboratories
West Hartford, CT
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] lrm in Design package--missing value where TRUE/FALSE needed
Ping-Hsun Hsieh wrote:
Hi,
A error message arose while I was trying to fit a ordinal model with lrm() I am
using R 2.8 with Design package.
Here is a small set of mydata:
RC RS Sex CovACovBCovCCovDCovE
2 1 0 1 1 0 -0.0055752802
2 1 0 1 0 1 -0.0019595802
3 0 0 0 1 0 -0.0047258802
0 0 0 1 0 0 -0.0055048502
2 1 1 0 0 0 -0.0038801701
2 1 0 0 1 0 -0.0060742302
2 1 0 0 1 1 -0.0039639202
2 1 0 0 1 00.0006582302
2 1 0 1 0 1 -0.0020336102
0 0 0 0 0 1 -0.0077617702
0 0 0 0 1 1 -0.0009517842
Note: In the complete data, there are NAs. But the error messages showed in
both the complete and above sets.
attach(mydata)
lrm(RC~RS+Sex+CovA+CovB+CovC+CovD+CovE,data=mydata,na.action=na.pass)
singular information matrix in lrm.fit (rank= 8 ). Offending variable(s):
CovE
Error in j:(j + params[i] - 1) : NA/NaN argument
detach(mydata)
lrm(mydata$RC~ mydata$RS+ mydata$Sex+ mydata$CovA+ mydata$CovB+ mydata$CovC+
mydata$CovD+ mydata$CovE,data=mydata,na.action=na.pass)
Please read the documentation. Use data=. Don't use $ in variables in
the model. I don't know what na.pass is. lrm does not allow NAs to be
used in the attempted model fit.
Frank
Error in if (!length(fname) || !any(fname == zname)) { :
missing value where TRUE/FALSE needed
I have debugged for a while, but no success. Does anyone know what happens?
Thanks,
Mike
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
--
Frank E Harrell Jr Professor and Chair School of Medicine
Department of Biostatistics Vanderbilt University
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] lrm in Design package--missing value where TRUE/FALSE needed
annie Zhang wrote:
Hi, Frank,
I met the same problem. My data does not have NA, when I run
fit <- lrm(Y_t~.,data=X)
The error message is:
singular information matrix in lrm.fit (rank= 35 ). Offending variable(s):
X35
Error in j:(j + params[i] - 1) : NA/NaN argument
How can I avoid this?
Thank you,
Annie
Please read earlier posts. Avoid it by not having an overdescribed
problem which will result in overfitting.
Frank
On Fri, Sep 4, 2009 at 2:44 PM, Frank E Harrell Jr
mailto:f.harr...@vanderbilt.edu>> wrote:
Ping-Hsun Hsieh wrote:
Hi,
A error message arose while I was trying to fit a ordinal model
with lrm() I am using R 2.8 with Design package.
Here is a small set of mydata:
RC RS Sex CovACovBCovCCovDCovE
2 1 0 1 1 0 -0.0055752802
2 1 0 1 0 1 -0.0019595802
3 0 0 0 1 0 -0.0047258802
0 0 0 1 0 0 -0.0055048502
2 1 1 0 0 0 -0.0038801701
2 1 0 0 1 0 -0.0060742302
2 1 0 0 1 1 -0.0039639202
2 1 0 0 1 00.0006582302
2 1 0 1 0 1 -0.0020336102
0 0 0 0 0 1 -0.0077617702
0 0 0 0 1 1 -0.0009517842
Note: In the complete data, there are NAs. But the error
messages showed in both the complete and above sets.
attach(mydata)
lrm(RC~RS+Sex+CovA+CovB+CovC+CovD+CovE,data=mydata,na.action=na.pass)
singular information matrix in lrm.fit (rank= 8 ). Offending
variable(s):
CovE Error in j:(j + params[i] - 1) : NA/NaN argument
detach(mydata)
lrm(mydata$RC~ mydata$RS+ mydata$Sex+ mydata$CovA+
mydata$CovB+ mydata$CovC+ mydata$CovD+
mydata$CovE,data=mydata,na.action=na.pass)
Please read the documentation. Use data=. Don't use $ in variables
in the model. I don't know what na.pass is. lrm does not allow NAs
to be used in the attempted model fit.
Frank
Error in if (!length(fname) || !any(fname == zname)) { :
missing value where TRUE/FALSE needed
I have debugged for a while, but no success. Does anyone know
what happens?
Thanks,
Mike
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Re: [R] lrm in Design package--missing value where TRUE/FALSE needed
Hi, Frank,
I met the same problem. My data does not have NA, when I run
fit <- lrm(Y_t~.,data=X)
The error message is:
singular information matrix in lrm.fit (rank= 35 ). Offending variable(s):
X35
Error in j:(j + params[i] - 1) : NA/NaN argument
How can I avoid this?
Thank you,
Annie
On Fri, Sep 4, 2009 at 2:44 PM, Frank E Harrell Jr wrote:
> Ping-Hsun Hsieh wrote:
>
>> Hi,
>>
>> A error message arose while I was trying to fit a ordinal model with lrm()
>> I am using R 2.8 with Design package.
>>
>> Here is a small set of mydata:
>> RC RS Sex CovACovBCovCCovDCovE
>> 2 1 0 1 1 0 -0.0055752802
>> 2 1 0 1 0 1 -0.0019595802
>> 3 0 0 0 1 0 -0.0047258802
>> 0 0 0 1 0 0 -0.0055048502
>> 2 1 1 0 0 0 -0.0038801701
>> 2 1 0 0 1 0 -0.0060742302
>> 2 1 0 0 1 1 -0.0039639202
>> 2 1 0 0 1 00.0006582302
>> 2 1 0 1 0 1 -0.0020336102
>> 0 0 0 0 0 1 -0.0077617702
>> 0 0 0 0 1 1 -0.0009517842
>>
>> Note: In the complete data, there are NAs. But the error messages showed
>> in both the complete and above sets.
>>
>> attach(mydata)
>>> lrm(RC~RS+Sex+CovA+CovB+CovC+CovD+CovE,data=mydata,na.action=na.pass)
>>>
>> singular information matrix in lrm.fit (rank= 8 ). Offending variable(s):
>> CovE Error in j:(j + params[i] - 1) : NA/NaN argument
>>
>> detach(mydata)
>>> lrm(mydata$RC~ mydata$RS+ mydata$Sex+ mydata$CovA+ mydata$CovB+
>>> mydata$CovC+ mydata$CovD+ mydata$CovE,data=mydata,na.action=na.pass)
>>>
>>
> Please read the documentation. Use data=. Don't use $ in variables in the
> model. I don't know what na.pass is. lrm does not allow NAs to be used in
> the attempted model fit.
>
> Frank
>
> Error in if (!length(fname) || !any(fname == zname)) { : missing value
>> where TRUE/FALSE needed
>>
>>
>> I have debugged for a while, but no success. Does anyone know what
>> happens?
>>
>> Thanks,
>> Mike
>> __
>> R-help@r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide
>> http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>>
>>
>
> --
> Frank E Harrell Jr Professor and Chair School of Medicine
> Department of Biostatistics Vanderbilt University
>
>
> __
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
[[alternative HTML version deleted]]
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
