R help - Jul 2010 - Error message: attempt to set rownames on object with no dimensions

Hi there,

I am trying to analyze some data using the lme package.
In my case there is a variable called Newmarker that can only take 2 values
(number 1 or number 2).
I have used the as.factor to remark this fact but an error message appears
stating: attempt to set rownames on object with no dimensions.

Here is the code I have used:

*Dataset <-   read.table("Data2.txt", header=TRUE,
sep="", na.strings="NA",
dec=".", strip.white=TRUE)

Dataset$Newmarker <- as.factor(Dataset$Newmarker)

attach(Dataset)

lme.1 <- lme(Newmarker ~ Age, data=Dataset,  random= ~1|ID)

summary(lme.1)*

If I don't use the as.factor I have no problems but I don't think this
is
the correct way to proceed... The other variables I use can have any value.

Can anybody help me please?

Thanking you in advance,

Regards,

Igor Blanco

	[[alternative HTML version deleted]]

?lme (at least the one in package nlme) seems not to mention that the 
response in 'fixed' must be a numeric variable, but it must (and a 
factor is not numeric).

If you want to use a binary response, you need to use other methods, 
and it would be better to ask on R-sig-mixed-models making clear what 
your aims actually are.

On Wed, 21 Jul 2010, Igor Blanco wrote:
> Hi there,
>
> I am trying to analyze some data using the lme package.
Perhaps you mean the nlme package?
> In my case there is a variable called Newmarker that can only take 2 values
> (number 1 or number 2).
> I have used the as.factor to remark this fact but an error message appears
> stating: attempt to set rownames on object with no dimensions.
>
> Here is the code I have used:
>
> *Dataset <-   read.table("Data2.txt", header=TRUE,
sep="", na.strings="NA",
> dec=".", strip.white=TRUE)
>
> Dataset$Newmarker <- as.factor(Dataset$Newmarker)
>
> attach(Dataset)
>
> lme.1 <- lme(Newmarker ~ Age, data=Dataset,  random= ~1|ID)
>
> summary(lme.1)*
>
> If I don't use the as.factor I have no problems but I don't think
this is
> the correct way to proceed... The other variables I use can have any value.
>
> Can anybody help me please?
>
> Thanking you in advance,
>
> Regards,
>
> Igor Blanco
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at 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.
>
-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595

On Jul 21, 2010, at 9:39 AM, Igor Blanco wrote:
> Hi there,
>
> I am trying to analyze some data using the lme package.
> In my case there is a variable called Newmarker that can only take 2  
> values
> (number 1 or number 2).
> I have used the as.factor to remark this fact but an error message  
> appears
> stating: attempt to set rownames on object with no dimensions.
>
> Here is the code I have used:
>
> *Dataset <-   read.table("Data2.txt", header=TRUE,
sep="",
> na.strings="NA",
> dec=".", strip.white=TRUE)
>
> Dataset$Newmarker <- as.factor(Dataset$Newmarker)
Why do you use as.factor? It's probably already a factor. What does  
str(Dataset) show?
>
> attach(Dataset)
You do not need to do this, and it creates potential for confusion.  
The data= argument will allow the column names to be accessed by the  
lme() function.
>
> lme.1 <- lme(Newmarker ~ Age, data=Dataset,  random= ~1|ID)
>
> summary(lme.1)*
>
> If I don't use the as.factor I have no problems but I don't think  
> this is
> the correct way to proceed... The other variables I use can have any  
> value.

-- 

David Winsemius, MD
West Hartford, CT