R help - Dec 2011 - Prediction from censReg?

Hi - 

First post, so excuse any errors in protocol: 

Wanted to ask if there's an easy way to use 'predict' with objects
of class
'censReg', 'maxLik', 'maxim' or 'list'.

Have a left-censored dataset, attempting to use a Tobit model and am working
with the censReg package. I like how easy it is to move from glm models to
predictions with 'predict' and wanted to ask if there was a way to do so
with objects output from 'censReg'.

Thanks,

Zack

--
View this message in context:
http://r.789695.n4.nabble.com/Prediction-from-censReg-tp4155855p4155855.html
Sent from the R help mailing list archive at Nabble.com.

Just posting again here...

--
View this message in context:
http://r.789695.n4.nabble.com/Prediction-from-censReg-tp4155855p4158844.html
Sent from the R help mailing list archive at Nabble.com.

Dear Zack

On 4 December 2011 03:08, z2.0 <zack.abrahamson at gmail.com>
wrote:
> Wanted to ask if there's an easy way to use 'predict' with
objects of class
> 'censReg', 'maxLik', 'maxim' or 'list'.
>
> Have a left-censored dataset, attempting to use a Tobit model and am
working
> with the censReg package. I like how easy it is to move from glm models to
> predictions with 'predict' and wanted to ask if there was a way to
do so
> with objects output from 'censReg'.
Unfortunately, I haven't had time yet to implement a predict() method
for "censReg" objects. Sorry! However, if you have (or anybody else
has) time and skills to do this, please do not hesitate to become a
project member at R-Forge and implement this method. Thanks!

Best wishes,
Arne

-- 
Arne Henningsen
http://www.arne-henningsen.name

> Have a left-censored dataset, attempting to use a Tobit model and am
working
> with the censReg package. I like how easy it is to move from glm
models to
> predictions with 'predict' and wanted to ask if there was a way to
do
so
> with objects output from 'censReg'.
----
You can fit tobin regression models with survreg, see the help page for
an example.  It has prediction methods.

Terry Therneau

(Sorry about the word wrap: a "feature" of my mail tool.)