[R] plot in generalized additive model (GAM)

[David Winsemius]

On Jul 2, 2014, at 1:25 AM, agostinodiciaula at tiscali.it wrote:

> Sorry for my unclear request and description
> I performed:
> 
> x.gam <- gam(mortality ~ s(PM10) + (Tmax) + (umidity), data = data, family = quasipoisson)
> plot(x.gam, page =1)
> 
> the plot showed on the left axis "sPM10,3.07".
> How can I have "Log relative risk" ?

You just want to change the axis label? Then add this to the plot call:

ylab="Log Relative Hazard"

Again, you have not told us anything about the data, so we remain unable to say whether the results corresponds to that label change, but with a quasipoisson link one might expect a logged estimate of <something>.

-- 
David

> thanks again for your kind help
> agostino
> 
> Il 02.07.2014 08:42 David Winsemius ha scritto:
> 
>> On Jul 1, 2014, at 11:33 PM, agostinodiciaula at tiscali.itwrote:
>>> Dear David, many thanks for your reply. The aim was to evaluate the relationship between daily mortality (variable "mortality") and mean daily values of PM10 levels (variable "PM10") in a specific geographic area, considering the effect of meteorological confounders (temperature, umidity). I used the following model (mgcv package): gam(mortality ~ (PM10) + (Tmax) + (umidity), data = data, family = quasipoisson) the question is: how can I obtain a plot of log-relative risk of daily mortality vs. PM10 levels? regards
>> Still rather unclear what the problem is. I see no error message in your question. Are you asking how to assign a model to a name and then call the plot method?
>> 
>> mdlAgostino
>> Il 02.07.2014 01:50 David Winsemius ha scritto:
>> 
>>> On Jul 1, 2014, at 12:02 AM, adc wrote:
>>>> I performed the following GAM by the MGCV package:
>>> I think it's actually spelled in all lower case.
>>>> gam(mortality ~ (PM10) + (Tmax) + (umidity), data = data, family = quasipoisson) How can I obtain a plot of Log-relative risk of mortality vs. PM10 ? thanks
>>> Shouldn't we need to know more details about the experimental setup to answer that question? And what sort of comparisons you are requesting? And about what parts of ?mgcv::plot.gam you need further explanations to answer the question?
>>>> agostino
>>> snipped
>>>> --
>>> snipped
>>>> Sent from the R help mailing list archive at Nabble.com. [[alternative HTML version deleted]]
>>> snipped
>>>> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
>>> David Winsemius Alameda, CA, USA ______________________________________________ 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.
>> 
>> Scopri istella, il nuovo motore per il web italiano.
>> Istella garantisce risultati di qualità e la possibilità di condividere, in modo semplice e veloce, documenti, immagini, audio e video.
>> Usa istella, vai su 
>> http://www.istella.it?wtk=amc138614816829636
>> 
>> 
>> 
> David Winsemius Alameda, CA, USA
> 
> 
> 
> Scopri istella, il nuovo motore per il web italiano.
> Istella garantisce risultati di qualità e la possibilità di condividere, in modo semplice e veloce, documenti, immagini, audio e video.
> Usa istella, vai su http://www.istella.it?wtk=amc138614816829636
> 

David Winsemius
Alameda, CA, USA