RMark 2.2.4 covariate.predictions alpha function

posts related to the RMark library, which may not be of general interest to users of 'classic' MARK

RMark 2.2.4 covariate.predictions alpha function

Postby Pavlacky » Mon Oct 02, 2017 6:33 pm

Hello Jeff et al.,

Just a quick note to let you know I'm having trouble with the alpha statement for the covariate.predictions function in the MultScalOcc model.

Using the larksparrow example, I get the same CIs for the alphas in the code below:

Code: Select all
ceap.95 <- covariate.predictions(Species.results,data=data.frame(ceap=ceap.values),alpha=0.025)
ceap.90 <- covariate.predictions(Species.results,data=data.frame(ceap=ceap.values),alpha=0.05)


Thanks much.

Regards,

David
Pavlacky
 
Posts: 8
Joined: Thu Aug 13, 2009 4:18 pm
Location: Ft. Collins, CO

Re: RMark 2.2.4 covariate.predictions alpha function

Postby jlaake » Mon Oct 09, 2017 4:46 pm

Thanks for this. Will look into it. --jeff
jlaake
 
Posts: 1417
Joined: Fri May 12, 2006 12:50 pm
Location: Escondido, CA

Re: RMark 2.2.4 covariate.predictions alpha function

Postby MTMJY » Thu Aug 22, 2019 9:13 am

Hello All,

I'm curious if anyone else encountering this issue has found a solution? I have been attempting to predict survival in the nest survival model using an alpha that is not the default and have encountered the same issue.

Thanks much,
Michael
MTMJY
 
Posts: 6
Joined: Sat Dec 02, 2017 4:42 pm
Location: Montana

Re: RMark 2.2.4 covariate.predictions alpha function

Postby jlaake » Thu Aug 22, 2019 7:00 pm

Sorry for dropping the ball on this. I haven't been good about following up once I retired. It isn't entirely clear in the documentation but the alpha parameter is only for the mata-wald confidence intervals. To use it you need to set argument mata=TRUE. I'll look into coding alpha for std confidence intervals. Will try to get to this by end of Sept. If you haven't heard from me by then, ping me. --jeff

From the documentation

The desired lower and upper error rate. Specifying alpha=0.025
corresponds to a 95% MATA-Wald confidence interval, an
alpha=0.05 to a 90% interval. 'alpha' must be between 0 and 0.5.
Default value is alpha=0.025.
jlaake
 
Posts: 1417
Joined: Fri May 12, 2006 12:50 pm
Location: Escondido, CA

Re: RMark 2.2.4 covariate.predictions alpha function

Postby MTMJY » Sat Oct 19, 2019 4:44 pm

Hi Jeff,

I was just curious if you'd had a chance to look into this? Appreciate all the work you've done already.

Thanks much,
Michael
MTMJY
 
Posts: 6
Joined: Sat Dec 02, 2017 4:42 pm
Location: Montana

Re: RMark 2.2.4 covariate.predictions alpha function

Postby jlaake » Mon Oct 21, 2019 1:10 pm

Yes but haven't posted to cran. You can install from my GitHub site. I'm still testing some new models before I release
jlaake
 
Posts: 1417
Joined: Fri May 12, 2006 12:50 pm
Location: Escondido, CA


Return to RMark

Who is online

Users browsing this forum: Bing [Bot] and 20 guests

cron