Prev 13386 / 20628 Next

DHGLM Double hierarchical GLMs

Ken Beath

Thu, May 28, 2015 2:55 AM

It looks like the package doesn't work properly, not unusual with a package
that is nearly 4 years old. Send an e-mail to the maintainer.

Ken

On 28 May 2015 at 00:55, Patrick, Samantha <Samantha.Patrick at liverpool.ac.uk

wrote:

Hi

I am using the package dhglm to run a double hierarchical GLM.  I have
been using the data provided with the package to experiment and I am having
problems getting the summary for the model.  This code is taken from the
package documentation:

### DHGLM introducing random effects in the overdispersion for crack
growth data
library(dhglm)

data(data_crack_growth)

model_mu<-DHGLMMODELING(Model="mean",
                        Link="log",
                        LinPred=y~crack0+(1|specimen),
                        RandDist="inverse-gamma")

model_phi<-DHGLMMODELING(Model="dispersion", Link="log",
                         LinPred=phi~cycle+(1|specimen),
RandDist="gaussian")

res_crack<-dhglmfit(RespDist="gamma",
                    DataMain=data_crack_growth,
                    MeanModel=model_mu,
                    DispersionModel=model_phi)

summary(res_crack)

##The output here is:

     Length Class  Mode
[1,] 241    -none- numeric
[2,] 241    -none- numeric

##when the instructions suggest it should contain:

FixCoef
RandCoef
iter
mtwolikelihood


##I have investigated looking at:

str(res_crack)


List of 2

 $ : num [1:241, 1] 1.2262 0.5985 -0.0856 1.1755 0.08 ...

 $ : num [1:241, 1] 0.0393 0.0447 0.0508 0.0577 0.0691 ..

class(res_crack)

[1] "list"

##However the documentation suggests it should be a dhglm object.  When I
run:

summary.dhglm


object 'summary.dhglm' not found

To me this suggests my computer can not locate the summary.dhglm command.
Has anyone else had any experiences like this or success using the package?

Many Thanks

Sam


Samantha Patrick
Lecturer in Marine Biology

School of Environmental Sciences
University of Liverpool
Nicholson Building
Brownlow Street
Liverpool
L69 3GP, UK
Tel: 0151 795 4390
Skype: Sammy_Patrick
Website: http://samanthacpatrick.wix.com/home
Twitter: SamCPatrick

From: Samantha Patrick<mailto:spatrick at liverpool.ac.uk>
Sent: ?Wednesday?, ?27? ?May? ?2015 ?15?:?45
To: 'r-sig-mixed-models at r-project.org'<mailto:
r-sig-mixed-models at r-project.org>

Hi

I am using the package dhglm to run a double hierarchical GLM.  I have
been using the data provided with the package to experiment and I am having
problems getting the summary for the model.  This code is taken from the
package documentation:

### DHGLM introducing random effects in the overdispersion for crack
growth data
library(dhglm)

data(data_crack_growth)

model_mu<-DHGLMMODELING(Model="mean",
                        Link="log",
                        LinPred=y~crack0+(1|specimen),
                        RandDist="inverse-gamma")

model_phi<-DHGLMMODELING(Model="dispersion", Link="log",
                         LinPred=phi~cycle+(1|specimen),
RandDist="gaussian")

res_crack<-dhglmfit(RespDist="gamma",
                    DataMain=data_crack_growth,
                    MeanModel=model_mu,
                    DispersionModel=model_phi)

summary(res_crack)

##The output here is:

     Length Class  Mode
[1,] 241    -none- numeric
[2,] 241    -none- numeric

##when the instructions suggest it should contain:

FixCoef
RandCoef
iter
mtwolikelihood


##I have investigated looking at:

str(res_crack)


List of 2

 $ : num [1:241, 1] 1.2262 0.5985 -0.0856 1.1755 0.08 ...

 $ : num [1:241, 1] 0.0393 0.0447 0.0508 0.0577 0.0691 ..

class(res_crack)

[1] "list"

##However the documentation suggests it should be a dhglm object.  When I
run:

summary.dhglm


object 'summary.dhglm' not found

To me this suggests my computer can not locate the summary.dhglm command.
Has anyone else had any experiences like this or success using the package?

Many Thanks

Sam


Samantha Patrick
Lecturer in Marine Biology

School of Environmental Sciences
University of Liverpool
Nicholson Building
Brownlow Street
Liverpool
L69 3GP, UK
Tel: 0151 795 4390
Skype: Sammy_Patrick
Website: http://samanthacpatrick.wix.com/home
Twitter: SamCPatrick

From: Samantha Patrick<mailto:spatrick at liverpool.ac.uk>
Sent: ?Wednesday?, ?27? ?May? ?2015 ?13?:?03
To: 'r-sig-mixed-models at r-project.org'<mailto:
r-sig-mixed-models at r-project.org>

Hi

I am using the package dhglm to run a double hierarchical GLM.  I have
been using the data provided with the package to experiment and I am having
problems getting the summary for the model.  This code is taken from the
package documentation:

### DHGLM introducing random effects in the overdispersion for crack
growth data
library(dhglm)

data(data_crack_growth)

model_mu<-DHGLMMODELING(Model="mean",
                        Link="log",
                        LinPred=y~crack0+(1|specimen),
                        RandDist="inverse-gamma")

model_phi<-DHGLMMODELING(Model="dispersion", Link="log",
                         LinPred=phi~cycle+(1|specimen),
RandDist="gaussian")

res_crack<-dhglmfit(RespDist="gamma",
                    DataMain=data_crack_growth,
                    MeanModel=model_mu,
                    DispersionModel=model_phi)

summary(res_crack)

##The output here is:

     Length Class  Mode
[1,] 241    -none- numeric
[2,] 241    -none- numeric

##when the instructions suggest it should contain:

FixCoef
RandCoef
iter
mtwolikelihood


##I have investigated looking at:

str(res_crack)


List of 2

 $ : num [1:241, 1] 1.2262 0.5985 -0.0856 1.1755 0.08 ...

 $ : num [1:241, 1] 0.0393 0.0447 0.0508 0.0577 0.0691 ..

class(res_crack)

[1] "list"

##However the documentation suggests it should be a dhglm object.  When I
run:

summary.dhglm


object 'summary.dhglm' not found

To me this suggests my computer can not locate the summary.dhglm command.
Has anyone else had any experiences like this or success using the package?

Many Thanks

Sam


Samantha Patrick
Lecturer in Marine Biology

School of Environmental Sciences
University of Liverpool
Nicholson Building
Brownlow Street
Liverpool
L69 3GP
UK

Tel: 0151 7954390
Skype: sammy_patrick
Website: http://samanthacpatrick.wix.com/home
Twitter: SamCPatrick



From: Patrick, Samantha
Sent: 27 May 2015 12:04
To: r-sig-mixed-models at r-project.org
Subject: DHGLM Double hierarchical GLMs

Hi

I am using the package dhglm to run a double hierarchical GLM.  I have
been using the data provided with the package to experiment and I am having
problems getting the summary for the model.  This code is taken from the
package documentation:

### DHGLM introducing random effects in the overdispersion for crack
growth data
library(dhglm)

data(data_crack_growth)

model_mu<-DHGLMMODELING(Model="mean",
                        Link="log",
                        LinPred=y~crack0+(1|specimen),
                        RandDist="inverse-gamma")

model_phi<-DHGLMMODELING(Model="dispersion", Link="log",
                         LinPred=phi~cycle+(1|specimen),
RandDist="gaussian")

res_crack<-dhglmfit(RespDist="gamma",
                    DataMain=data_crack_growth,
                    MeanModel=model_mu,
                    DispersionModel=model_phi)

summary(res_crack)

##The output here is:

     Length Class  Mode
[1,] 241    -none- numeric
[2,] 241    -none- numeric

##when the instructions suggest it should contain:

FixCoef
RandCoef
iter
mtwolikelihood


##I have investigated looking at:

str(res_crack)


List of 2

 $ : num [1:241, 1] 1.2262 0.5985 -0.0856 1.1755 0.08 ...

 $ : num [1:241, 1] 0.0393 0.0447 0.0508 0.0577 0.0691 ..

class(res_crack)

[1] "list"

##However the documentation suggests it should be a dhglm object.  When I
run:

summary.dhglm


object 'summary.dhglm' not found

To me this suggests my computer can not locate the summary.dhglm command.
Has anyone else had any experiences like this or success using the package?

Many Thanks

Sam


Samantha Patrick
Lecturer in Marine Biology

School of Environmental Sciences
University of Liverpool
Nicholson Building
Brownlow Street
Liverpool
L69 3GP
UK

Tel: 0151 7954390
Skype: sammy_patrick
Website: http://samanthacpatrick.wix.com/home
Twitter: SamCPatrick




        [[alternative HTML version deleted]]

_______________________________________________
R-sig-mixed-models at r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models

*Ken Beath*
Lecturer
Statistics Department
MACQUARIE UNIVERSITY NSW 2109, Australia

Phone: +61 (0)2 9850 8516

Building E4A, room 526
http://stat.mq.edu.au/our_staff/staff_-_alphabetical/staff/beath,_ken/

CRICOS Provider No 00002J
This message is intended for the addressee named and may...{{dropped:9}}

Thread (3 messages)

Patrick, Samantha DHGLM Double hierarchical GLMs May 27 Ken Beath DHGLM Double hierarchical GLMs May 28 Patrick, Samantha DHGLM Double hierarchical GLMs May 28