gmane.comp.lang.r.epi

Re: Gwet's AC1 Interrater reliability

Griera — 2012-05-04T09:58:57

On Thu, 3 May 2012 14:58:17 -0300
Pedro Emmanuel Alvarenga Americano do Brasil <emmanuel.brasil< at >gmail.com> wrote:


Thanks a lot!!! Very useful!!


_______________________________________________
R-sig-Epi< at >r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-epi

Gwet's AC1 Interrater reliability

Pedro Emmanuel Alvarenga Americano do Brasil — 2012-05-03T17:58:17

R friends,

with some help of a friend and the original author I turn available this
function which is helping me in some analysis. Perhaps it may be useful to
others... :-)

 1.
Gwet KL. Computing inter-rater reliability and its variance in the presence
of high agreement. Br J Math Stat Psychol. 2008 ;61(Pt 1):2948.

# AC1 statistic for 2 raters special case
# table = k x k table which represents table(rater1,rater2), must have
equal number of rows and columns
# N = population size which will be stick in standard error correction,
N=Inf is no correction.
# conflev = Confidence Level associated with the confidence interval (0.95
is the default value)

AC1 <- function(table,conflev=0.95,N=Inf,print=TRUE){
  if(dim(table)[1] != dim(table)[2]){
  stop('The table should have the same number of rows and columns!')
  }
  n <- sum(table)
  f <- n/N
  pa <- sum(diag(table))/n # formula 18
  q <- ncol(table) # number of categories
  pkk <- diag(table)/n
  pak <- sapply(1:q,function(i)sum(table[i,]))/n
  pbk <- sapp

Epidemiology/Biostat at Analytics & Data Mining Conference in San Diego, California, May 23-25

Lisa Solomon — 2012-05-02T20:23:41

Don't miss it, it's this month!

The 2012 Salford Analytics & Data Mining Conference aims to bring together
researchers, practitioners, and data enthusiasts to exchange ideas and
experiences.

Attendees will have the chance to have one-on-one meetings with the creators of the CART and RandomForests algorithms
(Dr. Adele Cutler, Dr. Jerome Friedman and Dr. Richard Olshen).

Attendees will have the chance to learn from practical and theoretical experts including:
*             Dr. Richard Olshen (Chief, Division of Biostatistics at Stanford University School of Medicine and co-creator of CART)
*             Dr. Adele Cutler (co-developer of RandomForests with the late Leo Breiman)
*             Dr. Marsha Wilcox, Director of Epidemiology, Johnson & Johnson
*             Ben Trzaskoma, Senior Statistical Scientist, Genentech, Inc.
*             Dr. Richard Straub, Investigator at Lieber Institute for Brain Development
*             Onchee Yu, Biostatistician at Group Health Research Institute
*             Dr.

Re: Cosinor Model (Halberg, Bingham) - Multiple components - Linear, Quadratic and Cubic trends

BXC (Bendix Carstensen — 2012-03-18T10:48:06

Dear Iva,
First it is normal politeness to identify yourself with name an affiliation at the end of your email to a list like this, many people will not answer anonymous e-mails.

It is a little unclear to me what you mean.

If you are alluding to quadratic or cubic terms in some variable 
you just include then in the model al

lm( y ~ I(z^2) + I(z^3), data=...)

But if you are referring to harmonic functions of higher order you can put hem in as separate sines and cosinse:

lm( y ~ I(cos(2*pi*t/T)) + I(sin(2*pi*t/T)) + I(cos(4*pi*t/T)) + I(sin(4*pi*t/T)) )

Here is a small function and a demo that shows what it does, maybe this is what you are looking for:

harm <-
function( mm, n )
{
  # Function to devise a n'th order harmonic from a
  # numerical vector, scaled to be in the range 0 to 1

  MM <- cbind(
  outer( mm * 2 * pi, 1:n, function(x,y) cos( x*y ) ),
  outer( mm * 2 * pi, 1:n, function(x,y) sin( x*y ) )
              )[,rep(1:n,each=2)+rep(0:1,n)*n]
  colnames( MM ) <- out

Cosinor Model (Halberg,Bingham) - Multiple components - Linear, Quadratic and Cubic trends

Iva P — 2012-03-18T10:21:11


Hello!

I have a doubt in relation with the use of the cosinor model with R when I have not only multiple components, but also linear, quadratic and cubic trends.

I explain the details:

In simple cosinor:


Y = M + A * cos(2
* Ï* t / T + Ï) + error

T knowed: y = M + Î²* X1 + Ï* X2 + error,
Â 
Where X1 = cos (2 * Ï* t / T) and X2 = sin(2
* Ï* t / T)
Â 
In this
case, I use lm(y ~ X1 + X2) .
Â 
For the
multiple components case:
Â 
y = M + âAj * cos(2 * Ï * t /Tj + Ïj) + error
Â 
In this
case I use:Â  lm(y ~ X1tot + X2tot)
Â 
However, in
the generalized model case (linear, quadratic and cubic trends), I donât know
how to analyze with R.
Â 
I include
the situacion formula:
Â 
y = M + Î±1 * t + Î±2 * t2 + Î±3 * t3+ âAj *
cos(2 *Ï* t /Tj + Ï2) + error
Â 
What
function in R can I use, as I used lm for the simple cosinor model and the
multiple components model?.
Â 
How can I
obtain global information and separated information?. I refer to ob

Re: Fwd: Need help to find multifactors influence‏

BXC (Bendix Carstensen — 2012-02-26T23:22:33

Dear Malik Arshad,
this list is a list for asking questions and advice relating to the Epi-package and  broader epidemiological questions related to that.

It is NOT for asking help to solve assignments, so please do not post this type of requests any more. If you are confused between different regression models, you should not ask questions here, but acquire the relevant qualifications first.
And this list cannot help with that.

Best regards,
Bendix Carstensen

________________________________

From: r-sig-epi-bounces< at >r-project.org [mailto:r-sig-epi-bounces< at >r-project.org] On Behalf Of Muhammad Arshad
Sent: 26. februar 2012 23:13
To: r-sig-epi< at >r-project.org
Subject: [R-sig-Epi] Fwd: Need help to find multifactors influence‏


Dear friends,

1-I have B.I value (Dependent variable). 
2-I have land cover types in the form of % area against each B.I (that was clipped through buffer for each B.I ). Buffer was put by considering B.I behavior that can be influence by land type.  
3- I want to see the i

Fwd: Need help to find multifactors influence‏

Muhammad Arshad — 2012-02-26T22:12:52

Dear friends,

1-I have B.I value (Dependent variable).
2-I have land cover types in the form of % area against each B.I (that was
clipped through buffer for each B.I ). Buffer was put by considering B.I
behavior that can be influence by land type.
3- I want to see the influence of land type on B.I.
4- Suppose B.I value varies with the change in (area) one or more types of
land cover. This change may be linear up to some extent but can also
increase with the combination of land types. Land types can also differ
from one buffer to other buffer.
5- I want to develop a Predication Model\Regression Equation to predict B.I
value with the combined influence of different land use types.
6- I am confused which Regression model (Linear, Logistic, and Poisson,
Exponential etc...)  Should be adopted to develop this type of relationship
where factors are varying.
7- Total study map consists of 77 land cover types and each buffer gets
some land type.

Please see the attached data having values extracted for each land typ

Re: R-sig-Epi Digest, Vol 54, Issue 1

Pedro Emmanuel Alvarenga Americano do Brasil — 2012-01-12T20:28:03

Taking a look at task views on survival analysis here:

http://finzi.psych.upenn.edu/views/Survival.html

it seems the package timereg may do what you want.

Abraço forte e que a força esteja com você,

Dr. Pedro Emmanuel A. A. do Brasil
Instituto de Pesquisa Clínica Evandro Chagas
Fundação Oswaldo Cruz
Rio de Janeiro - Brasil
Av. Brasil 4365,
CEP 21040-360,
Tel 55 21 3865-9648
email: pedro.brasil-am19qAsr2QmNrImTOV1V8w< at >public.gmane.org
email: emmanuel.brasil-Re5JQEeQqe8AvxtiuMwx3w< at >public.gmane.org

---Apoio aos softwares livres
www.zotero.org - gerenciamento de referências bibliográficas.
www.broffice.org ou www.libreoffice.org - textos, planilhas ou
apresentações.
www.epidata.dk - entrada de dados.
www.r-project.org - análise de dados.
www.ubuntu.com - sistema operacional

[[alternative HTML version deleted]]

Linear excess relative risk modelling in R

Grellier, James — 2012-01-11T13:08:55

Dear List,



I am attempting to carry out linear excess relative risk modelling for the
purposes of a nested case-control study of nuclear industry workers.



The majority of similar analyses in the literature have been carried out
using EPICURE, SAS or STATA, or have been implemented directly in FORTRAN.
For a number of reasons, it would be preferable for me to carry out the
analysis in R, but I am having difficulty finding an appropriate R
package.



Many thanks in advance for any advice on this matter,



James Grellier



James Grellier PhD

CREAL-Centre for Research in Environmental Epidemiology
Parc de Recerca Biomèdica de Barcelona (despatx 183.01.A)
Doctor Aiguader, 88 | 08003 Barcelona



Tel. +34 932 147 345
jgrellier-MstSlu9blcReoWH0uzbU5w< at >public.gmane.org

 <http://www.creal.cat/> www.creal.cat




[[alternative HTML version deleted]]

Course: Age-Period-Cohort models, Lisbon, September 2011

BXC (Bendix Carstensen — 2011-07-23T12:07:31

Course on Age-Period-Cohort models.
===================================
   Place: Lisbon
    Time: Monday 19th - Wednesday 21st September 2011. 
Deadline: 1 September 2011
     Fee: 380 EUR.
 Teacher: Bendix Carstensen, Steno Diabetes Center, Copenhagen
     URL: http://www.ceaul.fc.ul.pt/seeevent.html?id=206
          http://staff.pubhealth.ku.dk/~bxc/APC/Lisboa-2011
          ( The latter contains links to various material on the topic )
Audience: Epidemiologists and Statisticians.

Age-Period-Cohort models for mortality and morbidity rates is a useful tool for description of age- and time-trends. But the use and in particular the reporting is not straightforward.

The course will cover both the basics of tabulation of data, modeling and choice of parametrization as well as the more advanced aspects of Age-Period-Cohort models, including a substantial practical component, based on computer exercises in R. Specifically the apc-tools in the Epi package for R will be covered in some depth.

Formally no prereq

Running R on a Computer Cluster in the Cloud -cloudnumbers.com

Markus Schmidberger — 2011-07-07T18:11:25

Dear epidemiological data analysis and R experts,

cloudnumbers.com provides researchers and companies with the resources
to perform high performance calculations in the cloud. As
cloudnumbers.com's community manager I may invite you to register and
test R on a computer cluster in the cloud for free:
http://my.cloudnumbers.com/register

Our aim is to change the way of research collaboration is done today by
bringing together scientists and businesses from all over the world on a
single platform. cloudnumbers.com is a Berlin (Germany) based
international high-tech startup striving for enabling everyone to
benefit from the High Performance Computing related advantages of the
cloud. We provide easy access to applications running on any kind of
computer hardware: from single core high memory machines up to 1000
cores computer clusters.

Our platform provides several advantages:

* Turn fixed into variable costs and pay only for the capacity you need.
Watch our latest saving costs with cloudnumbers.com video:
htt

Course: Statistical Practice in Epidemiology with R

Martyn Plummer — 2011-04-26T13:48:04

Many of the subscribers to R-SIG-Epi will be familiar with the course
Statistical Practice in Epidemiology with R, which normally takes place
in Tartu, Estonia.  This year, the course will take place in Lyon,
France 5-9 September. 

The course is intended for epidemiologists and statisticians who wish to
use R  for statistical modelling and analysis of epidemiological data.
The aim of the course is to give participants access to a set of tools
in current use by statisticians in epidemiology. The course requires
fairly good understanding of statistical principles and some familiarity
with epidemiological concepts and study types.

The course is mainly practically oriented with more than half the 
time at the computer.

For more information see 
http://www.iarc.fr/en/education-training/R/
http://www.pubhealth.ku.dk/~BXC/SPE/

To apply for the course, download and fill in the application form. The
deadline for applications is 21 May.



-----------------------------------------------------------------------
Thi

OR in HGLM

Barbour, Russell — 2011-03-30T21:37:18

Dear All,

I  was  wondering how I can  generate adjusted odds  ratio confidence intervals  using the hglm package? I  know you can simply  use the exponential of the estimate to get the OR,  but I  am not sure how you  can get the  equivalent of the " logistic.display"  in epicalc that will also  generate the  CI's.  I  know this is   very  elementary  question.

Russell " Skip" Barbour  Ph.D.
Yale School  of Medicine
135 College St.  Suit 200
New Haven ,  CT. 06510
Tel: 203 764 4332
Fax: 203 764 4353
Email: russell.barbour-LrD5EImo2rg< at >public.gmane.org<mailto:russell.barbour-LrD5EImo2rg< at >public.gmane.org>


Doubt grows with knowledge.
Johann Wolfgang von Goethe<http://www.brainyquote.com/quotes/quotes/j/johannwolf380192.html>



[[alternative HTML version deleted]]

Sourveillance package

luca candeloro — 2011-03-22T14:03:09

Hi,
I'm using the function algo.farrington() in package surveillance to detect
mortality greater than expected for a given region.
As described in Farrington method, it should be possible to take into
account for population at risk but I can't find the way to do this whit the
specified R package/function.
Does anyone know how may I do?
Thanks,
Luca

[[alternative HTML version deleted]]

Re: converting string to a object name of a dataset

Madan Gopal Kundu — 2011-03-18T18:55:57

Thanks a lot for your help. Yeah it was a mistake from my end only.

Regards
Madan Gopal Kundu
On Fri, Mar 18, 2011 at 1:19 PM, David Winsemius <dwinsemius-Wuw85uim5zDR7s880joybQ< at >public.gmane.org> wrote:

Re: converting string to a object name of a dataset

David Winsemius — 2011-03-18T17:19:22

On Mar 18, 2011, at 11:18 AM, Madan Gopal Kundu wrote:


Did you mean to type:

  data1<- data.frame(x=c(1:4), y=rep(1, 4))  # ?

 > data1
   x y
1 1 1
2 2 1
3 3 1
4 4 1


David Winsemius, MD
West Hartford, CT

Re: converting string to a object name of a dataset

peter dalgaard — 2011-03-18T15:26:23

On Mar 18, 2011, at 16:18 , Madan Gopal Kundu wrote:


Well, that's not what you put in! Try ...y=rep(1,4)...

Adding to the original question, notice that there is a difference between variable names and expressions. get() will get you a variable by name, but "data1$y" is not a name (well, it is, but not of the object you are looking for). If you insist on building R expressions as character strings, you need to evaluate them with eval(parse(string)). David had the better idea though.

Re: converting string to a object name of a dataset

Ryung S. Kim — 2011-03-18T15:20:49

Hi, 

 try changing rep(1:4) to rep(1,4)

On Fri, 18 Mar 2011, Madan Gopal Kundu wrote:

Hi,

Thanks to David and Bendix for giving me the solution. I would like to
extend my question little bit further. I am trying to execute
following code:

data1<- data.frame(x=c(1:4), y=rep(1:4))
gvars<- c("x", "y")
for (i in 1:2)
{
print(data1[[gvars[i]]])
}

and it returns the following output:
[1] 1 2 3 4
[1] 1 2 3 4

However, my desired output is
[1] 1 2 3 4
[1] 1 1 1 1

I tried the following code as well, but the problem remains same:
attach(data1)
for (i in 1:2)
{
print(get(gvars[i]))
}

Thanks in advance!!

Regards
Madan

On Fri, Mar 18, 2011 at 3:19 AM, BXC (Bendix Carstensen) <bxc-77mEMlKuB9s< at >public.gmane.org> wrote:

_______________________________________________
R-sig-Epi-0bNBQ1PAWB4BXFe83j6qeQ< at >public.gmane.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-epi

Re: converting string to a object name of a dataset

Madan Gopal Kundu — 2011-03-18T15:18:16

Hi,

Thanks to David and Bendix for giving me the solution. I would like to
extend my question little bit further. I am trying to execute
following code:

data1<- data.frame(x=c(1:4), y=rep(1:4))
gvars<- c("x", "y")
for (i in 1:2)
{
print(data1[[gvars[i]]])
}

and it returns the following output:
[1] 1 2 3 4
[1] 1 2 3 4

However, my desired output is
[1] 1 2 3 4
[1] 1 1 1 1

I tried the following code as well, but the problem remains same:
attach(data1)
for (i in 1:2)
{
print(get(gvars[i]))
}

Thanks in advance!!

Regards
Madan

On Fri, Mar 18, 2011 at 3:19 AM, BXC (Bendix Carstensen) <bxc-77mEMlKuB9s< at >public.gmane.org> wrote:

Re: converting string to a object name of a dataset

David Winsemius — 2011-03-18T13:35:43

On Mar 18, 2011, at 3:19 AM, BXC (Bendix Carstensen) wrote:

Many R users make an effort to avoid using `attach` in any setting  
other than the very earliest efforts at learning R. As a result they  
also avoid the use of "$" in coding, since it is much less flexible  
than the function on which it depends, namely "[[". If you want the  
string "x" to beinterpreted as a columnname then "[[" is the way to go:

 > data1<- data.frame(x=c(1:4), y=rep(1,4))
 > gvars<- c("x", "y")

#Two methods get you the results you want:

 > data1[[gvars[1] ]]
[1] 1 2 3 4
 > get("data1")[[ gvars[1] ]]
[1] 1 2 3 4

Re: converting string to a object name of a dataset

BXC (Bendix Carstensen — 2011-03-18T07:19:47

get() looks in the search path, so you can put data 1 there using attach():

[1] 1 2 3 4
[1] 1 1 1 1

Best regards,
Bendix Carstensen
_________________________________________

Bendix Carstensen 
Senior Statistician
Steno Diabetes Center A/S
Niels Steensens Vej 2-4
DK-2820 Gentofte
Denmark
+45 44 43 87 38 (direct)
+45 30 75 87 38 (mobile)
bxc-77mEMlKuB9s< at >public.gmane.org    www.biostat.ku.dk/~bxc
www.steno.dk