[R] Result differences in 32-bit vs. 64-bit point.in.polygon?

[Lensing, Shelly Y]

Is anyone aware of point.in.polygon giving different results for 32-bit vs. 
64-bit R? Our OS is 64-bit Windows 7 Enterprise. I'm working with someone 
else's extensive R program and the final results are close but not exactly 
matching. We're thinking it might be something with the point.in.polygon 
function (one of many possibilities, including leaps).

Thanks much,

Shelly Lensing
Biostatistics / University of Arkansas for Medical Sciences
4301 W. Markham St. #781 / Little Rock, AR  72205
V: 501.686.8203 / F: 501-526-6729 / COPH 3236

--
Confidentiality Notice: This e-mail message, including a...{{dropped:10}}

__
R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see
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.

[R] R on Windows Server

[Lensing, Shelly Y]

We are starting the process for purchasing a server with Windows Server 2008 
OS. We are mainly interested in storage for multiple users, but would like to 
have the capability to run R simulations on the server. Are there any issues we 
should be aware of for installing R on the server or with having multiple users 
run R simultaneously? Thanks much!




[[alternative HTML version deleted]]

__
R-help@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.

[R] INSUBSCRIBE

[Lensing, Shelly Y]

On Jan 24, 2023, at 5:00 AM, r-help-requ...@r-project.org wrote:


Send R-help mailing list submissions to r-help@ r-project. org To subscribe or 
unsubscribe via the World Wide Web, visit https: //urldefense. proofpoint. 
com/v2/url?u=https-3A__stat. ethz. 
ch_mailman_listinfo_r-2Dhelp&d=DwIGaQ&c=27AKQ-AFTMvLXtgZ7shZqsfSXu-Fwzpqk4BoASshREk&r=ug-gw1ia3rShGleyKIdg4GIXRt6aKD3u1CM4odHlsvE&m=FCARkfGgHXcSaTZN1f38_6XCbtZ-Lopl641M4MpApMJf7EuJ7y2Y4873aWz38wiY&s=WyAtmOvZqkJ83zE98hkQxz9o1I6k6gYj7KJzInNKmcQ&e=
ZjQcmQRYFpfptBannerStart
This Message Is From an External Sender
This message came from outside your organization.

ZjQcmQRYFpfptBannerEnd

Send R-help mailing list submissions to
r-help@r-project.org

To subscribe or unsubscribe via the World Wide Web, visit

https://urldefense.proofpoint.com/v2/url?u=https-3A__stat.ethz.ch_mailman_listinfo_r-2Dhelp&d=DwIGaQ&c=27AKQ-AFTMvLXtgZ7shZqsfSXu-Fwzpqk4BoASshREk&r=ug-gw1ia3rShGleyKIdg4GIXRt6aKD3u1CM4odHlsvE&m=FCARkfGgHXcSaTZN1f38_6XCbtZ-Lopl641M4MpApMJf7EuJ7y2Y4873aWz38wiY&s=WyAtmOvZqkJ83zE98hkQxz9o1I6k6gYj7KJzInNKmcQ&e=
or, via email, send a message with subject or body 'help' to
r-help-requ...@r-project.org

You can reach the person managing the list at
r-help-ow...@r-project.org

When replying, please edit your Subject line so it is more specific
than "Re: Contents of R-help digest..."


Today's Topics:

   1. Re: Info files in Windows and Mac distributions (Duncan Murdoch)
   2. Re: [EXTERNAL] Re: function doesn't exists but still
  runs. (akshay kulkarni) (Jorgen Harmse)
   3. Re: [EXTERNAL] Re: function doesn't exists but still
  runs. (akshay kulkarni) (akshay kulkarni)
   4. package FactoMineR (varin sacha)
   5. Re: package FactoMineR (Rui Barradas)
   6. Re: Flickering when scrolling in R graphics windows
  (Martin Maechler)
   7. Re: package FactoMineR (PIKAL Petr)

--

Message: 1
Date: Sun, 22 Jan 2023 12:38:13 -0500
From: Duncan Murdoch 
To: Naresh Gurbuxani , R Help

Subject: Re: [R] Info files in Windows and Mac distributions
Message-ID: <6a1cb904-fd30-7686-9f7f-3d28e9b63...@gmail.com>
Content-Type: text/plain; charset="utf-8"; Format="flowed"

On 22/01/2023 12:09 p.m., Naresh Gurbuxani wrote:
> Recently I installed Linux on my desktop.  I discovered that R for Linux 
> ships with info files of manuals.  R for Windows and Mac only ship with html 
> and pdf files of manuals.
>
> Why not include info files in R distributions for Windows and Mac?  These are 
> very convenient with emacs.  Using pandoc , I tried converting from html to 
> info.  The results were nowhere near as good as the originals.

I think the answer to the question is just that there isn't much demand
for them:  emacs is mainly used by Linux users these days.

But the source to the manuals is available, so presumably you could
produce these pretty easily yourself.  The R-devel versions are here:

   
https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_r-2Ddevel_r-2Dsvn_tree_master_doc_manual&d=DwIGaQ&c=27AKQ-AFTMvLXtgZ7shZqsfSXu-Fwzpqk4BoASshREk&r=ug-gw1ia3rShGleyKIdg4GIXRt6aKD3u1CM4odHlsvE&m=FCARkfGgHXcSaTZN1f38_6XCbtZ-Lopl641M4MpApMJf7EuJ7y2Y4873aWz38wiY&s=XnWhnshtwyINVkabbrzkIYLCxHOxWnBrO3Jemc-Mqcw&e=

I don't know whether the .texi files are sufficient for emacs or whether
you need to process them first; I'm not an emacs user.

Duncan Murdoch




--

Message: 2
Date: Mon, 23 Jan 2023 16:01:15 +
From: Jorgen Harmse 
To: "r-help@r-project.org" , akshay kulkarni

Subject: Re: [R] [EXTERNAL] Re: function doesn't exists but still
runs. (akshay kulkarni)
Message-ID:



Content-Type: text/plain; charset="utf-8"

Hi Akshay,

I usually use debug (a function provided by R). When you are stepping through a 
function your environment is the one in which function code is being executed, 
so you can easily see everything that is visible to the function. If you single 
step into a function that the first function calls then you also see everything 
that is available to that function. Moreover, you don't see anything that is 
not visible to the function you are debugging, so you can really determine what 
any piece of code would do if called inside the function.

Note 1: Code in R is always executed in an environment. I show in the example 
below that in the empty environment (the ultimate ancestor of all other 
environments) R can't even add. Usually the current environment (e.g. 
.GlobalEnv at the command line or a fresh environment created by a function 
call) has the right contents and the right parent to do what you expect, but in 
some special cases you need to understand how environments work. Even evalq & 
with are functions (unavailable for example in the empty environment), and the 
environment argument has to be evaluated in the current environment before the 
main expression can be evalua

[R] Different results in glm() probit model using vector vs. two-column matrix response

[Lensing, Shelly Y]

Hi - I am fitting a probit model using glm(), and the deviance and residual 
degrees of freedom are different depending on whether I use a binary response 
vector of length 80 or a two-column matrix response (10 rows) with the number 
of success and failures in each column. I would think that these would be just 
two different ways of specifying the same model, but this does not appear to be 
the case. 

Binary response vector gives:
Residual deviance:  43.209  on 77  degrees of freedom

Two-column matrix response gives:
Residual deviance:  4.9204  on 7  degrees of freedom

I'd like to understand why the two-column response format gives a residual 
degrees of freedom of 7, and why the weights for one is nearly, but not 
exactly, a multiple of the other. I need the deviance, df, and weights for 
another formula, which is why I'm focused on these. My code is below. Thank you 
in advance for any assistance! Shelly



# 10 record set-up
group <- gl(2, 5, 10, labels=c("U","M"))
dose  <- rep(c(7, 8, 9, 10, 11), 2)
ldose <- log10(dose)  
n <- c(8,8,8,8,8,8,8,8,8,8)
r <- c(0,1,3,8,8,0,0,0,4,5)
p <- r/n
d <- data.frame(group, dose, ldose, n, r, p)
SF <- cbind(success=d$r, failure=d$n - d$r)

#80 record set-up
dose2<-c(7,8,9,10,11)
doserep<-sort(rep(dose2,8))
x<-c(doserep,doserep)
log10x<-log10(x)
y_U<-c(rep(0,8), 1, rep(0, 7), 1, 1, 1, rep(0,5), rep(1, 16))
y_M<-c(rep(0,24), rep(1,4), rep(0,4), rep(1,5), rep(0,3))
y<-c(y_U, y_M)
trt<-c(rep(1, 40), rep(0, 40))

# print x & y's for both
SF
y
ldose
log10x

# analysis with 10 records and 80 records
f1 <- glm(SF ~ group + ldose, family=binomial(link="probit"))
f3 <- glm(SF ~ ldose, family=binomial(link="probit"))
f180 <- glm(y ~ trt + log10x, family=binomial(link="probit"))
f380 <- glm(y ~   log10x, family=binomial(link="probit"))

summary(f1)
summary(f180)

f1$weights
f180$weights
# check weights divided by 8 to see if match -- match several decimal places, 
# but not exactly
f1$weights/8



Shelly Lensing
Biostatistics / University of Arkansas for Medical Sciences

Confidentiality Notice: This e-mail message, including a...{{dropped:7}}

__
R-help@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.

[R] Different results in glm() probit model using vector vs. two-column matrix response

[Lensing, Shelly Y]

Hi - I am fitting a probit model using glm(), and the deviance and residual 
degrees of freedom are different depending on whether I use a binary response 
vector of length 80 or a two-column matrix response (10 rows) with the number 
of success and failures in each column. I would think that these would be just 
two different ways of specifying the same model, but this does not appear to be 
the case. 

Binary response vector gives:
Residual deviance:  43.209  on 77  degrees of freedom

Two-column matrix response gives:
Residual deviance:  4.9204  on 7  degrees of freedom

I'd like to understand why the two-column response format gives a residual 
degrees of freedom of 7, and why the weights for one is nearly, but not 
exactly, a multiple of the other. I need the deviance, df, and weights for 
another formula, which is why I'm focused on these. My code is below. Thank you 
in advance for any assistance! Shelly



# 10 record set-up
group <- gl(2, 5, 10, labels=c("U","M"))
dose  <- rep(c(7, 8, 9, 10, 11), 2)
ldose <- log10(dose)  
n <- c(8,8,8,8,8,8,8,8,8,8)
r <- c(0,1,3,8,8,0,0,0,4,5)
p <- r/n
d <- data.frame(group, dose, ldose, n, r, p)
SF <- cbind(success=d$r, failure=d$n - d$r)

#80 record set-up
dose2<-c(7,8,9,10,11)
doserep<-sort(rep(dose2,8))
x<-c(doserep,doserep)
log10x<-log10(x)
y_U<-c(rep(0,8), 1, rep(0, 7), 1, 1, 1, rep(0,5), rep(1, 16))
y_M<-c(rep(0,24), rep(1,4), rep(0,4), rep(1,5), rep(0,3))
y<-c(y_U, y_M)
trt<-c(rep(1, 40), rep(0, 40))

# print x & y's for both
SF
y
ldose
log10x

# analysis with 10 records and 80 records
f1 <- glm(SF ~ group + ldose, family=binomial(link="probit"))
f3 <- glm(SF ~ ldose, family=binomial(link="probit"))
f180 <- glm(y ~ trt + log10x, family=binomial(link="probit"))
f380 <- glm(y ~   log10x, family=binomial(link="probit"))

summary(f1)
summary(f180)

f1$weights
f180$weights
# check weights divided by 8 to see if match -- match several decimal places, 
# but not exactly
f1$weights/8



Shelly Lensing
Biostatistics / University of Arkansas for Medical Sciences

Confidentiality Notice: This e-mail message, including a...{{dropped:7}}

__
R-help@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.