[R] Regarding R doubt

[shr@@k m@iii@g oii outiook@com]

Thank you so much for the help !

Sent from Mail<https://go.microsoft.com/fwlink/?LinkId=550986> for Windows 10

________________________________
From: Richard O'Keefe <raoknz using gmail.com>
Sent: Thursday, June 20, 2019 10:41:49 AM
To: shraak using outlook.com
Cc: r-help using r-project.org
Subject: Re: [R] Regarding R doubt

And PL.rasch has what class?
The manual for the 'ltm' package says that 'summary'
"[s]ummarizes the fit of either grm, ltm, rasch or tpm objects."

Download the sources from https://cran.r-project.org/src/contrib/ltm_1.1-1.tar.gz
Unpack the sources.  Look at ltm/R/summary.rasch.R
as that *computes* the summary and ltm/R/print.summ.rasch.R
as that *prints* the summary.

R is a wonderful wonderful tool with a great community and many fine statisticians
contributing code.  Statisticians are not software engineers, so it is no
reflection on the professional competence of the author to say that neither of
these files has any comments.  On the other hand, the code is not very complex.
The files are about one page each.

On Thu, 20 Jun 2019 at 15:49, shraak using outlook.com<mailto:shraak using outlook.com> <shraak using outlook.com<mailto:shraak using outlook.com>> wrote:
library(ltm)
library(psych)

setwd("C:/Users/Admin/Desktop/IRT_CatSim")

irtdat<-read.csv("Fresh_r_2pl.csv",header=F)
head(irtdat)
PL2.rasch<-ltm(irtdat~z1)
summary(PL2.rasch)

plot(PL2.rasch,type=c("ICC"))
plot(PL2.rasch,type=c("IIC"))


Above is the code,When I run summary(PL2.rasch) I will get the following table directly:
Coefficients:
                 value           std.err   z.vals
Dffclt.V1    3.1135       9.8208  0.3170
Dffclt.V2   -0.5157       0.8941 -0.5768
�
Discrm.V1   -1.3585       3.2062 -0.4237
Discrm.V1   -1.0032    8649.3103 -0.0001
�

Working on Item response theory and I�m struggling at calculating above values manually.
You will get this difficulty and discrimination values directly, I just want the simple formulas to calculate item difficulty and item discrimination.
Also how they have calculated theta(ability) and scores at the backend of the code.


Sent from Mail<https://go.microsoft.com/fwlink/?LinkId=550986> for Windows 10

________________________________
From: Richard O'Keefe <raoknz using gmail.com<mailto:raoknz using gmail.com>>
Sent: Thursday, June 20, 2019 2:18:26 AM
To: shraak using outlook.com<mailto:shraak using outlook.com>
Cc: r-help using r-project.org<mailto:r-help using r-project.org>
Subject: Re: [R] Regarding R doubt

You did not say what your doubt about R was.
PL2.rasch has some class.
> class(PL2.rasch)
[1] 'Grofnigtz'   # or whatever
The summary function is really just a dispatcher.
> summary.Grofnigtz
... a listing comes out here ...

Or you could look in the source code of whatever package you are usin.


On Thu, 20 Jun 2019 at 00:25, shraak using outlook.com<mailto:shraak using outlook.com> <shraak using outlook.com<mailto:shraak using outlook.com>> wrote:
Hello Team,
I hope you are doing well.
I have one doubt about backend functioning of R command.
Currently I'm working on IRT analysis in python but this function is implemented in R and in R they have direct rasch model library but no such library in the Python.

So I wanted to know that is there any way to find the math or formula behind the specific command of R language.
for eg, summary(PL2.rasch)
after this command you will directly get difficulty and discrimination values like mentioned below:

Coefficients:
                 value           std.err   z.vals
Dffclt.V1    3.1135       9.8208  0.3170
Dffclt.V2   -0.5157       0.8941 -0.5768
Dffclt.V3   -1.3585       3.2062 -0.4237
Dffclt.V4   -1.0032    8649.3103 -0.0001
Dffclt.V5    0.0400    1350.8452  0.0000

So is there any way to find out the math behind this summary command ?

Thanks,
Shreepad



        [[alternative HTML version deleted]]

______________________________________________
R-help using r-project.org<mailto:R-help using 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.

	[[alternative HTML version deleted]]