Thank, Jim to look to my post . I dont explain pass/fail by the exam score but
I want to explain both of them by a set of explanotory variables.
y_{i}=a_{0}+\sum_{i}a_{i}x_{i}
or P(z_{i}=k)=F(a_{0}+\sum_{i}a_{i}x_{i}) z_{i}=1(c_{k}<y<c_{k+1}
I want to know if there is a great difference? which are the advantage for the
each other compared to another.
Justin BEM
Elève Ingénieur Statisticien Economiste
BP 294 Yaoundé.
Tél (00237)9597295.
----- Message d'origine ----
De : Jim Lemon <[EMAIL PROTECTED]>
À : justin bem <[EMAIL PROTECTED]>
Envoyé le : Mardi, 24 Avril 2007, 11h10mn 01s
Objet : Re: [R] statistical modelling skill
justin bem wrote:
> Dears helpers,
>
> I have a question not specially about R, but about statistical modelling.
> This is the problem, I want to conduct a regression analysis to explain the
> causes of students fail in an exam. I have two variables the score obtain at
> the exam and the categorical variable coding 0 in case of fail and 1 in case
> of success, on a panel data. I am interest to know what made a student who
> usually succeed start to fail. So I have two possibilty : linear regression
> analysis with the score or a probit model with the fail indicator.
>
> In my view, the result will be similary. but is there any difference? what
> the advantage off choosing one the two approaches ?
Hi Justin,
I'm probably missing something, but I can't see how predicting pass/fail
with the exam score will reveal anything other than the minimum passing
grade. There is an awful lot of work in this field, typically measuring
everything from the student's birth weight to the number of bars they
visit while at college. However, the generalized linear model is your
tool, using the binomial link function.
Jim
___________________________________________________________________________
[[alternative HTML version deleted]]
______________________________________________
[email protected] 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.
