Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: standardizing scores by cohort
From
Nick Cox <[email protected]>
To
"[email protected]" <[email protected]>
Subject
Re: st: standardizing scores by cohort
Date
Wed, 24 Apr 2013 12:32:21 +0100
Statalist software here can't represent the equals sign = in your post
correctly. I guess that, contrary to request, you are not sending
plain text to the list.
That aside
egen mean_math = mean(math), by(yoa)
egen sd_math = sd(math), by(yoa)
gen std_math = (math - mean_math) / sd_math
should be simpler than the dreaded alternative. Note that a -by()-
option is supported, although not documented, by -egen-'s -mean()- and
-sd()- functions, but your indicated syntax
... by yoa
certainly would not work.
Nick
[email protected]
On 24 April 2013 12:15, Paul Byatta <[email protected]> wrote:
> I am trying to standardize raw
> scores for several cohorts of students based on year of admission to high
> school.
>
> My data looks like this
>
>
> StudentID Year of math
> Admission (yoa)
>
> 1 2004 78
> 2 2004 83
> 3 2004 99
> 4 2005 58
> 5 2005 68
> 6 2005 67
> 7 2006 87
> 8 2006 75
> 9 2006 56
>
> It would have been easier to use
>
>
> egen std_math =3D std(math) by yoa
>
> But then egen doesn=92t go with =93by=94 in this case.
>
> Anybody with a suggestion of how standardize the scores without having to
> through the long process that is (below) and combining the generated
> variables to get std_math?
>
>
>
> egen std_math4 =3D std(math) if yoa=3D=3D2004
> egen std_math5 =3D std(math) if yoa=3D=3D2005
> egen std_math6 =3D std(math) if yoa=3D=3D2006
>
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/