Many Thanks Phil for the reply; everything worked just as I
hoped!
Clint
On 9 Nov 2003 at 0:27, Philip Ryan wrote:
> Clint
>
> It's a little hard to be sure exactly how to approach this most
> efficiently as your data all *appear* as strings, but of course may just
> be labels hiding numbers. In what follows I will assume that the outcome
> variables (q1_1 and q1_2) are in fact numeric - otherwise you won't be
> able to do a signed rank test - but if they are strings you had better
> first change them to numeric. I will however assume that the variable
> "eye" holding values "OD" and "OS" is string, only because this leads to
> a demonstration of a required extra option in the -reshape- command.
> (may one guess that "OD" signifies the right - dextra- eye, and "OS" the
> left - sinistra - eye??).
>
> Anyway, assuming that "None" for the outcome variables might really be a
> score of 0 in some, at least ordinal, scoring system:
>
> . list , nolabel
>
> +------------------------------------------+
> | jmec_no eye iol q1_1 q1_2 sex |
> |------------------------------------------|
> 1. | 30332 OD SA60 0 0 F |
> 2. | 30332 OS AR40 0 0 F |
> 3. | 46199 OD SA60 0 0 F |
> 4. | 46199 OS AR40 0 0 F |
> +------------------------------------------+
>
> then
>
> . reshape wide iol q1*, i(jmec_no) j(eye) string
> (note: j = OD OS)
>
> Data long -> wide
> ------------------------------------------------------------------------
> ----- Number of obs. 4 -> 2 Number of
> variables 6 -> 8 j variable (2 values)
> eye -> (dropped) xij variables:
> iol -> iolOD iolOS
> q1_1 -> q1_1OD q1_1OS
> q1_2 -> q1_2OD q1_2OS
> ------------------------------------------------------------------------
> -----
>
> Note that:
>
> 1. I had to specify the -string- option, because the j index is
> ordinarily expected to be numeric.
>
> 2. I had to either drop the iol variable or (as I ended up choosing)
> include it in the list of variables I wanted reshaped, since iol is not
> constant within
>
> each case identifier.
>
>
> . list, nolabel
>
> +------------------------------------------------------------------
> -+ | jmec_no iolOD q1_1OD q1_2OD iolOS q1_1OS q1_2OS
> sex |
> |------------------------------------------------------------------
> -|
> 1. | 30332 SA60 0 0 AR40 0 0 F
> | 2. | 46199 SA60 0 0 AR40 0 0
> F |
> +------------------------------------------------------------------
> -+
>
> and, given some more data to make it sensible, one could:
>
> . signrank q1_1OD = q1_1OS
>
> to do a paired test on outcome q1_1 between eyes, and
>
> . signrank q1_2OD = q1_2OS
>
> to do the same on outcome q1_2
>
>
> Phil
>
>
> Quoting [email protected]:
>
> > Greetings STATA-listers,
> > I have a dataset examining eye surgeries and I want to examine
> > how responses to certain variables (e.g. q1_1, q1_2, etc.)
> > between each eye vary. The problem is, my dataset is
> > structured as pasted below:
> >
> > +------------------------------------------+
> > | jmec_no eye iol sex q1_1 q1_2 |
> > |------------------------------------------|
> > 1. | 30332 OD SA60 F None None |
> > 2. | 30332 OS AR40 F None None |
> > 3. | 46199 OD SA60 F None None |
> > 4. | 46199 OS AR40 F None None |
> > +------------------------------------------+
> >
> > How do I restructure the dataset so that the Wilcoxon sign rank
> > test can be performed?? That is, I recognize that I need to
> > reshape it or create an array or do some manipulation, but I am
> > at a loss as how to proceed (even after a perusal of the
> > reference manual and STATA help feature) - any suggestions?
> >
> > Many thanks,
> > Clint Thompson
> > *
> > * For searches and help try:
> > * http://www.stata.com/support/faqs/res/findit.html
> > * http://www.stata.com/support/statalist/faq
> > * http://www.ats.ucla.edu/stat/stata/
> >
>
>
> --
> Philip Ryan
> Associate Professor
> Department of Public Health
> University of Adelaide
> 5005 South Australia
> AUSTRALIA
> CRICOS Provider Number 00123M
> -----------------------------------------------------------
> This email message is intended only for the addressee(s)
> and contains information that may be confidential and/or
> copyright. If you are not the intended recipient please
> notify the sender by reply email and immediately delete
> this email. Use, disclosure or reproduction of this email
> by anyone other than the intended recipient(s) is strictly
> prohibited. No representation is made that this email or
> any attachments are free of viruses. Virus scanning is
> recommended and is the responsibility of the recipient.
> *
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
