Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Repeated measured analysis


From   Austin Nichols <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Repeated measured analysis
Date   Fri, 12 Aug 2011 11:34:44 -0400

Marlis Gonzalez Fernandez <mgonzal5@jhmi.edu>:
See for starters [R] permute and refs therein.

On Fri, Aug 12, 2011 at 10:52 AM, Marlis Gonzalez Fernandez
<mgonzal5@jhmi.edu> wrote:
> Austin-
>
> So your suggestion is to analyze food types separately and then compare?
> I am not familiar with randomization/permutation tests.
>
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Austin Nichols
> Sent: Wednesday, August 10, 2011 5:04 PM
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: Repeated measured analysis
>
> Marlis Gonzalez Fernandez <mgonzal5@jhmi.edu>:
> The suggestion was to use a cluster-robust standard error, used by
> -svy- and -suest- and many other commands, which would normally be my
> first thought as well. Unfortunately, with 13 clusters, the CRSE will
> be severely biased downward.
> Probably better with such a small sample size to analyze each type
> separately, using a randomization/permutation test.
>
> On Wed, Aug 10, 2011 at 1:30 PM, Marlis Gonzalez Fernandez
> <mgonzal5@jhmi.edu> wrote:
>> Thank you Ronán-
>>
>> I agree looking not only at food but the interaction between food and disease will be really intresting...
>>
>> Thanks for the suggestions.
>>
>> Marlis
>>
>> -----Original Message-----
>> From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Ronan Conroy
>> Sent: Wednesday, August 10, 2011 12:15 PM
>> To: statalist@hsphsun2.harvard.edu
>> Subject: Re: st: Repeated measured analysis
>>
>> On 2011 Lún 10, at 16:44, Marlis Gonzalez Fernandez wrote:
>>
>>> Hello-
>>>
>>> Trying to help a colleague who has an interesting study.
>>>
>>> He has distance of movement (hyoid bone) measures in mm on 13 subjects with no less than 20 measures (some have many more than that) during swallowing 3 different foods (so lots of repeats!). He wants to determine if there are significant distance differences between normal and disease states (while taking into account food type). I was concerned about having so many repeated measures and appropriately accounting for that to discern where is the true variability (ie. disease state?  Subject?).  Any ideas welcome.maybe I am over-thinking this?  Should he just analyze food types separately?
>>
>> Why not -svyset- with participant as the PSU?
>>
>> The interesting question was whether food type interacted with disease status. In achalasia, difficulty swallowing varies considerably by food type, and this may be true for other disorders of swallowing too - it's not my area - but I'd have a look at the interaction term.

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index