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 on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: Bonferroni-holm


From   Sadjad Riahi <sadjad.riahi@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Bonferroni-holm
Date   Sun, 19 Aug 2012 19:43:15 +0430

dear billy,

thank you very much for the advice. my part of analysis is not
voxel-wise but volumetric analysis so I have about 16 volumes to test.
Thank you for your advice, I will try what you said.
thank you very much again,
sadjad

On Sun, Aug 19, 2012 at 7:24 PM, William Buchanan
<william@williambuchanan.net> wrote:
> Hi Sadjad,
>
> While Tony had suggested reading a book on multiple comparisons, I'm not sure that would get you all the way to the answer that you need.  Depending on the voxel size that was used for your scan, it is possible to have upwards of 30,000 dependent variables; in this case to reach a significant finding using a typical Bonferroni correction you would need to observe a p value of less than 0.00000167.  I'm not aware of any user written programs in Stata that are used for neuroimaging analysis, so I would suggest you may have an easier time doing this by using software designed for this type of analysis.  Off the top of my head, I know there there are some modules in R for this, there are also a series of routines written in Python that are fairly common, and then there are commercially available packages in MatLab (among others).  If you do a search for ANFI (another freely distributed package) you can probably find a link that would direct you to many of the programs funded b!
 y !
>  NIH for the development of neuroimaging analyses.
>
> Has your data already been cleaned/prepped?  If not that is an incredibly time consuming task that you should focus on first.
>
> HTH,
> Billy
>
> Sent from my iPhone
>
> On Aug 19, 2012, at 7:26, Sadjad Riahi <sadjad.riahi@gmail.com> wrote:
>
>> dear billy,
>> thank you for your kind reply.Please accept my apologies if the
>> question sounds silly but I am a medical student and newbie in the
>> field of research and this is my first project, I have searched hard
>> for this on the web but no luck.the original paper is: Rimol LM,
>> Hartberg CB, Nesvag R, et al. Cortical thickness and subcortical
>> volumes in schizophrenia and bipolar disorder. Biol Psychiatry
>> 2010;68:41-50. it has done the analysis via SPSS which I know there is
>> no such correction option in SPSS.
>> yours,
>> Sadjad Riahi
>>
>> On Sun, Aug 19, 2012 at 6:22 PM, William Buchanan
>> <william@williambuchanan.net> wrote:
>>> Hi Sadjad,
>>>
>>> As stated in the FAQ, you are instructed to provide full references to material when referencing anything.  Additionally, the correction methods used in neuroimaging analyses are likely to differ to some degree compared with those used in social sciences, since it is much less likely that someone in the social sciences would be working with several tens of thousands of dependent variables simultaneously.  Most software for neuroimaging analyses will have built in support for these corrections (at least Brain Voyager does).  It would be helpful to provide more explicit detail to the list if you would like any reasonable advice.
>>>
>>> HTH,
>>> Billy
>>>
>>> Sent from my iPhone
>>>
>>> On Aug 19, 2012, at 6:33, Sadjad Riahi <sadjad.riahi@gmail.com> wrote:
>>>
>>>> dear statalist,
>>>> I have found In a paper with the similar methodology with ours that
>>>> for correction of multiple comparisons, authors have applied
>>>> bonferroni-holm correction. To explain the analysis in short, they
>>>> have several dependent variable (subcorticalgray matter  region
>>>> volumes) and three groups of diagnosis, intracranial volumes,age and
>>>> sex as predictor variables.they have fitted a GLM for each region
>>>> volume as the dependant variable seperately, then F test was preformed
>>>> and subsequently contrast analysis. but for multiple comparison they
>>>> first corrected for the omnibus test and then correction for pairwise
>>>> comparison for each GLM that survived the first round of correction
>>>> was performed. Can you please enlighten me with this correction
>>>> procedure more in detail.
>>>>
>>>> yours,
>>>>
>>>> Sadjjad Riahi
>>>> *
>>>> *   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/
>>>
>>> *
>>> *   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/
>>
>> *
>> *   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/
>
> *
> *   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/

*
*   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