Removing within-subject & within-session outliers in EdataAid

[tudor]

Thanks David. PST support have suggested the same thing, i.e. removing 
outliers based on an arbitrary threshold. However, I think I'd nevertheless 
like to try removing them by using a number of std devs away from the mean. 
I'm not sure this could be done in Excel or SPSS (at least without a macro, 
which I don't personally know much about), given that what you export there 
are just raw RTs (one trial per row, for all sessions and for all 
subjects). To eliminate outliers within each subject's session, it seems to 
me that you'd really have to write a Matlab script to use on the exported 
Excel file. Since eliminating RTs this way is such a basic (and commonly 
done) operation, it is regrettable that it is not included in Edataaid's 
Analyze window. Perhaps in a future version...

On Tuesday, 8 October 2013 00:10:38 UTC+1, McFarlane, David wrote:
>
> To eliminate all RTs greater than a certain fixed value, just use a 
> filter in E-DataAid, or in the Analyze tool of E-DataAid -- I am 
> pretty sure that this is covered in the tutorial Guides that came 
> with E-Prime (and I also cover this in my online course). 
>
> If you want custom filters for individual subjects or for individual 
> sessions of each subject, or if you want the filter criterion to be 
> derived from some computation based on the data, then I think you 
> will have to use another tool, as far as I know those sorts of 
> analyses go beyond what E-DataAid can do and what it is meant to 
> do.  As you already know, E-DataAid will easily reveal mean RTs for 
> each subject, or for each session of each subject, but from there you 
> have to explort data and do the rest in Excel, SPSS, Systat, or what have 
> you. 
>
> I do like E-DataAid and its Analyze feature a lot for initial data 
> preparation (e.g., filtering rows and selecting columns to export) 
> and for initial exploration of descriptive statistics, and I devote 
> one lesson in my online course to covering these uses, but after that 
> I would export the data for further analysis (e.g., hypothesis 
> testing, ANOVA, etc.). 
>
> Just my $.02, curious to hear from others. 
>
> ----- 
> David McFarlane 
> E-Prime training 
> online:  http://psychology.msu.edu/Workshops_Courses/eprime.aspx 
> Twitter:  @EPrimeMaster (https://twitter.com/EPrimeMaster) 
>
> /---- 
> Stock reminder:  1) I do not work for PST.  2) PST's trained staff 
> take any and all questions at https://support.pstnet.com , and they 
> strive to respond to all requests in 24-48 hours, so make full use of 
> it.  3) In addition, PST offers several instructional videos on their 
> YouTube channel (http://www.youtube.com/user/PSTNET ).  4) If you do 
> get an answer from PST staff, please extend the courtesy of posting 
> their reply back here for the sake of others. 
> \---- 
>
>
> At 10/7/2013 04:27 PM Monday, tudor wrote: 
> >I have a merged .emrg2 (EdataAid) file containing reaction time data 
> >from several subjects, across several sessions done by each. I would 
> >like to eliminate RT outliers within each subject individually, and 
> >if possible also within session rather than across all sessions of a 
> >single subject. 
> > 
> >By 'outlier' I would mean RTs that are more than 2.5 standard 
> >deviations away from the mean, although if that's hard to do, it 
> >would also be fine to just eliminate all RTs greater than a certain 
> >fixed value (e.g. 3,000 ms). 
> > 
> >I have not found a way to do this with the Analyze window, and 
> >because I have many such merged files, I would prefer to not have to 
> >do this 'the hard way', i.e. by exporting all the data to Excel and 
> >doing the outlier-removal and the averaging (which is otherwise done 
> >easily in Analyze) over there. 
> > 
> >Can anyone help? Many thanks in advance! 
>
>

-- 
You received this message because you are subscribed to the Google Groups "E-Prime" group.
To unsubscribe from this group and stop receiving emails from it, send an email to e-prime+unsubscribe at googlegroups.com.
To post to this group, send email to e-prime at googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/e-prime/2d83b3af-964a-422c-b7d9-95c7e2e85436%40googlegroups.com.
For more options, visit https://groups.google.com/groups/opt_out.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/eprime/attachments/20131009/c7d2db10/attachment.htm>