Dear Shane,

I am writing a CPT Identical Pairs (CPT-IP) script in PEBL, and I was a bit confused after read your discussion on d' calculation:
http://sourceforge.net/p/pebl/discussion/281130/thread/d87c5c31/#59e9

I am using PEBL0.13 and d'/beta computations in your pcpt script version 0.6 12/2011 and I get, for instance, in the pcpt report:

Target Acc Rate         0.645
Foil Acc Rate           0.933
Sensitivity (d')        -1.869
Bias (beta)             0.814

but then, if I use your on-line non-parametric Signal detection statistics:
http://mueller-linux.bio.mtu.edu:3838/aprime/

I get:
False Alarm rate: 0.067 (= 1-0.933)
Hit rate: 0.645
        Statistic                       Value
1       Hit rate                        0.645000
2       False alarm rate                0.067000
3       Zhang & Mueller Sensitivity (A) 0.870715
4       Zhang & Mueller bias (b)    1.908517
5       d' sensitivity                  1.870369
6       beta (bias)                     2.868050

What I am really computing in PEBLv0.13 SDTDPrime and SDTBeta functions? Are they correct or not?... or what is my mistake?

Thank you in advance and best regards,

--
Giuseppe Cabras, PhD - Chemistry, Physics and Environment Dept.
InterUniversity Center for Behavioral Neurosciences http://icbn.uniud.it
University of Udine - via delle Scienze, 206 - 33100 UDINE
Phone: +39-043255-8212 - Fax:   +39-043255-8222
SMS:                     http://www.fisica.uniud.it/cabras/SMS.html
URL:                     http://people.uniud.it/page/giuseppe.cabras

Attachment: smime.p7s
Description: Firma crittografica S/MIME

------------------------------------------------------------------------------
Android is increasing in popularity, but the open development platform that
developers love is also attractive to malware creators. Download this white
paper to learn more about secure code signing practices that can help keep
Android apps secure.
http://pubads.g.doubleclick.net/gampad/clk?id=65839951&iu=/4140/ostg.clktrk
_______________________________________________
Pebl-list mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/pebl-list

Reply via email to