Need a sensitivity measure for subjects

[Inliner]

I am a psychologist working on developing an estimate if intra-subject
sensitivity based on hit rates (0 versus 1)  on a series of targets.
Each target has prescribed signal strength and noise is not directly
manipulated or measures.  I need a way to assign a sensitivity level
to subjects based on their percent of hits (1’s). Each target has
different signal strength as follows..

0.50 ,   .66,   .83,   1,   1.16,   1.33,   1.5,   1.66,   1.83.

Subjects are presented with 10 to 20 target opportunities and receive
a 1 for correct and a 0 for incorrect detection of the signals.

I want to assign a single measure of sensitivity to each subject based
on hits at the various levels of the signal strength.  Each target
does have an indirect measure of “noise” in the form of subject matter
expert agreement as to the true level of the signal strength. So for
example, a certain target may have perfect SME agreement and thus
theoretically have no noise while another may have 10% SME
disagreement as to its true signal strength and thus have that degree
of noise.

Any assistance any one could offer would be very much appreciated.

Peter

-- 
You received this message because you are subscribed to the Google Groups "E-Prime" group.
To post to this group, send email to e-prime at googlegroups.com.
To unsubscribe from this group, send email to e-prime+unsubscribe at googlegroups.com.
For more options, visit this group at http://groups.google.com/group/e-prime?hl=en.