other challenging concepts:

heritability
discriminative stimuli


>>> "Paul C Bernhardt" <[email protected]> 04/20/10 8:00 PM >>>
Thanks for the various responses to the Biserial question.  I love that I learn 
new things every day!

Challenging Concepts to Teach:
         Sleeper Effect (persuasion)
         Kelley's Covariation Theory (attributions)

Paul C. Bernhardt
Department of Psychology
Frostburg State University
Frostburg, Maryland



-----Original Message-----
From: Jim Clark [mailto:[email protected]]
Sent: Tue 4/20/2010 4:20 PM
To: Teaching in the Psychological Sciences (TIPS)
Subject: Re: [tips] Top 10 challenging concepts
 
Hi

Confusion might be between biserial corr and point-biserial.  Latter is simply 
standard r between dichotomous variable X and quantitative variable Y.  Hence, 
does not violate standard conditions for Pearson r.

Biserial, however, attempts to estimate from dichotomized quantitative variable 
X and quantitative variable Y what the r would be for quantitative X.  Whatever 
procedure is used can produce r > 1, as alluded to below as the "the well known 
fact that r* can be greater than 1" (albeit not well known by me until this 
discussion).

http://biomet.oxfordjournals.org/cgi/pdf_extract/42/1-2/205

Take care
Jim


James M. Clark
Professor of Psychology
204-786-9757
204-774-4134 Fax
[email protected]

>>> Paul Bernhardt <[email protected]> 20-Apr-10 2:42:49 PM >>>
I am skeptical that the Biserial correlation can exceed an absolute value of 1. 
Can you provide an example in which it does that? 

Paul Bernhardt
Dept of Psychology
Frostburg State University
pcbernhardt _at_ frostburg _dot_ edu


On Apr 20, 2010, at 8:44 AM, Wuensch, Karl L wrote:

>  
> 
>             Actually, there are some correlation coefficients that can exceed 
> one (the biserial, for example).
>  
>             Tell your students to square r before comparing one with another. 
>  Give them a set of data and the plot and the accompanying negative r.  Then 
> invert or reflect one of the variables and present the plot and positive r.  
> They should get the message then.
>  
>             Try a criminal courtroom analogy.  Assume innocence.  Type I = 
> convict an innocent defendant.  Type II = let a criminal get off.
>  
> Cheers,
>  
> Karl W.
>  
> From: [email protected] [mailto:[email protected]] 
> Sent: Monday, April 19, 2010 8:43 AM
> To: Teaching in the Psychological Sciences (TIPS)
> Subject: Re: [tips] Top 10 challenging concepts
>  
>  
> 
> A couple of editorial comments (unwanted I am sure but I don't care):
>  
>  
> differentiating between the phallic and genital stage 
> Since there is very little validity or empirical support for Freud's 
> theoretical constructs of development and personality, 
> I would say that there is no need to waste precious class time on this 
> distinction m-
> It helps the modern scientific psychologist not at all...
> Let the English, Philosophy or History prof deal with it.
>  
> >  -why a -7.0 correlation coefficient is more significant than a +5.0  There 
> > are no such things as 
> a -7.0 correlation coefficient or a 5.0 one. All "r"s range between -1.00 and 
> +1.00
>  
>  
>  
>  
> 
> Nancy Melucci
> Long Beach City College
> Long Beach CA
> 
> -----Original Message-----
> From: Mike Palij <[email protected]>
> To: Teaching in the Psychological Sciences (TIPS) <[email protected]>
> Cc: Mike Palij <[email protected]>
> Sent: Sun, Apr 18, 2010 10:19 pm
> Subject: re: [tips] Top 10 challenging concepts
> 
> On Sun, 18 Apr 2010 16:06:30 -0700, Michael Sylvester wrote:
> >I am attempting to compile a list of the top 10 challenging concepts 
> >to explain to students.So far I have come up with the following from 
> >my courses:
> >  -Type 1 and type 2 error
> >  - differentiating between the phallic and genital stage
> >  -negative reinforcement
> >  -positive punishment
> >  -why a -7.0 correlation coefficient is more significant than a +5.0
> >  - assimilation and accomodation in Piagetian theory
> >  - diathesis stress theory of schizophrenia
>  
> Why do fools fall in love?
>  
> -Mike Palij
> New York University
> [email protected] 
>  
> P.S. Do Sylvesterian correlation coefficients exceed +/- 1.00?
> If so, how are they calculated?
>  
>  
> ---
> You are currently subscribed to tips as: [email protected].
> To unsubscribe click here: 
> http://fsulist.frostburg.edu/u?id=12993.aba36cc3760e0b1c6a655f019a68b878&n=T&l=tips&o=2094
>  
> or send a blank email to 
> leave-2094-12993.aba36cc3760e0b1c6a655f019a68b...@fsulist.frostburg.edu 
> ---
> 
> You are currently subscribed to tips as: [email protected].
> 
> To unsubscribe click here: 
> http://fsulist.frostburg.edu/u?id=13060.c78b93d4d09ef6235e9d494b3534420e&n=T&l=tips&o=2098
>  
> 
> (It may be necessary to cut and paste the above URL if the line is broken)
> 
> or send a blank email to 
> leave-2098-13060.c78b93d4d09ef6235e9d494b35344...@fsulist.frostburg.edu 
> 
> 
> ---
> 
> You are currently subscribed to tips as: [email protected].
> 
> To unsubscribe click here: 
> http://fsulist.frostburg.edu/u?id=13441.4e79e96ebb5671bdb50111f18f263003&n=T&l=tips&o=2109
>  
> 
> (It may be necessary to cut and paste the above URL if the line is broken)
> 
> or send a blank email to 
> leave-2109-13441.4e79e96ebb5671bdb50111f18f263...@fsulist.frostburg.edu 
> 







---
You are currently subscribed to tips as: [email protected].
To unsubscribe click here: 
http://fsulist.frostburg.edu/u?id=13251.645f86b5cec4da0a56ffea7a891720c9&n=T&l=tips&o=2115
 
or send a blank email to 
leave-2115-13251.645f86b5cec4da0a56ffea7a89172...@fsulist.frostburg.edu

---
You are currently subscribed to tips as: [email protected].
To unsubscribe click here: 
http://fsulist.frostburg.edu/u?id=13441.4e79e96ebb5671bdb50111f18f263003&n=T&l=tips&o=2116
or send a blank email to 
leave-2116-13441.4e79e96ebb5671bdb50111f18f263...@fsulist.frostburg.edu


---
You are currently subscribed to tips as: [email protected].
To unsubscribe click here: 
http://fsulist.frostburg.edu/u?id=13058.902daf6855267276c83a639cbb25165c&n=T&l=tips&o=2120
or send a blank email to 
leave-2120-13058.902daf6855267276c83a639cbb251...@fsulist.frostburg.edu

---
You are currently subscribed to tips as: [email protected].
To unsubscribe click here: 
http://fsulist.frostburg.edu/u?id=13090.68da6e6e5325aa33287ff385b70df5d5&n=T&l=tips&o=2139
or send a blank email to 
leave-2139-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu

Reply via email to