That would make too much sense (for the APA).  By the way, the sample 
standard deviation (n-1) is a biased estimator, but the sample variance (n-1) 
is unbiased.

Cheers,
 
Karl W.

-----Original Message-----
From: Paul C Bernhardt [mailto:[email protected]] 
Sent: Friday, October 15, 2010 7:13 PM
To: Teaching in the Psychological Sciences (TIPS)
Subject: RE: [tips] Statistical Symbols, APA Style

I don't think it is very clear and I believe that we should err on the side of 
historical continuity. Given the long history of SD being used for sample 
standard deviation, lacking an explicit notation that SD is now reserved for 
biased estimate (denominator n), I would say that both are acceptable for 
sample standard deviations. Note that there is an explicit listing for biased 
variance. 

Imagine if the intent was to change to SD being biased estimator now but 
formerly was unbiased estimator. A reader would need to keep track of when each 
journal made the switch. Very bad form. 

Better would be to eliminate SD as an acceptable abbreviation, use a capital S 
for biased estimator and lower case s for unbiased estimator. 

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



-----Original Message-----
From: Wuensch, Karl L [mailto:[email protected]]
Sent: Fri 10/15/2010 5:46 PM
To: Teaching in the Psychological Sciences (TIPS)
Subject: [tips] Statistical Symbols, APA Style
 
            In Table 4.5 of the latest edition of the APA Pub Manual it says to 
use "s" for "sample standard deviation (denominator sqrt(n-1)).  This is new to 
this edition.  This table still includes "SD" for "standard deviation" 
(presumably with n in the denominator).
            Since n-1 is almost always used, rather than n, in the standard 
deviation that is reported in research manuscripts, one would think that SD 
would pretty much vanish from use.  Have APA journals actually shifted from SD 
to s, and have those who teach APA style?

Cheers,
________________________________

[cid:[email protected]]

Karl L. Wuensch, Professor and ECU Scholar/Teacher, Dept. of Psychology
East Carolina University, Greenville NC  27858-4353, USA, 
Earth<http://core.ecu.edu/psyc/wuenschk/Earth.htm>
Voice:  252-328-9420     Fax:  252-328-6283
[email protected]<mailto:[email protected]>
http://core.ecu.edu/psyc/wuenschk/klw.htm


---
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=5712
or send a blank email to 
leave-5712-13441.4e79e96ebb5671bdb50111f18f263...@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=5737
or send a blank email to 
leave-5737-13090.68da6e6e5325aa33287ff385b70df...@fsulist.frostburg.edu

Reply via email to