--------------6F47CB3D3B10A10A3E9B064C
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
An "outlier" is any value for a variable that is suspect given the
measurement system, "common sense", other values for the variable in
the data set, or the values a case has on other variables.
Yes, an outlier can be low given the measurement system and the values
for the other cases in the data set.
BUT In my experience an outlier usually means that proper quality
assurance has not been done on the data set. Before doing anything
else, QA procedures should be redone before doing the actual analysis on
a data set. Go back and look at the measurement situation. Consider
redoing the data entry.
ve person.
some examples of "out of defined range" values
a ranking of 11 would be impossible if there are 10 stimuli to be
ranked.
An average of 3 judges on a 1 to 5 response scale cannot be 3.5.
169 would be an unreasonable number of hours to claim to work in a week.
--------------6F47CB3D3B10A10A3E9B064C
Content-Type: text/html; charset=us-ascii
Content-Transfer-Encoding: 7bit
<!doctype html public "-//w3c//dtd html 4.0 transitional//en">
<html>
An "outlier" is any value for a variable that is suspect given the measurement
system, "common sense", other values for the variable in the data
set, or the values a case has on other variables.
<p>Yes, an outlier can be low given the measurement system and the values
for the other cases in the data set.
<p>BUT In my experience an outlier <b>usually</b> means that proper quality
assurance has not been done on the data set. Before doing anything
else, QA procedures should be redone before doing the actual analysis on
a data set. Go back and look at the measurement situation. Consider
redoing the data entry.
<p>ve person.
<p>some examples of "out of defined range" values
<br>a ranking of 11 would be impossible if there are 10 stimuli to be ranked.
<br>An average of 3 judges on a 1 to 5 response scale cannot be 3.5.
<br>169 would be an unreasonable number of hours to claim to work in a
week.</html>
--------------6F47CB3D3B10A10A3E9B064C--
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at
http://jse.stat.ncsu.edu/
=================================================================
