st: R: Does there exist measurement error when I got high Cronbach's alpha?

["Carlo Lazzaro" <carlo.lazzaro@tin.it>]

Sharon wrote:

"Another question is about the computation of Cronbach's alpha. I got
different values of alpha when using different computation procedure: the
key difference happened when I recoded the responses of five factors
personality to "missing values" when the original responses were "-3" (i.e.
no questions answered) or "-2" (i.e. information incomplete)."

As far as this portion of your message is concerned, I would recommend you
to discover which kind of missing mechanism underlies your missing data.
Missing data mechanism is probably the substantive topic and, missing data,
the reason why you are faced with different values of Cronbach's alphas (or
of whatever statistc you're interested in). I would figure out that you
might have missing at random (MAR) or missing non at random (MNAR or
NMAR)observations. Problems with managing missing data usually arise when
they are MNAR.  

For further details on this topic, I take the liberty to refer you to the
following references:

Little RJA, Rubin DR. Statistical analysis with missing data. 2nd ed.
Chichester: Wiley, 2002;
Allison PD. Missing data. Thousand Oaks, CA: Sage Publications, 2002;
Royston, P. 2004. Multiple imputation of missing values. Stata Journal 4(3):
227-241.
Royston, P. 2005. Multiple imputation of missing values: update. Stata
Journal 5(2): 1-14.

Kindest Regards,
Carlo
-----Messaggio originale-----
Da: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Per conto di xueliansharon
Inviato: sabato 16 luglio 2011 14.47
A: statalist@hsphsun2.harvard.edu
Oggetto: st: Does there exist measurement error when I got high Cronbach's
alpha?

Dear all:

I got quite high Cronbach's alphas (0.9) for five-factor personality traits
(extraversion, agreeableness, conscientiousness, emotional stability and
intellect). With such high values, can I argue that there may still exist
measurement errors in the measures for five-factor personality traits?

Another question is about the computation of Cronbach's alpha. I got
different values of alpha when using different computation procedure: the
key difference happened when I recoded the responses of five factors
personality to "missing values" when the original responses were "-3" (i.e.
no questions answered) or "-2" (i.e. information incomplete). For example,
for the extraversion measure, the range of the score should be 5 to 50
points, when I recoded the response "-3" or "-2" to "missing value", the
sample size was reduced by around 680, since the number of observations who
didn't answer the questions about extraversion or didn't provide complete
information for each item were 680, and the alpha coefficient fell from 0.9
to 0.6. So is it correct to do such recoding when computing alpha
coefficients?

Your response is greatly appreciated.

Thanks & Regards,
Sharon

--
View this message in context:
http://statalist.1588530.n2.nabble.com/Does-there-exist-measurement-error-wh
en-I-got-high-Cronbach-s-alpha-tp6589508p6589508.html
Sent from the Statalist mailing list archive at Nabble.com.
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/