[IPAC-List] Question on LXR Software

Joel Wiesen jwiesen at appliedpersonnelresearch.com
Tue Sep 3 10:17:55 EDT 2013

Several people have asked, back-channel, so let me give more detail.

The difference in SPSS and LXR item-total correlations is not due to
including or not including the item in question from the total score.
(The SPSS item-total correlations from the Reliability command exclude
the item from the total.)

The SPSS item-total correlations agree with correlation calculations in
Excel, to many decimal places.

The correlation between the SPSS item-total correlations and the LXR
item-total correlations is .998. However, the mean absolute difference
between the correlations is .05, which is too large to be due to
rounding error. The largest differences between the SPSS and LXR
item-total correlations are more than .10, which is a large difference
for an individual item.

Has anyone had success in verifying the item-total correlations in LXR
against some other software package, or by hand?



- -
Joel P. Wiesen, Ph.D., Director
Applied Personnel Research
62 Candlewood Road
Scarsdale, NY 10583-6040
(617) 244-8859

Note: This e-mail and any attachments may contain confidential and/or
legally privileged information. Please do not forward any contents
without permission. If you have received this message in error please
destroy all copies, completely remove it from your computer, and notify
the sender. Thank you.

On 9/2/13 3:10 PM, Joel Wiesen wrote:

> LXR is giving me item total correlations that I cannot reproduce with

> SPSS or Excel.


> Has anyone run into this?


> Is there something unusual about the way LXR calculates item total

> correlations?


> Thanks.


> Joel





More information about the IPAC-List mailing list