Login  Register

Re: Christine Blasey (Ford) - regression after centering

Posted by Rich Ulrich on Sep 24, 2018; 11:30pm
URL: http://spssx-discussion.165.s1.nabble.com/Christine-Blasey-Ford-regression-after-centering-tp5736683p5736697.html

I'm happy to center only for computing the interactions, to avoid getting
statistics on the page (from confounding) that I have to go out of my way to explain.

According to her Wikipedia article, which is all of a week old,
"she specializes in designing statistical models for research projects".

--
Rich Ulrich

From: SPSSX(r) Discussion <[hidden email]> on behalf of Bruce Weaver <[hidden email]>
Sent: Monday, September 24, 2018 4:26 PM
To: [hidden email]
Subject: Re: Christine Blasey (Ford) - regression after centering
 
Hi Rich.  When I search my articles folder for <Kraemer>, I find several
articles, but not that one.  I was aware of it, because I'd noticed it when
looking at Christine Blasey's Google Scholar profile:

  https://scholar.google.ca/citations?user=J2T7HxgAAAAJ&hl=en

Re centering variables prior to regression analysis, I'm generally less
enthusiastic about it than I used to be.  Occasionally, it may be necessary
to deal with numerical problems that arise.  But generally, if one has
software that makes it easy to compute and plot marginal values of Y, those
tables and plots are far more useful than the table of coefficients is in
helping a reader understand the nature of the model.



Rich Ulrich wrote
> I wondered what sort of research psychologist she is, when I saw that the
> accuser
> of Kavanaugh was one. Apparently, she is the less common sort of
> psychologist, one
> who is comfortable with numbers.
>
> Christine Blasey (Ford) has published with Helena Kraemer a couple of
> times. She is
> the co-author on the 2nd edition of Kraemer's book on power analysis, and
> on an
> article about regression. I don't know if this is an article that Bruce
> has recommended
> previously, but the abstract looks pertinent to many SPSS users.
>
> Int J Methods Psychiatr
> Res.&lt;https://www.ncbi.nlm.nih.gov/pubmed/15297898#&gt;
> 2004;13(3):141-51.  Centring in regression analyses: a strategy to prevent
> errors in statistical inference.  Kraemer
> HC&lt;https://www.ncbi.nlm.nih.gov/pubmed/?term=Kraemer%20HC%5BAuthor%5D&amp;cauthor=true&amp;cauthor_uid=15297898&gt;1,
> Blasey
> CM&lt;https://www.ncbi.nlm.nih.gov/pubmed/?term=Blasey%20CM%5BAuthor%5D&amp;cauthor=true&amp;cauthor_uid=15297898&gt;.
>
> --
> Rich Ulrich
>
>
> =====================
> To manage your subscription to SPSSX-L, send a message to

> LISTSERV@.UGA

>  (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD





-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
Sent from: http://spssx-discussion.1045642.n5.nabble.com/

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (not to SPSSX-L), with no body text except the command. To leave the list, send the command SIGNOFF SPSSX-L For a list of commands to manage subscriptions, send the command INFO REFCARD