A correspondent who wishes to remain anonymous sends this in:

From Pat Robertson’s Regent University course catalog:

GOV 601 Quantitative Analysis (3) Skills for quantitative data gathering, measurement, policy analysis and program evaluation. Research and sampling design, surveys, data collection and data reduction and display. Review of basic statistics through multivariate analysis, z-scores, regression through the use of statistical computer package (SPSS),

and a Judeo-Christian perspective on the use of statistics.

I wonder if they teach the principle that God is in every leaf of every tree.

(I looked for the course description online but couldn’t find it. But the description seems consistent with others in the catalog.)

I've always sought divine assistance in interpreting the SPSS regression output.

thank god, finally!

Judeo-Christian perspective? I'm confused. Is that Bayesian or frequentist?

There are deep issues of epistemology regarding the foundations of statistics, and someone could weigh in on such issues from a uniquely Christian viewpoint, but I seriously doubt that's what's going on. It seems more likely that the instructors are encouraged to stick the phrase "Judeo-Christian perspective" in their course descriptions.

It's in the graduate course catalog.

SPSS: Statistical Package for the Seriously Saved

The "T" test is best, and is always significant.

Cross-over designs are preferred.

Work by Jewish statisticians formed the basis, but has now been superceded by the revelations of Christian statisticians.

John: I agree that there could be some fascinating discussions of Christianity and statistics. I'm speaking nearly entirely from ignorance here, but, no joke, I've often thought that the fallibility of statistical models and our statistical inferences in general is related to the Christian idea that we are all sinners and must accept that in order to be saved. It's the idea of falsifiability, but not just in any individual circumstance but a more general realization of our inherent limitations in using necessarily non-algorithmic processes to do statistics, and science. But, of course, there's no way that these ideas are being covered in that class.

You shouldn't mock Andrew! When statisticians get very senior they tire of estimating the average treatment effect of new fertilizers and start thinking of weightier matters.

Kruskal's written a piece on the casual assumption of independence in Hume's argument against miracles. David Bartholomew's even written a couple of books on theology and statistics. There's a really far out JRSS paper by him on the subject with a discussion by people like Cox, Durbin and Barnard. Who knows, maybe a correctly specified hierarchical model will resolve these problems once and for all?

"Judeo-Christian perspective? I'm confused. Is that Bayesian or frequentist?"

Well, we have to remember the first use of a p-value by Arbuthnot was as part of an argument for divine providence. It's kind of ironic that theological point's been settled, but the really divisive bayes/frequentist thing is still rumbling on.

The (graduate) course catalogue, containing the above course description on page 227, is here:

http://www.regent.edu/academics/catalogs/GRAD_cat…

I'd guess that you may need specific statistical tools

"to help discern the footprints of the

coming of Christ's new world-wide order." (GOV 654 International Politics)

I first saw this thread and was quite puzzled, not so much by the catalog description (which at first I thought was just content-free buzzwords, concurring with John Cook basically) but by the reactions, either taking it wayy too seriously, or a subtle antireligiousity.

It seems there might be a far more natural (and far less exciting) interpretation. Here's a hint. Finish the following phrase:

"Lies, damned lies, and …"

The catalog is probably making an appeal to ethics, an acknowledgment that one has an obligation to use these new powerful tools in an appropriate (ie, ethical, from a Judeo-Christian perspective) way. Mosteller's maxim is apropos: "It is easy to lie with statistics. It is easier to lie without them".

This might sound credulous, but think back to when you listen to a phone survey by a political operative, ostensibly trying to gauge popular opinion, but really framing questions about their boss's opponent in a disingenuous way to *persuade* your opinion, yet without actually misstating any facts.

That irks me everytime I think about it, and every day I guard against doing the professional equivalent, even if inadvertantly.

Factuality is certainly not synonymous with truth. To the extent that it is a lower-case "t"ruth being alluded to in the catalog, I heartily endorse such an effort.

Unusual facts about this course:

* The Poisson distribution is inherently Papist and will not be taught

* Two whole weeks spent on the von Mises test for normality, the Gold Standard of statistics

Well, why not? On the <a href="http://www.google.com/url?sa=t&source=web&ct=res&cd=6&url=http%3A%2F%2 Fwww.acmsonline.org%2FStucki-Worship.pdf&ei=G3m0Sr34K4mm8QbVrvi5Dg&usg=AFQjCNE5O7bc-Ajy7nKXrIeylWI7bLBGuA&sig2=R6MOOdfOm78KSazz6-FXFA” target=”_blank”>connection between mathematics and theology.

"Phooey!" (Nero Wolfe)

Wolfe says "Pfui!", actually.

Usually, I say a silent prayer every time I run a model in WinBUGS.

I would *hope* that they mean not using statistics for deception and lying. However, this is Regent University and Pat Robertson, so they probably mean how to lie (for Mammon, in the name of God) with statistics.