Richard Ristow: Yes. You’ll notice that on my resume I’ve listed, besides SPSS and SAS, things like BMDP, FORTRAN, APL and Basic. I’m also very experienced in mainframe operating systems and system-specific languages, all of which help in my work as a consultant. Amazing things have been done with very strange tools, by ingenious people willing to work very hard at it.

King Douglas: What SPSS modules do you use on a regular basis?

Richard Ristow: I’m a heavy base user. As you may have surmised, I’m a fancier data-handler than statistician. Some of the fancier stuff I’ve done in SPSS has been in response to questions on the [SPSSX e-mail] List. In working with real people, and real data, I emphasize simple, direct implementation of a ‘flat’ file structure, if that’s at all consonant with the study…because SPSS is so darned good at it.

King Douglas: Do you consider yourself a specialist in any area of SPSS programming?

Richard Ristow: I’m basically a data manipulation specialist. Secondarily, making really good use of the simple statistics. Data manipulation is challenging intellectually and fun. Something that they don’t tell you in stats classes is that in a real statistics problem eighty to ninety percent of the work is in getting the data ready.

King Douglas: Do you think that, generally, you are in the same boat with Raynald Levesque on that?

Richard Ristow: It’s very hard to claim to be in the same boat with Ray.

King Douglas: Do you write and/or employ SPSS macros or scripts in your work?

Richard Ristow: I do write macros, but not scripts. I’ve resisted learning to write scripts, but it’s clear that I’m simply going to have to. It should be easier for users to generate scripts via point and click. For instance, generating syntax from the menus is one of the absolute glories of SPSS. I don’t think they know how valuable it is.

King Douglas: What is your comfort level with statistics?

Richard Ristow: Fairly good, partly because I have a fairly good sense of my limitations and because I do grasp, philosophically, what statistical inference is about. And it’s helpful to have a really solid math background in my business. I listen to Marta and Hector when I get out of my own depth. I think Marta’s the best mathematical statistician on the [SPSSX e-mail] List; AND she can program, which is rare among statisticians.

King Douglas: What are your thoughts about “instant statisticians” as made possible by desktop statistical packages?

Richard Ristow: I don’t think people should jump in with just a manual and do something. But in a day or so of teaching I can get somebody going in a relatively responsible fashion. I’m not above anybody’s plainly understanding the very simplest of things with a day’s hard work.