"R. Martin" <[EMAIL PROTECTED]> wrote in message news:<[EMAIL PROTECTED]>...
First, thank you, Russell, for contributing your experience after taking the time to read my post. I truly appreciate it. > If your data is taken at time intervals of days or hours, I'd > convert the dates to Julian dates (I can give you a formula if you > need it), perhaps subtracting off the earliest just to keep the > numbers smaller. Yes, my data is taken at time intervals of days, although irregular intervals. (which certainly makes no difference) I have stumbled on several references to "Julian dates" since I posted my original message. These are different things to different people. To IBM, the Julian date for this day is 20030206. For the makers of Statistica, it's the number of days since January 1, 1900. For the makers of Origin (another statiscal package), "the Julian day zero was over four thousand years ago." The list of possible definitions is pretty long... This being said, Britannica gave me some good background information on the Julian calendar, which is yet something else. Then, MATLAB handles dates as the number of days since "0-Jan-0000". "SPSS actually stores dates as the number of seconds that have elapsed since October 14, 1582." Stata, on the other hand, considers the number of seconds that have elapsed since January 1,1960. Etc. Wow! Now, I checked the AAVSO Web site and I found: "Astronomers simplify their timekeeping by simply counting the days. All days are numbered consecutively from Julian Day 0, which began at noon on January 1, 4713 B. C. January 1st, 1993, was JD 2448989; January 1st, 2000 will be JD 2451545." So, considering this large choice of arbitrary origins, I would really appreciate if you could tell me how you compute a Julian date given a "normal" date. Since Julian dates seem to be a mystical way to do the trick, I might as well join the club. :) > Unless your data is taken at millisecond intervals > I think milliseconds is not the appropriate unit. You could also > use decimal years, but that doesn't handle leap years as neatly, I > think. BTW the American Association of Variable Star Observers > records all its data in terms of Julian date (and requires its > observers to report them that way, as I recall), so there is a > real world example of time series data handled that way. > > There is no real "arbitrariness" involved in picking some date > as your zero point in time. Unless there is some theoretical > reason that your computation should be referenced to the moment > of the Big Bang, there is always some arbitrariness in dating. > Just make sure you're using the same zero point and same units > and you should be able to directly compare regressions, etc. OK. I was just concerned about using a continuous scale to report discrete measurement times. I recognize this was a bit silly on my part. > The comment about Z-values confuses me, too. Well, at last, I don't feel as weird now! :) Thanks again, Russell. . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
