Mailing List Archive Mailing List Archive
"HeimannJ" <heimannj@MA*.ND*.GT*.CO*> says about Tom Wylie's inquiry <tw> I cannot seam to fit an alogrithum( polynomial, expon) to the <tw> pp02 verses %CNS data between ppo2 0.6 -> 1.82 with any <tw> degree of accuracy to the tables stated in the IANTD advanced Nitrox <tw> Manual. > I assume this is the same table that was in the old IANTD technical > workbook, i.e., %CNS exposure per minute at given level of PO2. If so, > then the reason you can't approximate it as a simple mathematical > function is that it does not derive from a such a model, but rather is > based on empirical data (namely, the NOAA CNS exposure tables). John, it is quite common to use mathematical functions (simple or not) to fit (approximate) empirical data that is not generated from any known mathematical model. There is a vast amount of statistical and mathematical literature that deals with that precise topic. While I don't consider myself a techdiver (just happened to be lurking here to see if Rich Pyle has anything to report about the Deep Diving panel of which he is/was one of the panelist in Tek '95 or his meeting/talking with Dr. Dan Manion), I do have some expertise on the subject of "mathematical/statistical model-building." I read Tom Wiley's statement of the "Problem" posed on this LIST as one in "model-building" with rather unconventional fitting criteria that can be equivalently stated as requiring all "residuals" (observed minus fitted) to be of the same sign, while trying to limit the Chebyshev (L1) norm of percentage errors to 2%. If that is in fact the case, then if Tom Wiley can e-mail me the data he used I'll be happy to take a look at it to see if I can be of help in fitting them to the desired precision. -- Bob. RFLNG@cl*.ed* Ph.D., Fellow of the American Statistical Assoc.
Navigate by Author:
[Previous]
[Next]
[Author Search Index]
Navigate by Subject:
[Previous]
[Next]
[Subject Search Index]
[Send Reply] [Send Message with New Topic]
[Search Selection] [Mailing List Home] [Home]