home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: sci.physics.fusion
- Path: sparky!uunet!cs.utexas.edu!sun-barr!ames!agate!linus!linus.mitre.org!linus!mbunix!eachus
- From: eachus@Dr_No.mitre.org (Robert I. Eachus)
- Subject: Re: Ying Experiment
- In-Reply-To: ames!FNALD.FNAL.GOV!DROEGE's message of Wed, 22 Jul 1992 22:07:31 GMT
- Message-ID: <EACHUS.92Jul22233419@Dr_No.mitre.org>
- Sender: news@linus.mitre.org (News Service)
- Nntp-Posting-Host: dr_no.mitre.org
- Organization: The Mitre Corp., Bedford, MA.
- References: <920722135155.242008a0@FNALD.FNAL.GOV>
- Date: Thu, 23 Jul 1992 04:34:19 GMT
- Lines: 44
-
- In article <920722135155.242008a0@FNALD.FNAL.GOV> ames!FNALD.FNAL.GOV!DROEGE writes:
-
- Gamma Duration Duration Accumulated Estimated Average
- Status Seconds Hours Net Joules Error-J Power - watts
-
- On 17760 4.9 532.8 49 0.0300 +/- 0.0027
- Off 48060 13.4 1268.8 50 0.0264 +/- 0.0010
- On 87300 24.3 2715.0 100 0.0311 +/- 0.0011
- Off 77220 21.5 1621.6 50 0.0210 +/- 0.0006
- On 82740 23.0 3607.5 50 0.0436 +/- 0.0006
- Off 51840 14.4 1658.9 50 0.0320 +/- 0.0010
-
- As a statistician this looks like a good place to use some
- non-parametric tests. (Non parametric statistics to not assume
- anything about the error distribution, although they still assume
- independence of data samples.) Of course you pay for the relaxation
- of assumptions in test power, but in my opinion it beats looking for
- 100 sigma to overcome assumptions about error sources...
-
- A week more of data would make a more reasonable data set (say ten
- on periods and ten off). For the current data using Wilcoxon's W
- statistic (H0 = no effect, H1 = excess heat during on periods), I get
- alpha = 0.20. (In other words, there is a 20% chance that a random
- data set would be this "good" assuming the null hypothesis is true.)
-
- Probably a more powerful test given the expeimental setup would be
- to look at On-Off pairs using a signed rank test (this is the less
- likely to be affected by long term drift in the calibration). I get
- alpha = 0.125 for the current data, but a sample of three is very
- small. I'll post again when Tom supplies more data.
-
-
- Robert I. Eachus
-
- with STANDARD_DISCLAIMER;
- use STANDARD_DISCLAIMER;
- function MESSAGE (TEXT: in CLEVER_IDEAS) return BETTER_IDEAS is...
- --
-
- Robert I. Eachus
-
- with STANDARD_DISCLAIMER;
- use STANDARD_DISCLAIMER;
- function MESSAGE (TEXT: in CLEVER_IDEAS) return BETTER_IDEAS is...
-