[Thread Prev][Thread Next][Index]
[ferret_users]weird regresst
- To: ferret <ferret_users@xxxxxxxx>
- Subject: [ferret_users]weird regresst
- From: Peter Szabo <szabpet83@xxxxxxxxx>
- Date: Thu, 29 Oct 2009 09:04:48 +0100
- Dkim-signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=domainkey-signature:mime-version:received:date:message-id:subject :from:to:content-type; bh=s5lKsD4hxJZoq2kzWUBAJPOuJ9yLr/LEh0l7g5hfBuo=; b=QYkRl4YaLXANFCVwQ+p/g2syPSzVh46HZj2Dko8n/gsfvQshL8gw797njOc4lmHODZ KriQ+0CQL7GcWWPokgAi+Bndq65vyPx3CMdaaXWNCoNMFhiHIiQpo2bRBat/e9mjBjea jcYpTCeMo6Cj4Tc7N7Dob7zKK9GeSR9moodTo=
- Domainkey-signature: a=rsa-sha1; c=nofws; d=gmail.com; s=gamma; h=mime-version:date:message-id:subject:from:to:content-type; b=LvZ4IVwOapIRdHXREDYV2cYAZRPRvvAoXphYKy4Vn2pbaVrW0ZRgTzuzMrdNJr1i+V lhkTmxiLKJouIQfnwvAuxGN+xYPc+JlC0+oM+nm6tjCAQV0Ug52Q78t5Uyiv2CwsC0J+ FB7TBv8c6mR7BBzQ3r/ZKmpX7bnewsNvmmMqY=
- Sender: owner-ferret_users@xxxxxxxx
Hello Users,
i found something very strange during trend-analysis: suppose a variable is a rare occurence, it exists only in the end of the period (it is integral or non-valid value. If i wanted to plot a trend analysis, it just connects the two dots to be a line (like in the attached pic). Is it just strange for me? Normally it should be ascendent through the time instead of descending.
Here is what i did:
plot/color=9/nolabel/sym=2 aa
let p=t[gt=aa,l=1:40]
let q=aa[l=1:40]
go regresst
plot/vs/line/ov/nolab/col=9 p, qhat
Writing this i just realized i should have zero instead of non-valid values and the script should be modified like this, so there wont be dots at every zero points and the line will be ascendent:
let q=missing(aa[l=1:40],0)
So, its just a helping thread for someone coming up against this :)
Peter
Attachment:
regresst.gif
Description: GIF image
[Thread Prev][Thread Next][Index]
Contact Us
Dept of Commerce /
NOAA /
OAR /
PMEL /
TMAP
Privacy Policy | Disclaimer | Accessibility Statement