From: xiang li <lixiang128_at_gmail.com>

Date: Fri, 08 Apr 2011 15:58:43 -0500

R-help_at_r-project.org mailing list

https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Received on Sat 09 Apr 2011 - 03:54:43 GMT

Date: Fri, 08 Apr 2011 15:58:43 -0500

Dear R users:

In my research I need to come up with a method to measure the smoothness for a closed curve (looks like ellipse, but actually not). I was working on calculating Hurst Exponent using 2 dimensional dataset.

I checked fArma, Randomfields and several functions in fractal packages, but could not find a way to calculate Hurst Exponent for 2 dimensional data. For example, in fArma package, rescaled method is defined as rsFit(x, levels = 50, minnpts = 3, cut.off = 10^c(0.7, 2.5), doplot = FALSE, trace = FALSE, title = NULL, description = NULL). But I need to input 2 variables instead of one.

An example dataset a:

Obs Day Hour Ta Tb

121 20 0 15.72917 38.72908 122 20 1 15.22833 38.72137 123 20 2 14.58000 38.70560 124 20 3 13.92000 38.71345 125 20 4 13.54167 38.69884 126 20 5 13.71583 38.64483 127 20 6 15.16667 38.61158 128 20 7 16.92333 38.60596 129 20 8 17.81167 38.61342 130 20 9 18.76250 38.60460 131 20 10 19.84833 38.60891 132 20 11 20.53583 38.57431 133 20 12 23.00750 38.60031 134 20 13 26.49583 38.60715 135 20 14 23.42250 38.61355 136 20 15 26.01417 38.64173 137 20 16 26.76500 38.66624 138 20 17 24.54917 38.66912 139 20 18 23.67833 38.67209 140 20 19 23.20083 38.67061 141 20 20 22.12750 38.68486 142 20 21 20.42083 38.72173 143 20 22 19.25083 38.70809 144 20 23 17.44417 38.73694

You can run: plot(x=a$Ta,y=a$Tb,type="l") to see the curve. Could someone help me to find a way to measure the smoothness of this curve? Or could you teach me how to calculate H for 2 dimensional dataset? Thank you so much for your help. I really appreciate!

Xiang

R-help_at_r-project.org mailing list

https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Received on Sat 09 Apr 2011 - 03:54:43 GMT

Archive maintained by Robert King, hosted by
the discipline of
statistics at the
University of Newcastle,
Australia.

Archive generated by hypermail 2.2.0, at Sat 09 Apr 2011 - 04:00:28 GMT.

*
Mailing list information is available at https://stat.ethz.ch/mailman/listinfo/r-help.
Please read the posting
guide before posting to the list.
*