R help - Jun 2005 - Fitting Theoretical Distributions to Daily Rainfall Data

Dear List Members, 

I need a bit help about fitting some theoretical
distributions (such as geometric, exponential,
lognormal or weibull distribution) to the following
*dry spell*, *wet spell*, *cycles (Wet-Dry or
Dry-Wet)* from my meteorological (daily rainfall) data
http://www.angelfire.com/ab5/get5/R.rainfall.txt only
for rainy seasen (july - september) of 14 years only:

dryspell<-c(1,1,4,1,1,4,2,2,3,4,1,2,1,1,1,3,1,3,
2,3,1,2,3,3,2,2,6,2,1,1,3,1,2,1,4,4,1,1,2,1,1,2,
2,4,1,1,1,3,4,1,7,1,3,2,5,1,3,1,1,3,4,8,4,3,1,1,
1,2,3,1,1,2,1,1,2,2,2,3,3,13,13,7,1,1,1,1,7,3,2,
1,3,1,1,2,5,1,2,1,3,1,1,2,3,2,3,2,1,5,1,2,2,2,1,
9,2,2,1,1,4,5,1,1,3,1,3,3,2,1,1,1,17,1,4,5,1,1,
1,1,2,1,2,1,1,7,3,8,2,1,1,2,4,5,1,1,1,2,3,1,1,2,
1,1,3,2,3,1,1,1,3,6,4,1,2,1,2,2,4,2,4,2,1,2,1,3,
1,2,2,1,1,1,1,4,2,1,12,3,1,1,5,1,1,5,1,2,1,1,1,1,
5,3,1,1,3,1,1,6,10,1,1,1,2,1,3,2,2,5,1,1,2,2,1,2,
3,1,3,6,2,1,1,4,6,1,1,1,3,2,2,1,1,1,5,1,1,1,1,3,
1,2,1,7,1,3,1,3,4,1,1,3,4,3,1,4,4,1,3,1,5,3,1,2,
2,1,1,1,2,1,1,6,1,1,1,3,1,3,4,1,1,3,4,1,1,8,1)

wetspell<-c(1,5,6,4,1,5,3,4,5,2,3,1,5,4,1,4,1,2,3
,1,5,4,5,2,1,1,1,6,2,19,5,4,6,5,2,7,1,3,1,1,2,1,
3,8,2,3,1,2,5,1,3,8,9,1,1,7,1,2,3,7,9,4,4,1,2,3,
1,1,1,1,1,2,6,7,1,4,1,6,1,5,5,3,2,3,1,1,1,1,6,1,
3,2,1,3,5,6,3,2,6,1,1,3,1,7,3,5,1,2,2,3,1,12,1,8,
3,1,2,1,1,2,1,2,4,2,3,1,1,3,1,4,1,6,5,2,11,6,2,1,
1,9,2,7,1,7,4,1,6,4,8,2,1,1,1,9,3,3,7,2,1,3,3,8,2,
1,7,1,2,2,1,1,1,1,1,5,1,1,3,1,1,1,9,1,7,1,4,3,1,5,
7,1,5,1,5,6,8,5,3,4,1,2,7,9,3,1,4,2,1,1,2,3,1,1,8,
5,2,1,1,1,4,1,1,1,8,4,9,6,3,1,6,5,3,5,2,2,1,5,9,8,
1,6,4,1,2,8,6,1,3,1,2,2,2,3,1,1,5,2,3,11,1,1,1,5,
3,5,1,2,1,9,3,1,1,1,4,10,6,1,1,1,1,1,3,4,1,2,1,5,
2,1,3,2,9,2,1,1,4,2,1,2,9,3,1,1,1,2,6,6,3)

cycleWetDry<-c(2,9,7,5,5,7,5,7,9,3,5,2,6,5,4,5,4,4,
6,2,7,7,12,5,3,3,7,8,3,20,8,5,8,6,6,11,2,4,3,2,3,3,
5,9,6,4,2,3,8,5,4,15,10,4,3,12,2,5,4,8,12,8,9,5,5,
4,2,2,3,4,2,3,8,8,2,6,3,8,4,8,18,16,9,4,2,2,2,8,9,
3,4,5,2,4,7,11,4,4,7,4,2,4,3,10,5,8,3,3,16,4,3,14,
3,9,12,3,4,2,2,6,6,3,5,5,4,4,4,5,2,5,2,17,6,6,16,
7,3,2,2,11,3,9,2,8,11,4,14,6,16,3,3,5,6,10,4,4,9,
5,2,4,5,9,3,4,9,4,3,3,2,4,7,5,2,10,2,3,5,5,3,5,11,
2,9,2,7,4,3,7,8,2,6,2,9,8,9,9,14,6,5,2,7,8,10,8,2,
6,3,2,2,3,8,4,2,9,8,3,2,7,3,5,2,2,3,9,7,11,8,8,2,
7,7,5,6,4,5,2,8,12,10,2,7,8,7,3,9,7,4,5,3,3,3,3,8,
2,2,6,3,6,18,2,3,2,12,4,8,2,5,5,10,4,4,5,4,5,14,
10,2,4,2,6,4,4,6,3,4,2,6,3,3,4,3,15,3,2,2,7,3,4,
6,10,4,4,5,2,3,14,7,4)

cycleDryWet<-c(2,6,10,5,2,9,5,6,8,6,4,3,6,5,2,7,2,
5,5,4,6,6,8,4,4,3,3,12,4,20,6,7,7,7,3,11,5,4,2,3,3,
2,5,10,3,7,2,3,6,4,7,9,16,2,4,9,6,3,6,8,10,7,8,9,6,
6,2,2,2,3,4,3,7,9,2,5,3,8,3,8,8,16,15,11,2,2,2,2,13,
4,5,3,4,4,6,8,8,3,8,2,4,4,2,9,6,7,4,4,3,8,2,14,3,10,
4,10,4,3,2,3,5,7,5,3,6,2,4,6,3,5,2,7,22,3,15,11,3,2,
2,10,4,8,3,8,5,8,9,12,10,3,2,3,5,14,4,4,8,4,4,4,4,
10,3,2,10,3,5,3,2,2,4,7,5,6,3,2,5,3,5,3,13,3,8,3,
5,6,2,7,9,2,6,2,6,10,10,6,3,15,7,2,3,12,10,4,6,5,
4,2,2,3,4,6,4,9,6,5,2,2,7,14,2,2,2,10,5,12,8,5,6,
7,6,5,7,3,4,4,6,12,14,3,7,5,5,8,9,7,2,6,3,4,3,3,4,
6,2,6,3,4,14,15,2,3,6,10,6,4,3,4,13,4,2,4,5,7,11,
10,5,2,4,2,6,6,5,3,4,3,6,3,2,5,3,10,8,2,2,5,5,2,
5,13,4,2,4,5,3,7,14,4)


Using table() to each dryspell, wetspell, cycleWetDry,
cycleDryWet we find the empirical distribution
functions all of which seem to be positively skewed
with long tail. Therefore, i'd like to fit geometric,
exponential, lognormal or weibull distribution for
each dryspell, wetspell, cycleWetDry, cycleDryWet.
Better fit may be defined by higher p-values of
goodness-of-fit tests.

Is there any way i can do fit data to those
theoretical distributions in R? Is there any existing
program/function/package to solve such problem? 

Any suggestion, direction, references, help, replies
will be highly appreciated. 

Thank you for your time. 


----------------------------------

Mohammad Ehsanul Karim 

Web: http://snipurl.com/ehsan 
ISRT, University of Dhaka, BD 

----------------------------------



		
__________________________________ 

Get on-the-go sports scores, stock quotes, news and more. Check it out!

Have a look at the fit.dist function in Jim Lindsey's gnlm package at
http://popgen0146uns50.unimaas.nl/~jlindsey/rcode.html

fit.dist {gnlm}	R Documentation
Fit Probability Distributions to Frequency Data

Description

fit.dist fits the distributions in Chapter 4 of Lindsey (1995, 2003 2nd edn): 
binomial, beta-binomial, Poisson, negative binomial, geometric, zeta, normal, 
log normal, inverse Gauss, logistic, Laplace, Cauchy, Student t, exponential, 
Pareto, gamma, and Weibull to frequency (histogram) data, possibly plotting 
the frequency polygon of fitted values with the histogram.

fitdistr from the MASS package works quite well, too.

>Dear List Members, 
>
>I need a bit help about fitting some theoretical
>distributions (such as geometric, exponential,
>lognormal or weibull distribution)
____________________
Ken Knoblauch
Inserm U371, Cerveau et Vision
Department of Cognitive Neurosciences
18 avenue du Doyen Lepine
69500 Bron
France
tel: +33 (0)4 72 91 34 77
fax: +33 (0)4 72 91 34 61
portable: 06 84 10 64 10
http://www.lyon.inserm.fr/371/