s-news
[Top] [All Lists]

Re: Fitting a smooth curve through data with many NAs

To: s-news@lists.biostat.wustl.edu
Subject: Re: Fitting a smooth curve through data with many NAs
From: Sarah Henderson <sarah.henderson@ubc.ca>
Date: Wed, 11 Feb 2009 13:07:17 -0800
In-reply-to: <4993384E.9020700@elmo.ch>
References: <7.0.1.0.2.20090211122045.02591d60@ubc.ca> <4993384E.9020700@elmo.ch>

Ha!

Thanks for all of your replies. I just wasn't looking at the right place in the help pages -- I see it now.

Feeling very silly but, as always, grateful for the support of this list.

Cheers,

Sarah

Sarah,

I guess you simply want to pull up the help pages for these functions.
They come with arguments like na.rm=T and that takes out the NA values before doing the calculations.

Best regards,

        Andreas

Sarah Henderson wrote:
Hi all --
I am doing thousands of preliminary plots to investigate the relationship between daily measurements of forest fire intensity and the aerosol optical thickness (AOT) as measured by MODIS. Values for AOT are null if there is any cloud in the atmospheric column, so these data are spotty at best. On average I have values for 200 out of 365 days. I would like to fit a smoothed line through the AOT values to get a better visualization of what's happening, but all of the functions (smooth, lowess, spline) seem not to accept NAs. However, if I run smoothing plots from the GUI they work just fine so it must be dealing with these null values somehow.
Can anyone suggest a quick fix?
Many thanks,
Sarah
--------------------------------------------------------------------
This message was distributed by s-news@lists.biostat.wustl.edu.  To
unsubscribe send e-mail to s-news-request@lists.biostat.wustl.edu with
the BODY of the message:  unsubscribe s-news


<Prev in Thread] Current Thread [Next in Thread>