s-news
[Top] [All Lists]

Loess

To: s-news@wubios.wustl.edu
Subject: Loess
From: Davorka Gulisija <gulisija@calshp.cals.wisc.edu>
Date: Sun, 23 Mar 2003 13:43:51 -0600 (CST)
Hi,


I am using Loess procedure in order to infer certain relationship
for the data set of ~130,000 observations with ~300 distinct values of
single predictor. I understand that fitted values y-hat are just 300
Weighted
LS fits in certain neighborhood of predictors. I am bit confused about
how exactly is this neighborhood assigned . Say I choose spanning
parameter = .5, for each LS analysis 75000 observations should be used.
However, intuitively it doesn't seem right since points are not equally
distributed among predictors and there are many observations for a single
value of predictor.
I would appreciate if someone could clear this for me.

Thank you,


Davorka



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