[R] Loess smoothing - alpha Parameter

[8legged]

I have thousands of Fst-values (markers) spread across the genome. I would
like to use Loess to visualize and integrate them along the chromosomes.
This makes sense only along the chromosome, since markers (and thus Fst
values) are physically linked when located in close physical proximity. 
The problem arises, because the length of different chromosomes varies (the
longest is 3-4 times as long as the shortest). If I understand correctly,
when I define in loess() "span" (alpha), I define the number of Fst-values
AS FRACTION OF ALL Fst-values that belong to the same chromsome when when
calculating the local estimated value with loess. E.g., when I take a higher
value for "span", a larger percentage of all values will be considered. 
The problem is, that larger chromosomes have more markers and thus more
Fst-values. I therefore expect a bias between large and short chromosomes.
Is this true? - If so, is there an option to define "span" (alpha) dependent
on the number of values?

thanks

--
View this message in context: http://r.789695.n4.nabble.com/Loess-smoothing-alpha-Parameter-tp4307000p4307000.html
Sent from the R help mailing list archive at Nabble.com.