a) Is it possible to estimate the strength of seasonality in timeseries
data. Say I have monthly mean prices of an ten different assets. I decompose
the data using stl() and obtain the seasonal parameter for each month. Is it
possible to order the assets based on the strength of seasonality?
b) which gives a better estimate on seasonality stl() or a robust linear
model like MASS::rlm(mean price ~ month), considering the fact that the
variable analysed is price series.
Possibly your code "MASS::rlm(mean price ~ month)" will result in Spurious
regression; you would make wrong impression of your estimated beta coef. as
in presence of the spurious regression they no longer have t-distribution.
May be you should try with "MASS::rlm(diff(log(mean price)) ~ month)?"
And secondly decomposition using standard approach is some sort of
**deterministic** act therefore, you would not get any measure of "strength"
in Statistical inference sense. To get that, I think above regression
approach would be handy.
Thanks and regards,
Arun Kumar Saha, FRM
QUANTITATIVE RISK AND HEDGE CONSULTING SPECIALIST
Visit me at: http://in.linkedin.com/in/ArunFRM _____________________________________________________