K-S test for parameter estimation … ?

I noticed this paper by Anne Buckner & Dirk Froebrich on the scale heights of star clusters, in which they aim to estimate the parameters for a non-standard (i.e., not Normal, Student’s t, skew Normal, Gamma, etc.) probability model given univariate observed data assumed generated iid (from this model under some unknown parameterisation).  Their solution is to attempt to set confidence intervals on the unknown parameters using the p-values of K-S tests between the observed data and the model’s cumulative density function.  What puzzles me is why they didn’t just do a Bayesian or maximum likelihood analysis, since the likelihood is available from the product of the derivative of the CDF at each observed datapoint?  Strange …

Advertisements
This entry was posted in Uncategorized. Bookmark the permalink.

One Response to K-S test for parameter estimation … ?

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s