"David Delgado Gomez" <[EMAIL PROTECTED]> wrote in message news:[EMAIL PROTECTED] > Good morning, > > I have data with a normal distribution. Values higher than the mean are > corrupted with noise. Is it possible to estimate the variance of the > gaussian distribution just taking into account values smaller than the > mean? > Thanks > David >
Unless you know something about the corruption - or is it contamination with extra values which have a larger mean - it is going to be difficult. The corruption means that you cannot accurately estimate the mean. Is it reasonable to take the sample median, and assume that the sample is almost uncorrupted up to the median?Perhaps a half-normal distribution could then be fitted by maximum likelihood up to the sample median? Those are a few thoughts which might prompt some discussion. Cheers -- Alan Miller http://users.bigpond.net.au/amiller Retired Statistician . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
