MAVDIFFERENCE procedure

Applies the average difference algorithm to Affymetrix data (D.B. Baird).

Options

PRINT = string

Whether to print monitoring information (monitoring); default *

SDLIMIT = scalar

Maximum number of iterations; default 50

Parameters

DATA = variates or pointers

Data values

GROUPS = factors

Groupings of the data values

MEANS = variates

Saves the means

SE = variates

Saves standard errors

Description

MAVDIFFERENCE uses the average difference algorithm to remove extreme values from Affymetrix data. These are defined as values more than option SDLIMIT standard deviations from the mean.

The data values are specified by the DATA parameter. They can be in a single variate, with any groupings (corresponding to different genes or probes) specified by the GROUPS parameter. Alternatively, they can be in separate variates, one for each group. The MEANS parameter saves the means. The SE parameter saves the estimated standard deviation when there are no groups, or the standard error of the mean when there are groups.

Options: PRINT, SDLIMIT.

Parameters: DATA, GROUPS, MEANS, SE.

Action with RESTRICT

MAVDIFFERENCE takes account of any restrictions on DATA or GROUPS.