SAM Algorithm

The data is , i = 1, 2, ... p genes, j = 1, 2, ... n samples, and response data , j = 1,2, ... n ( may be a vector).

Generic SAM procedure :

• Compute a statistic : ; i = 1, 2, ... p
• is a score.
• is a standard deviation.
• is a fudge factor.

Details of and for Two Class, Unpaired Data response type :

• .
• .
• ; k = 1,2. = 1 or 2.
• is the number of observations in .

Computation of :

1. Compute the 100 quantiles of the values, denoted by .
2. For (0, .01, .02, ... 1.0)
1. Let , where be the percentile of the values.
2. Compute , j = 1, 2, ... 100, where _mad_ is the median absolute deviation from the median, multiplied with 1.4826.
3. Compute cv() = .
3. Choose = argmin[cv()].
4. Finally compute = . is henceforth fixed at the value .
Topic revision: r12 - 06 Feb 2012, WillGray

• Biostatistics Webs

Copyright © 2013-2022 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Vanderbilt Biostatistics Wiki? Send feedback