Summary Statistic to Compute for Each Variable

Select the summary statistics to compute.

The summary statistics are summarized in the following table:

Statistic	Description
CSS	Corrected sum of squares
CV	Coefficient of variation
Kurt	Kurtosis
LCLM	Lower confidence limit for the mean
Max	Maximum value
Mean	Mean value
Median	Median value
Median polish	Median polish procedure Note: Median Polish works for Affymetrix probe level data as the summarization method in RMA and GCRMA. When selecting Median Polish, specifying one and only one variable in the Variables By Which to Summarize field is needed.
Min	Minimum value
N	Number of values
NMiss	Number of missing values
P1	1st percentile
P5	5th percentile
P10	10th percentile
P25	25th percentile
P75	75th percentile
P90	90th percentile
P95	95th percentile
P99	99th percentile
Probt	The probability that an observation from a Student's t distribution, with degrees of freedom df and noncentrality parameter nc, is less than or equal to x
QRange	Interquartile range (Q3-Q1)
Range	Range from the minimum value to the maximum value
Skew	Skewness
StdDev	Standard deviation
StdErr	Standard error
Sum	Sum of all values
SumWgt	Sum of the weights
t	The computed t-statistic for the values
UCLM	Upper confidence limit for the mean
USS	Uncorrected sum of squares
Var	Variance

For more information about these methods, consult a statistics text.

To Specify a Summary Statistic:

Left-click the desired statistic. Hold down Ctrl while left-clicking to select multiple statistics.