Stacked data sets
typically have all of the
variables
of interest stacked into a single set of columns.
The
Unstack
process transposes a
stacked
data set into a
tall
SAS data set, splitting the variables of interest among multiple columns, and generates an accompanying
Experimental Design Data Set (EDDS)
.
All you need to run this process is a
stacked
Input Data Set
. A typical stacked data set is shown
below
.
Typically,
stacked
data sets contain a smaller number of columns when compared with the number of rows (circled
above
). This data set has 100300 data rows, but only 7 columns. All of the actual intensity data is stacked into the one
log2i
column! You should also note the repetition of the
ChipID
,
Experiment
, and
Series
columns for all
probes
on the array.
For detailed information about the files and data sets used or created by JMP Life Sciences software, see
Files and Data Sets
.
The output of the
Unstack
process includes the
Results
window, which lists the output data set and EDDS.
|
Click
to view the
affylatin_stack_tal.sas7bdat
output data set.
|
The number of data columns in the output data set has increased to 59 from one in the input data set. This represents a 59-fold increase. The number of rows decreased from 100300 to 1700; a corresponding 59-fold decrease. All of the responses have been grouped into columns, with each column representing an individual array. Column names all contain the
Chip_
prefix. The
Series
column has been eliminated.
|
|
Click
to view the
affylatin_stack_exp.sas7bdat
output EDDS.
|
|
•
|