explicit_dFF(levelM​ap, includeHeader)

Creates an explicit full factorial experimental design.

EXPLICIT_DFF is basically an extension of the FULLFACT function (Statistics and Machine Learning Toolbox or the equivalent can be found in Octave). It allows for an explicit mapping of levels to each parameter within the design. It eliminates the need to encode parameter levels into a numeric mapping of values for FULLFACT.
Useful when you have parameters levels described by strings. Also useful when you don't know all parameters and/or parameter levels ahead of time to define the mapping, which can occur if your full factorial design is being generated based on user input.

% EXPLICIT_DFF
% Explicit mixed-level full-factorial designs
%
% Name:
% explicit_dFF
%
% Description:
% Creates a cell array EXP_DFF containing the explicit factor
% levels/labels for a full factorial design
%
% Inputs:
% levelMap - cell, array containing parameter level mapping to
% design matrix integer levels (i.e., mapping of dFF
% integers to levels/labels)
% includeHeader - boolean, flag indicating whether or not you want to
% include a header in the output design; default is
% to output with header
%
% Outputs:
% expdFF - cell, array containing the explicit mixed-level full
% factorial design matrix with explicit levels/labels
% rather than integer placeholders
%
% Author:
% Curtis Neiderer, Jan 2014

Example Usage:
levelMap = {'System State', {'Up', 'Down'}; ...
'Switch, {true, false}}
levelMap2 =
{1x2 cell}
{1x2 cell}

exp_dFF = explicit_dFF(levelMap)
exp_dFF =
'System' 'Switch'
'Up' [ 1]
'Down' [ 1]
'Up' [ 0]
'Down' [ 0]

levelMap2 = {{'Up', 'Down'}; ...
{true, false}}
levelMap2 =
{1x2 cell}
{1x2 cell}

exp_dFF = explicit_dFF(levelMap2)
exp_dFF =
'Param1' 'Param2'
'Up' [ 1]
'Down' [ 1]
'Up' [ 0]
'Down' [ 0]