| percentTestData {fuzzySim} | R Documentation |
Percent test data
Description
Based on the work of Schaafsma & van Vark (1979), Huberty (1994) provided a heuristic ("rule of thumb") for determining an adequate proportion of data to set aside for testing species presence/absence models, based on the number of predictor variables that are used (Fielding & Bell 1997). The 'percentTestData' function calculates this proportion as a percentage.
Usage
percentTestData(nvar)
Arguments
nvar |
the number of variables in the model. |
Value
A numeric value of the percentage of data to leave out of the model for further model testing.
Author(s)
A. Marcia Barbosa
References
Huberty C.J. (1994) Applied Discriminant Analysis. Wiley, New York, 466 pp.
Schaafsma W. & van Vark G.N. (1979) Classification and discrimination problems with applications. Part IIa. Statistica Neerlandica 33: 91-126
Fielding A.H. & Bell J.F. (1997) A review of methods for the assessment of prediction errors in conservation presence/absence models. Environmental Conservation 24: 38-49
See Also
Examples
# say you're building a model with 15 variables:
percentTestData(15)
# the result tells you that 21% is an appropriate percentage of data
# to set aside for testing your model, so train it with 79% of the data