Premium
POWER ANALYSIS FOR DETECTING TRENDS IN THE PRESENCE OF CONCOMITANT VARIABLES
Author(s) -
Nickerson David M.,
Brunell Arnold
Publication year - 1998
Publication title -
ecology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.144
H-Index - 294
eISSN - 1939-9170
pISSN - 0012-9658
DOI - 10.1890/0012-9658(1998)079[1442:pafdti]2.0.co;2
Subject(s) - alligator , covariance , concomitant , analysis of covariance , statistics , abundance (ecology) , power (physics) , statistical power , ecology , environmental science , mathematics , biology , physics , quantum mechanics
In some situations, survey counts must be adjusted for the effects of concomitant variables using analysis of covariance in order to detect a trend in abundance over time. A power analysis in these cases allows the calculation of the probability of detecting a trend after adjustments. The methods will be applicable to samples taken at regular or irregular intervals in time or space, and in which the effects of the concomitant variables do not change over time. Furthermore, the detection of linear and intrinsically linear change can be determined. The methods are applied to the monitoring of American alligator ( Alligator mississippiensis ) populations in Florida.