Bias in exponential and power function fits due to noise: comment on Myung, Kim and Pitt

Title: Bias in exponential and power function fits due to noise: comment on Myung, Kim and Pitt
Creator: Brown, Scott; Heathcote, A.
Relation: Memory & Cognition Vol. 31, Issue 4, p. 656-661
Relation: http://www.psychonomic.org/MC
Publisher: Psychonomic Society, Inc.
Resource Type: journal article
Date: 2003
Description: Myung, Kim and Pitt (2000) demonstrated that simple power functions almost always provide a better fit than simple exponential functions to purely random data. This result has important implications because it suggests that high noise levels, which are common in psychological, may cause a bias favouring power functions. We replicate their result, and extend it by showing strong bias for realistic sample sizes. We also show that biases occur for data that contain both random and systematic components, as may be expected in real data. We then demonstrate that these biases disappear for two- or three- parameter functions that include linear parameters (in at least parameterisation).
Subject: noise; power functions
Identifier: uon:2023
Identifier: http://hdl.handle.net/1959.13/27947
Identifier: ISSN:0090-502X
Language: eng
Full Text
Reviewed

		Thumbnail	File	Description	Size	Format
View Details Download			ATTACHMENT01	Author final version	364 KB	Adobe Acrobat PDF	View Details Download