Constraints on deformable models: recovering 3D shape and nongrid motion
Artificial Intelligence
On the Importance of Being Asymmetric in Stereopsis—Or Why We Should Use Skewed Parallel Cameras
International Journal of Computer Vision
Integrating Primary Ocular Processes
ECCV '92 Proceedings of the Second European Conference on Computer Vision
Robust estimating equations and bias correction of correlation parameters for longitudinal data
Computational Statistics & Data Analysis
| Hi-index | 0.01 |
The correlation coefficient r is a measure of similarity used to compare regions of interest in image pairs. In fluorescence microscopy there is a basic tradeoff between the degree of image noise and the frequency with which images can be acquired and therefore the ability to follow dynamic events. The correlation coefficient r is commonly used in fluorescence microscopy for colocalization measurements, when the relative distributions of two fluorophores are of interest. Unfortunately, r is known to be biased understating the true correlation when noise is present. A better measure of correlation is needed. This article analyses the expected value of r and comes up with a procedure for evaluating the bias of r, expected value formulas. A Taylor series of so-called invariant factors is analyzed in detail. These formulas indicate ways to correct r and thereby obtain a corrected value free from the influence of noise that is on average accurate (unbiased). One possible correction is the attenuated corrected correlation coefficient R, introduced heuristically by Spearman (in Am. J. Psychol. 15:72---101, 1904). An ideal correction formula in terms of expected values is derived. For large samples R tends towards the ideal correction formula and the true noise-free correlation. Correlation measurements using simulation based on the types of noise found in fluorescence microscopy images illustrate both the power of the method and the variance of R. We conclude that the correction formula is valid and is particularly useful for making correct analyses from very noisy datasets.