Answers are grounded in this paper and cite their sources.
In the mathematical statistics, in order to close approximately to the cumulative distribution function of standard normal distribution, the Fisher z transformation is the widely employed explicit elementary function, and is used to estimate the confidence interval of Pearson product moment correlation coefficient. A new Sigmoid-like function is suggested to replace the Fisher z transformation, and the new explicit elementary function is not more complicated than the Fisher z transformation. The new Sigmoid-like function can be 4.677 times more accurate than the Fisher z transformation.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2014) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: