Toward using confidence intervals to compare correlations.

By Gy Zou. Psychological methods, 2007

651 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/19b2d68974613c02111101956c09c01aa535cad9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Associations Between Grit, Motivation, and Achievement in High School Students (2017, methodology): “To test whether these differences in correlation were statistically significant for each construct, we used an approach outlined by Zou (2007) to calculate confidence intervals for differences between overlapping correlations (i.e., two correlations calculated from the same sample with a common…”
Surveying the forest: A meta-analysis, moderator investigation, and future-oriented discussion of the antecedents of voluntary employee turnover (2018, background): “If samples are independent and confidence intervals are available, these approaches would be recommended to test for significant effect differences (Steiger, 1980; Zou, 2007).”
Using Anchor-Based Methods to Determine the Smallest Effect Size of Interest (2019, neutral): “In our data, people’s responses on the GRoC question were more strongly correlated with change scores (PA: r = .47; NA: r = .42) than with T2 present state scores (PA: r = .37, rdif = 0.10, 95% CI [0.04; 0.16], NA: r = .27, rdif = 0.14, 95% CI [.07; 0.22]; Zou, 2007).”
Development and Validation of a Brief Version of the Difficulties in Emotion Regulation Scale: The DERS-16 (2015, methodology): “Confidence intervals for differences between correlations of the original 36-item DERS and DERS-16 with the relevant self-report measures were calculated using a method for comparing overlapping correlations for dependent groups (Zou 2007).”
Small Sample Size Solutions (2020, methodology): “With these confidence intervals, we can calculate a confidence interval for the difference between both effect sizes, Dω2, by applying the modified asymmetric method introduced by Zou (2007) for correlations and squared correlations.”
Determinants of Entrepreneurial Intent: A Meta–Analytic Test and Integration of Competing Models (2012, methodology): “We followed the recommendations in the literature for comparing nonindependent correlations (Meng, Rosenthal, & Rubin, 1992) and applied Steiger’s z-test (Steiger, 1980) as well as the procedure suggested by Zou (2007), which takes into account the confidence limits around overlapping effect sizes.”
Detecting Improvements in Forecast Correlation Skill: Statistical Testing and Power Analysis (2017, methodology): “The methods by Steiger (1980) and Zou (2007) are approximations: they assume that the data are normally distributed, and that the sample size is sufficiently large.”
Simple confidence intervals for lognormal means and their differences with environmental applications (2009, methodology): “Exten- Copyright © 2008 John Wiley & Sons, Ltd. Environmetrics 2009; 20: 172–180 DOI: 10.1002/env sions and applications of this method in other contexts can be found elsewhere (Zou, 2007; Zou and Donner, 2008).”
Parents' math–gender stereotypes, children's self-perception of ability, and children's appraisal of parents' evaluations in 6-year-olds (2015, methodology): “Finally, we used Fisher’s z significance test with 95% confidence intervals (Zou, 2007) to test whether the degree of agreement between parents varied as a function of their child’s gender.”
cocor: A Comprehensive Solution for the Statistical Comparison of Correlations (2015, methodology): “1 shows how to access the available tests and lists them with their individual test label (e.g., zou2007 ).”
Measuring the Mathematical Attitudes of Elementary Students: The Effects of a 4-Point or 5-Point Likert-Type Scale (2010, neutral): “The reliability coefficients of the pilot sample data for scores on both subscales, .920 (95% confidence interval [CI] = .908, .931; Zuo, 2007) for Enjoyment of Mathematics, and .880 (95% CI = .862, .897) for Mathematical Self-Perceptions, indicated a high degree of internal consistency, or domain…”
Best Practices for Crowd-based Evaluation of German Summarization: Comparing Crowd, Expert and Automatic Evaluation (2020, methodology): “To determine if these differences are statistically signiﬁcant, we applied Zou’s conﬁdence intervals test for dependent and overlapping variables and found out that the differences between correlation coefﬁcients were not statistically signiﬁcant for all nine measures (Zou, 2007).”