Skip to content
Research Article Open access CC BY 3.0

Sample Size for Correlation Studies When Normality Assumption Violated

Azadeh Saki, Hamed Tabesh

Current Journal of Applied Science and Technology · pp. 1808–1822 · Published 26 Feb 2014

10.9734/BJAST/2014/7923

Abstract

Aims: Assessing the correlation between two variables is very important in observational and experimental researches. “How many sample size was required?” is one of the preliminary questions for correlation studies. Although achieving normality is rare the available techniques calculated the sample size based on fisher transformation statistics that supposed the bivariate normal distribution. This study conducted to find the sample size of correlation studies when the distribution of population is not bivriate normal. Methodology: A Simulation study was used to compared the required sample size of the correlation test for ρ= 0.1, 0.2 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9. Samples are drawn from bivariat normal, skewed, highly skewed, and heavy tailed distributions. The bias, variance, Mean Square Error (MSE), and the rejection rate of the fisher test for 10000 sample correlation coefficient were calculated. To achieving the nominal power the sample size was increased gradually. Results: Both the mean Bias and Mean Square Error of Sample correlation increased when the bivariate distribution is not normal. The correlation test is robust against minor and major departures from bivariate normal assumption when the sample size of study was sufficiently large. To find the significance correlation between two variables with nominal power the required sample size depending on ρ and population distribution approximately 10 to 30 percent increased. Conclusion: Departure from normality affected both accuracy and precision of sample correlation. Normality is not an ignorable assumption for correlation studies and it is important to have information about population distribution to determine the sample size when designing a study.

Correlation coefficient fisher test sample size bias simulation normality

References (11)

  1. 1 Statistical power analysis for the behavioral sciences [DOI]
  2. 2 On the probable error of a coefficient of correlation deduced from a small sample
  3. 3 FREQUENCY DISTRIBUTION OF THE VALUES OF THE CORRELATION COEFFIENTS IN SAMPLES FROM AN INDEFINITELY LARGE POPU;ATION [DOI]
  4. 4 Sample Size Requirements for Estimating Pearson, Kendall and Spearman Correlations [DOI]
  5. 5 The Probability Plot Correlation Coefficient Test for Normality [DOI]
  6. 6 Sample Size Methodology [DOI]
  7. 7 Tamanho de amostra para estimação do coeficiente de correlação linear de Pearson entre caracteres de milho [DOI]
  8. 8 Patterns of Daily Duration and Frequency of Breastfeeding among Exclusively Breastfed Infants in Shiraz, Iran, a 6-month Follow-up Study Using Bayesian Generalized Linear Mixed Models [DOI]
  9. 9 Correlation Coefficients: Mean Bias and Confidence Interval Distortions [DOI]
  10. 10 Tamanho de amostra para estimação do coeficiente de correlação de Pearson entre caracteres de Crambe abyssinica [DOI]
  11. 11 A simple powerful bivariate test for two sample location problems in experimental and observational studies [DOI]

Cited by 4

Loud and proud: Collective self-esteem is negatively associated with internalized stigma and minority stress. A mixed methods study of intersectional stigma among queer autistic adults from Poland

A. Pyszkowska, Ari Nowacki, Franciszek Stefanek · Research in Autism · 2026

Emotions and individual differences shape human foraging under threat

Hailey Trier, J. X. O’Reilly, Lisa Spiering · Nature Mental Health · 2025

Relationship Between Airline Category, Geographical Region, and Safety Performance

P. Simpson · 2018

British Virgin Islands Tourists' Motives to Travel, Destination Image, and Satisfaction

Sherrine Natahsa Augustine · 2017

Related research

Article metrics

Real usage data collected on this platform.

36

Page views

0

PDF downloads

14

Outbound clicks

4

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.