I use a test in my research, that it's scores have narrow range. thus, I can't use parametric methods for computing correlations and differences between research variables. do you know any alternative/nParametric method?
Just because a continuous response variable has a narrow range doesn't mean you can use parametric analyses.
Is the response variable a counting variable, i.e., 1, 2, 3, 4, etc.? In that case results of parametric analyses may not be an appropriately interpreted—you'd also need to be conscious of ties in the ranks if moving to non-parametric approaches.
Perhaps you can provide more information in the scores–e.g., min, Q1, median, Q3, max, mean, sd, kurtosis, skewness, histogram–and exactly how you'd be violating assumptions parametric tests?
Hello Mahdi, I agree with Ette on the adoption of either of Spearman's rho or Kendall's tau rank correlations. Kendall’s tau values are smaller than Spearman’s rho correlation. Its calculations are based on concordant and discordant pairs and are insensitive to error. P values are more accurate with smaller sample sizes.
The Spearman’s rho correlation coefficients usually have larger values than Kendall’s Tau and their calculations are based on deviations. They are also much more sensitive to error and discrepancies in data.
The main advantages of using Kendall’s tau are as follows:
The distribution of Kendall’s tau has better statistical properties.
The interpretation of Kendall’s tau in terms of the probabilities of observing the agreeable (concordant) and non-agreeable (discordant) pairs is very direct.
In most of the situations, the interpretations of Kendall’s tau and Spearman’s rank correlation coefficient are very similar and thus invariably lead to the same inferences.
However, Spearman’s rank correlation coefficient is the more widely used rank correlation coefficient.
Symbolically, Spearman’s rank correlation coefficient is denoted by rs . It is given by the following formula:
rs = 1- (6∑di2 )/ (n (n2-1))
*Here di represents the difference in the ranks given to the values of the variable for each item of the particular data