Analyzing Parametric Statistics
According to Gogtay et al (2017) correlational analysis is a data analysis method used to show the relationship between two or more quantitative variables based on the assumption that there is a relationship between the variables. This analysis gives the correlation coefficient whose value can be either +1 (to show positive correlation), -1 (to indicate a negative correlation), or 0 (to show that there is no correlation between the variables). Correlation analysis only shows that the data is associated and should not be confused with causation thus cannot be used for prediction in data analysis.
There are two correlation analysis tests;
- Pearson correlation
- Spearman’s correlation test.
Pearson Correlation Analysis
Pearson correlation measures the strength and direction between two variables.
It’s based on the assumptions that;
- The relationship between the variables is linear
- The variables are independent of each other
- The variables are distributed normally.
Spearman’s correlation Analysis
It’s a non-parametric analysis that is used to indicate the strength and direction of a monotonic association between two ranked variables. It’s used when measuring the relationship between two ordinal variables. The result of the analysis is the Spearman’s correlation coefficient (rs) the coefficient can be -1(negative correlation), 0( no correlation between the variables), or +1( a positive correlation).
Assumptions of a Spearman’s correlation test
- A random sample
- A monotonic relationship between the variables
- Variables are at least ordinal
- Data contain paired samples
- Independence of observations.
Correlation coefficients are used to show the strength and direction between pairs of continuous data. When the data is normally distributed Pearson’s coefficient is used and when the data is non-parametric Spearman’s coefficient is used. The study sample was normally distributed and analyzed using Spearman’s correlation instead of the Pearson correlation thus it was not the correct level of analyzing the data. Spearman’s correlation is mostly preferred for non-parametric data. As explained above, correlation is a way of measuring the extent to which two variables are related, i.e. changes in one variable is accompanied by changes in the other variable. Thus in correlational analysis, the variables being analyzed are dependent on each other (change in one variable is associated with changes in the other variable).
Association analysis is a data analysis method used to identify data items that often appear together. It is used for identifying dependent and associated data variables in a sample. There are three important terms (metrics) used to determine the strength of the analysis, these are; Support, Confidence, and Lift.
In conclusion, correlation analysis is used when there exists a linear relationship between the different data variables being analyzed. Association analysis is used to analyze any relationship between two or more variables, whether linear or not. These data analyzing methods are thus not equivalent.
The evidence is this study cannot be used to inform practice change. As seen and explained above, correlation analysis cannot be used to make a prediction.
Maxwell, J. A. (2020). Why qualitative methods are necessary for generalization. Qualitative Psychology.
Gogtay, N. J., & Thatte, U. M. (2017). Principles of correlation analysis. Journal of the Association of Physicians of India, 65(3), 78-81.
I NEED A COMMENT FOR THIS DISCUSSION BOARD AT LEAST 2 PARAGRAPHS AND USE AT LEAST 3 SOURCES NO LATER THAN 5 YEARS.
Leave a ReplyWant to join the discussion?
Feel free to contribute!