Correlational Analysis

Understanding correlation analysis (Pearson's and Spearman correlations)

Correlation analysis is a statistical method used measure the relationship and association between two variables. The test measures the strength and direction of an association between two variables. For instance, a correlation analysis can be used to determine whether there is an association between employee productivity and their levels of stress. In most cases, correlation analysis is used together with a regression analysis or another test that examines the relationship further.

1. Pearson's correlation
   The Pearson's correlation, also referred to as the Pearson product-moment correlation coefficient is used to measure whether two variables are associated. The test measures the strength and direction of the relationship that is present between two variables that have been measured on at least an interval level (continuous and scale variables). When conducting a Pearson's correlations, it is crucial that the data being utilized meets certain assumption that allow for conducting an accurate Pearson's correlation test. These assumptions are;

• The two variables being tested should be measured at the interval or ratio level (continuous variables)
• There should exist a linear relationship between the two variables. A scatter plot is used to show the linearity of two variables plotted against each other.
• The data being utilized, i.e., both variables should not have significant and extreme outliers. Outliers my end up distorting the results.
• The variables being tested should be nearly normally distributed. This is tested in a histogram, where it shows almost a bell-shaped curve for approximately normally distributed variables.
1. Spearman correlations
   The Spearman's correlation, also referred to as the Spearman rank-order correlation coefficient is used to measure whether two variables are associated. The test measures the strength and direction of the relationship that is present between two variables that have been measured on at least an ordinal level (categorical variables). When conducting a Spearman's correlations, it is crucial that the data being utilized meets certain assumption that allow for conducting an accurate Spearman's correlation test. These assumptions are;
• The two variables being tested should be measured at the ordinal level (categorical variables). For example, a variable with 3 categories (bad, neutral and good) or 5-, 7- and 9-point Likert scales and so forth.
• The two variables being measured should represent paired observations.
• The variables being tested should exhibit a monotonic relationship.
2. Interpreting correlations analysis
   Both the correlations are basically interpreted the same way. Both Pearson's denoted with the symbol (1) and Spearman's denoted with the symbol (1's) correlation analysis results range between a value between -1 and 0 for negative correlation and 0 and 1 for positive correlations.
• The closer the values of the correlations are to -1 or to 1, the stronger the association between the variables is and the closer they are to 0, the weaker the association is.
• When the correlations value is below 0 (a value between 0 and -1) the correlation direction is said to be negative. This means that, the association between the two variables is such that, as one variable increases, the other decreases and vice versa.
• When the correlations value is above 0 (a value between 0 and 1) the correlation direction is said to be positive. This means that, the association between the two variables is such that, as one variable increases, the other also increases and as one decreases, the other will also decrease.

Essay Experts is Canada's premier essay writing and research service. We help undergraduate and graduate students with their essays, research papers, theses and dissertations. Our statisticians are standing by to help. Simply email us your question, requirements or assignment and we'll get back to you with a quote. Our statisticians all possess advanced degrees and have experience in helping students succeeed in statistical writing and analysis.