Correlation is used to test the presence, strength and direction of a linear relationship among variables (Bates, 1996). Correlation is a numerical expression that signifies the relationship between two variables and allows a researcher to explore this relationship by 'measuring the association' between the variables. Some researchers like to call correlation a 'measure of association' because the correlation coefficient provides the degree of the relationship between the variables. But it is important to remember that correlation does not equal causation. For example: The number of churches in a city in 1970 was 150 and the crime rate was 5 percent. In 1990, the number of churches in a city was 400 and the crime rate was 15 percent. So, would it be logical to conclude as the number of churches in a city increases the crime rate increases? No. Other variables are at work. The most obvious one in this case is a population increase. We will be using interval and ratio data to run correlations. There are three types of relationships:
A correlation coefficient is the numeric value of the relationship between variables. The correlation coefficient is a percentage and can vary between -1 and +1. If no relationship exists, then the correlation coefficient would equal 0. If the correlation coefficient lies between -1 and 0, it is a negative (inverse) relationship; 0 and +1, it is a positive relationship. The closer the coefficient lies to -1 or +1, the stronger the relationship. Here are some guidelines for interpretation:
less than .20: slight correlation; almost neglible relationship [1] Source: J.P. Guilford, Fundamental Statistics in Psychology and Education (New York: McGraw-Hill. 1956) p.145. Cited in F. Williams, Reasoning with Statistics, (New York: Holt, Rinehart and Winston. 1979) p. 128. If you don't
understand something in this Web note, please e-mail
Dr. Sitton.
Revised 092811 — http://www.uamont.edu/FacultyWeb/sitton/crz/mrea/correlation.html |
