Sample Dissertation Methodology Paper on Regression Correlation Analysis

Regression analysis entails the identification of the relationship between a given dependent variable and other independent variables. A hypothesized model of the relationship together with estimates of the variable values is used to form an approximated regression equation. When the model is satisfactory after being tested, it can be utilized to forecast the figures of the dependent variable once given those of the independent variable. For instance, a linear regression model that describes an association between a dependent variable y and an independent variable x can be represented as y = a0 +a1x +k where a0 and a1 are model parameters and k is a constant. Regression analysis mostly utilizes the least square method in the development of the estimates of the parameters (Vogt and Johnson 45).

The correlation coefficient can be described as a measure of linear relationship present between two variables. The correlation coefficient values lie between -1 and +1. A coefficient of +1 shows that the two variables that are studied has a perfect positive relationship. On the other hand, a coefficient of -1 show that the two variables studied have a perfect negative relationship. In a simple linear regression, the coefficient of determination’s square root gives as the sample correlation coefficient (Vogt and Johnson 46).

Regression correlation analysis, however, does not determine the cause and effect of the relationship between variables. It just indicates how and the extent to which the variables are related to each other. The coefficient of correlation is used in measuring the degree of association between the two variables under study. Therefore, the conclusion on the cause and effect of the relationship between variables has to be based on the views of the analyst (“Regression and Correlation Analysis”)

Works Cited

“Regression and Correlation Analysis.” Mac OS X Server. N.p., n.d. Web. 12 Sept. 2015.

Vogt, W P, and Burke Johnson. Correlation and Regression Analysis. Los Angeles: SAGE, 2012. Print.