# Partial Correlation

Statistics Solutions provides a data analysis plan template for the partial correlation analysis.  You can use this template to develop the data analysis section of your dissertation or research proposal.

The template includes research questions stated in statistical language, analysis justification and assumptions of the analysis.  Simply edit the blue text to reflect your research information and you will have the data analysis plan for your dissertation or research proposal.

Data Analysis Plan: Partial Correlation

Copy and paste the following into a word document to use as your data analysis plan template.

Research Question:

RQ: After controlling for covariate 1, is there a relationship between variable 1 and variable 2?

Ho: After controlling for covariate 1, there is no relationship between variable 1 and variable 2.

Ha: After controlling for covariate 1, there a no relationship between variable 1 and variable 2.

Data Analysis

To examine the research question, a partial correlation will be conducted to assess if relationships exist between variable 1 and variable 2, after controlling for covariates.  A partial correlation is an appropriate statistical measure when the researcher seeks to examine if a relationship exists between two variables when one or more variables are partialled out of both variable 1 and variable 2.  The contribution of the covariate is removed from variable 1 and variable 2, thus taking into account that the covariate that is partialled out of the results.  In this research question, the covariate may be significantly related to variable 1 and variable 2; therefore, partialling the covariate out of the analysis will reveal the relationship between variable 1 and variable 2 more accurately.  Correlations vary from 0 (no relationship) to 1 (perfect linear relationship) or -1 (perfect negative linear relationship).  Positive coefficients indicate a direct relationship; as one variable increases, the other variable also increases.  Negative correlations coefficients indicate an indirect relationship; as one variable increases, the other variable decreases.  Cohen’s standard will be used to evaluate the correlation coefficient, where .10 to .29 represents a weak association between the two variables, .30 to .49 represents a moderate association, and .50 or larger represents a strong association.

Reference