Bivariate Data Analysis: Regression and Correlation Methods

Bivariate Data Analysis: Regression and Correlation Methods

1. It's a statistical analysis that can be used during the analysis and reporting stage of quantitative market research.

   • Bivariate Regression: involves analysing two variables to establish the strength of the relationship between them. The two variables are frequently denoted as X and Y, with one being an independent variable (or explanatory variable), while the other is a dependent variable (or outcome variable).
     • It uses a linear regression line (because the relationship between the variables is assumed to be linear) in order to help measure how the two variables change together, simultaneously.
       • This will take the form of a line of best fit placed on a scatter chart through the plotted values of the independent variable (X-axis), against the dependent variable (Y-axis).
   • Uses of Bivariate Regression Analysis include testing simple hypotheses, particularly of association and causality.

2. Types of Bivariate Analysis

   • The types of a bivariate analysis will depend upon the types of variables or attributes we will use for analyzing.
     • Numerical and Categorical – When one variable is numerical and one is categorical.
     • Categorical and Categorical – When both the variables are categorical.
     • Numerical and Numerical – In this type, both the variables of bivariate data, independent and dependent, are having numerical values.

3. The Bivariate Correlations procedure computes Pearson's correlation coefficient, Spearman's rho, and Kendall's tau-b with their significance levels.

   • Correlations measure how variables or rank orders are related. Before calculating a correlation coefficient, screen your data for outliers (which can cause misleading results) and evidence of a linear relationship.
   • Pearson's correlation coefficient is a measure of linear association. Two variables can be perfectly related, but if the relationship is not linear, Pearson's correlation coefficient is not an appropriate statistic for measuring their association.