Posts

Showing posts from February, 2019

Correlation Analysis

Correlation Analysis A correlation analysis is a statistical technique which quantifies the relation between two variables in a model. It is used to understand the nature of relationships between two individual variables. It measures the strength of association between the variables. Correlation analysis gives a great privilege to the Data Scientists to identify the implication of a variable on other variables in the model. With it's prominence in predicting the relationship between the variables, it is considered to be one of the most important techniques used in Exploratory Data Analysis (EDA). It's been highly misunderstood that correlation analysis determines cause and effect. All that correlation explains is the association between the variables and not the causation. It is much suitable for continuous variables than categorical variables. A correlation between two variables can be either positive, negative or neutral. Positive Correlation - Increase ...