Important Questions: Correlation

Q1: What is a simple correlation?
Ans: A simple correlation refers to the study of the relationship between only two variables. It measures both the degree (how strong) and the direction (positive or negative) of their linear association. The relationship is usually summarised by a correlation coefficient that ranges between -1 and +1. Simple correlation does not take into account other variables and does not by itself prove cause and effect.
Q2: When is the rank correlation method used?
Ans: The rank correlation method is used when variables are qualitative or measured in ordered categories (ordinal data), for example bravery, beauty, virtue or wisdom. Instead of using original numeric values, each observation is replaced by its rank and the association between ranks is measured. Common measures of rank correlation are Spearman's rank correlation and Kendall's tau. This method is useful when numerical measurements are not available or when the relationship is not linear.
Q3: Define the line of best fit.
Ans: The line of best fit is a straight line drawn through a scatter plot so that it represents the general direction of the data. It minimises the overall distance between the line and the points (commonly by the method of least squares, which minimises the sum of squared vertical deviations). The line provides a simple linear model of the relationship and is used for prediction and to summarise trends in the data.
Q4: What is the difference between negative and positive correlations?
Ans: In a positive correlation, variables move in the same direction: when one variable increases, the other also tends to increase (for example, hours of study and marks obtained, typically). In a negative correlation, variables move in opposite directions: when one variable increases, the other tends to decrease (for example, price and quantity demanded, typically). The strength of these associations is indicated by the magnitude of the correlation coefficient (closer to 1 or -1 means stronger association).
Q5: What is a multiple correlation?
Ans: Multiple correlation refers to the study of the relationship between one dependent variable and two or more independent variables considered together. It is summarised by the multiple correlation coefficient (R), which measures how well the set of independent variables, taken jointly, explains the variation in the dependent variable. Multiple correlation is used in multiple regression analysis to assess combined effects of several factors.
Q6: Define correlation.
Ans: Correlation is a statistical measure that quantifies the strength and direction of the relationship between two or more quantitative variables (for example, demand and price). It shows how changes in one variable are associated with changes in another. Importantly, correlation indicates association but does not by itself prove causation between variables.
Q7: The coefficient of correlation is between -1 and +1. Express it arithmetically.
Ans: Arithmetically, the coefficient of correlation r satisfies:  -1 ≤ r ≤ +1. A value of +1 indicates a perfect positive linear relationship, -1 indicates a perfect negative linear relationship, and 0 indicates no linear correlation (though a non-linear relationship may still exist).
Q8: Define partial correlation.
Ans: Partial correlation measures the relationship between two variables after removing the effect of one or more other variables. For example, the partial correlation between income and expenditure controlling for household size shows the direct association between income and expenditure when the influence of household size is held constant. It helps to isolate the unique association between two variables in the presence of others.
Q9: Explain the principal methods for calculating the coefficient of correlation.
Ans: The principal methods for calculating the coefficient of correlation include:

• Scatter diagram method: Plotting paired observations on a graph to visualise the relationship. The pattern of points suggests whether the association is positive, negative or absent and whether it is roughly linear.
• Karl Pearson's coefficient of correlation: A numerical formula that quantifies the strength and direction of a linear relationship between two quantitative variables. It produces a value between -1 and +1 and is widely used when data are measured on an interval or ratio scale.
• Spearman's rank correlation coefficient: A non-parametric method that uses ranks instead of raw values. It is suitable for ordinal data or when the assumptions for Pearson's coefficient are not met. It measures how well the relationship between two variables can be described by a monotonic function.

Q10: What is the nature of the correlation of two variables when they move in the same direction?
Ans: When two variables move in the same direction, the correlation is positive. This means that as one variable increases, the other variable also tends to increase. A positive correlation is indicated by a positive value of the correlation coefficient (between 0 and +1), and larger positive values denote a stronger tendency for the variables to rise and fall together.