Descriptive Statistics – Measures of association

In the earlier notes on descriptive statistics, we covered descriptive statistics for univariate analysis using both graphical and analytical tools.

In the graphical tools for the univariate analysis, we have seen different plotting techniques such as histogram, scatter plot, and kernel density functions to visualize the characteristics of individual data points within a variable. Compared to the analytical tools for univariate analysis, we have learned the different measures such as the central tendency of data, dispersion or variability of data, and shape of the distribution curve by skewness and kurtosis.

All these concepts were practical to study the characteristics of frequency or distribution curves. However, to find the degree of association between two variables, we need a bivariate analysis. The bivariate analysis measures the degree of association between variables.

Let us understand the association of two variables from the natural phenomenon.

Association of Two Variables

  • The number of hours of study affects the mark obtained in an examination.
  • Electricity/power consumption increases when the weather temperature rises.
  • The weight of infants and small children increases as their height increases under normal circumstances.

All these above examples are the learning from the experiences or observations from our daily life. Now the question comes, how to realize similar concepts graphically or quantify these mathematically.

Again, in the descriptive statistic, we can use two tools to measure the degree of association between two variables. The first one is a graphical tool, and the second one is a quantitative tool. In the graphical tools we will see how to use bivariate analysis using various plots.

In the next note of descriptive statistics, we will cover both graphical and quantitative tools to measure the relationship between variables.

Q&A

From this note, we can get answers to the following questions.

  • How to measure the association between two variables?
  • Why is it important to quantify the degree of association between two variables?
  • Which is a measure of association between categorical variables?
  • Which is a measure of association between ordinal variables?
  • Which is a measure of association between numerical variables?

References

  1. Descriptive Statistic, By Prof. Shalabh, Dept. of Mathematics and Statistics, IIT Kanpur.

 131 total views,  1 views today

Scroll to Top
Scroll to Top
%d bloggers like this: