Univariate data involves a single variable. The prefix “uni” refers to “one,” indicating that this type of data deals with only one variable at a time. For example, analyzing the heights of students in a classroom. Here, the variable is “height”.
Since there is only one variable, the analysis focuses on understanding the distribution, central tendency (mean, median, mode), and dispersion (range, variance, standard deviation) of that variable.
Common plots include histograms, bar charts, pie charts, and box plots. These visualizations help to summarize and understand the patterns and distribution of the data.
Types of tests – descriptive statistics, Normality Test, Z-scores, One-Sample t-test.
Bivariate data involves two variables. The prefix “bi” refers to “two,” indicating that this type of data examines the relationship between two different variables. For example, examining the relationship between study hours (independent variable) and test scores (dependent variable) of students. The relationship could be causal, dependency or correlation.
Scatter plots, line charts, and heat maps are commonly used to visualize bivariate data. These plots help to identify correlations and trends between the two variables.
Types of Bivariate Tests: Correlation analysis, regression analysis, Chi-Square Test of Independence, t-tests and ANOVA.
Multivariate data involves more than two variables. The prefix “multi” refers to “many,” indicating that this type of data analysis involves examining the relationships among three or more variables simultaneously. For example, analyzing the impact of different factors like age, income, education level, and marital status on purchasing behavior.
Multivariate data involves more complex analysis because it considers the interdependencies and relationships among multiple variables. It requires advanced statistical methods to understand these relationships fully.
Multidimensional scatter plots, parallel coordinates plots, and pair plots are some common ways to visualize multivariate data. In some cases, dimensionality reduction techniques like PCA (Principal Component Analysis) are used for visualization.
Types of Multivariate Tests: Multivariate Analysis of Variance (MANOVA), Multiple Regression Analysis, Factor Analysis, Cluster Analysis, Principal Component Analysis (PCA).