Reason for Using Frequency and Percentage to Analyse Categorical Data

Abstract

Categorical data are commonly generated in research through demographic questions, survey responses, classifications and other variables that place observations into distinct groups or categories. Appropriate analysis is important because the method should match the nature of the data collected. Frequency and percentage are among the most useful descriptive statistical techniques for analysing categorical data because they show how observations are distributed across categories and make results easy to interpret and compare. Frequency indicates the number of observations in each category, while percentage expresses that distribution relative to the total number of observations. This article discusses why frequency and percentage are used to analyse categorical data, regardless of the degree or level of study. It explains their suitability for nominal and other categorical variables, their ability to summarise large quantities of data, facilitate comparison, reveal patterns and support clear presentation of findings. The article also discusses using a 50% benchmark to interpret percentages from both non-Likert and Likert scale responses. It concludes that frequency and percentage provide a simple, transparent and appropriate approach for describing categorical data, particularly in descriptive survey research.