May 2026 CPHQ Prep Virtual Class-Data Types

Data Types

Pdf Summary

The document explains why understanding data types is essential for both collecting and analyzing research data. It distinguishes between two broad variable types: quantitative and qualitative (categorical). Quantitative variables include continuous variables, which can theoretically take any value in an interval (such as height, body mass, or blood pressure), and discrete quantitative variables, which take only specific numeric counts with meaningful numeric interpretation (such as number of pregnancies or hospitalizations). Qualitative variables include nominal variables, which have no inherent order (such as sex), and ordinal variables, which do have a meaningful order (such as histologic stage).<br /><br />A major point of the article is that data type should guide how variables are recorded. If a variable is originally continuous, it is usually better to collect the raw continuous data rather than only a simplified category, because continuous data contain more information and allow more flexible analysis later.<br /><br />Data types also determine the appropriate statistical summaries and tests. Continuous variables are usually summarized with measures like mean, median, minimum, maximum, and standard deviation, while categorical variables are summarized with frequencies and proportions. For example, body temperature is continuous and should be summarized with means or medians, while diabetes status is nominal and should be summarized by counts and percentages.<br /><br />The article also shows how data types affect hypothesis testing. If comparing a continuous outcome across two groups, such as body temperature by gender, a two-sample t-test may be appropriate. If comparing a categorical outcome, such as diabetes status by gender, a chi-square or Fisher’s exact test is more suitable.<br /><br />Overall, the article emphasizes that choosing the right data type is crucial for meaningful data collection, clear reporting, and correct statistical analysis.

Keywords

data types

quantitative variables

qualitative variables

continuous variables

discrete variables

nominal variables

ordinal variables

statistical analysis

hypothesis testing

categorical data