Descriptive and Inferential Statistics in Biomedical Sciences: An Overview

Abstract

Statistical literacy is essential for understanding medical literature and conducting biomedical research. Data constitute the raw material for statistical work. Descriptive statistics summarizes data from a sample or population. Categorical data are described in terms of percentages or proportions. With numerical data, individual observations tend to cluster about a central location, with more extreme observations being less frequent. Measures of central tendency summarize the extent to which observations cluster while the spread is described by measures of dispersion. There is no way of assessing true population parameters by observing samples alone. We can, however, obtain a standard error and use it to define a range in which the true population value is likely to lie with a given level of uncertainty. This is the confidence interval (CI), Conventionally, the 95% CI is used. The commonly encountered pattern in data sets is the normal distribution which appears as a symmetrical bell-shaped curve. Much of medical research begins with a research question that can be framed as a hypothesis. Inferential statistics starts with a null hypothesis that reflects the conservative position of no change or no difference in comparison to the baseline or between groups. Usually, the researcher believes that there is some effect which is the alternative hypothesis. Thinking of the research hypothesis as addressing one of five generic research questions helps in selection of the right hypothesis test. This chapter aims to introduce the basic tenets of descriptive and inferential statistics without delving into the mathematical depths.