In This Article Expand or collapse the "in this article" section Statistics in Public Health

  • Introduction
  • Displaying Data
Back to top

Public Health Statistics in Public Health
by
David L. Streiner
  • LAST MODIFIED: 26 July 2017
  • DOI: 10.1093/obo/9780199756797-0165

Introduction

Statistics refers to a branch of mathematics that is concerned with the description and analysis of data. It is generally divided into two parts: “descriptive statistics” and “inferential statistics.” As the name implies, descriptive statistics summarize data numerically and graphically, allowing the user to easily grasp their basic features to see, for example, if there are any underlying patterns. These numerical summaries consist of measures that describe the central tendency of the data (where the bulk of the data lie) and their variability or dispersion (how spread out the data are). Other indices can indicate whether or not the data are symmetrically distributed (the skewness) and whether the tails of the distribution are heavier or thinner than what is theoretically expected (the kurtosis). Graphical techniques traditionally consisted of line charts, bar charts, histograms, and pie charts. Recent innovations, such as box plots and stem-and-leaf plots, as well as the ability to interact with the data on computers, have greatly expanded the ability to visualize data. By far the larger realm is inferential statistics. They serve two purposes. Within the context of studies, either surveys or experiments, they allow the researcher to determine the probability that any differences between or among groups were real or that they may have happened due to the play of chance. That is, if we were to randomly draw two samples from the population and do nothing different to either group, their scores on some variable will differ, simply because of sampling. Consequently, if we did do something different to one group, such as giving them an experimental drug, and we were to find a difference, inferential statistics would allow us to determine the probability that the results were due to the intervention as opposed to chance variation. The other purpose of inferential statistics is to be able to generalize the results from the sample of people in the study to the entire population, where the term population means everyone we are interested in, such as those who will most likely vote in the next election, or people who suffer from a particular disorder; it rarely means everyone in the world. Within recent years, the term biostatistics has entered the lexicon. It refers to the application of statistics to the biological sciences and medicine. The techniques are identical to those used in statistics, although there is greater focus on measures of impact, such as relative risk and odds ratios.

General Overviews

There are literally thousands of textbooks about statistics, appearing in most fields of inquiry: psychology, medicine, economics, rehabilitation, education, engineering, and so forth. For the most part, they cover the same statistical techniques, and differ primarily with respect to the nature of the examples used to illustrate them. They also differ in terms of emphasizing application and interpretation as opposed to the mathematical underpinnings of the techniques.

back to top

Users without a subscription are not able to see the full content on this page. Please subscribe or login.

How to Subscribe

Oxford Bibliographies Online is available by subscription and perpetual access to institutions. For more information or to contact an Oxford Sales Representative click here.

Article

Up

Down