Making Sense of Medical Statistics: A Bite Sized Visual Guide

This book provides a comprehensive overview of medical statistics, explaining fundamental concepts and commonly used tests with anecdotes, illustrations, and online resources. It is designed for physicians to gain confidence in performing statistical analyses.

Format: Paperback / softback
Length: 160 pages
Publication date: 21 October 2021
Publisher: Cambridge University Press

Do you want to know what a parametric test is and when not to perform one? Do you get confused between odds ratios and relative risks? Want to understand the difference between sensitivity and specificity? Would like to find out what the fuss is about Bayes theorem? Then this book is for you! Physicians need to understand the principles behind medical statistics. They don t need to learn the formula. The software knows it already! This book explains the fundamental concepts of medical statistics so that the learner will become confident in performing the most commonly used statistical tests. Each chapter is rich in anecdotes, illustrations, questions, and answers. Not enough? There is more material online with links to free statistical software, webpages, multimedia content, a practice dataset to get hands-on with data analysis, and a Single Best Answer questionnaire for the exam.

Parametric tests are statistical procedures that assume certain underlying assumptions about the data, such as normality and equal variances. They are commonly used in hypothesis testing when the data follows a specific distribution. On the other hand, non-parametric tests do not make these assumptions and are more robust to outliers and non-normal data. They are often used when the data does not meet the assumptions of parametric tests.

The choice between parametric and non-parametric tests depends on the nature of the data, the research question, and the assumptions made. Parametric tests are generally more powerful and precise when the data follows a specific distribution, while non-parametric tests are more flexible and robust when the data does not meet these assumptions.

One common example of a parametric test is the t-test, which is used to compare the means of two groups. The t-test assumes that the data follows a normal distribution and that the variances of the two groups are equal. If these assumptions are met, the t-test can provide a statistically significant test of the null hypothesis that the means of the two groups are equal.

However, if the data does not meet these assumptions, the t-test may not be appropriate. For example, if the data is skewed or contains outliers, the t-test may produce inaccurate results. In such cases, non-parametric tests, such as the Mann-Whitney U test or the Kruskal-Wallis test, may be more appropriate.

Another example of a parametric test is the chi-square test, which is used to test the independence of two categorical variables. The chi-square test assumes that the variables are categorical and that the frequencies of the categories are equal. If these assumptions are met, the chi-square test can provide a statistically significant test of the null hypothesis that the variables are independent.

However, if the data is not categorical or the frequencies of the categories are not equal, the chi-square test may not be appropriate. In such cases, non-parametric tests, such as the Fisher's exact test or the McNemar's test, may be more appropriate.

In conclusion, parametric and non-parametric tests are two different types of statistical procedures that are used to analyze data. Parametric tests assume certain underlying assumptions about the data, while non-parametric tests do not. The choice between these tests depends on the nature of the data, the research question, and the assumptions made. Physicians need to be aware of the differences between these tests and choose the appropriate test for their data analysis.

Weight: 352g
Dimension: 157 x 233 x 16 (mm)
ISBN-13: 9781108978156
Edition number: New ed