Confounding refers to a mixing or muddling of effects that can occur when the relationship we are interested in is confused by the effect of something else. It arises when the groups we are comparing are not completely exchangeable and so differ with respect to factors other than their exposure status. If one (or more) of these other factors is a cause of both the exposure and the outcome, then some or all of an observed association between the exposure and outcome may be due to that factor.

This chapter gives an introduction to key concepts in epidemiology for the clinician, student, trainee or early career researcher interested in psychiatry and mental health. Following a brief introduction to the history of epidemiology, we provide a comprehensive, yet accessible introduction to key epidemiological concepts and how these apply to psychiatry and mental health. We introduce the major observational (cohort, case-control, cross-sectional, ecological) and experimental (randomised controlled trial) designs used in epidemiology, their strengths and limitations and specific issues for their use in psychiatry. We also cover measures of disease frequency (incidence, prevalence), measures of effect (risk, rate and odds ratios) and measures of impact (population attributable risk). Our chapter then provides a comprehensive introduction to traditional and contemporary approaches to understanding the critical issue of causation, illustrated via the use of causal diagrams known as Directed Acyclic Graphs. Throughout, we use accessible examples from published research and hypothetical worked examples to consolidate the reader’s knowledge about key methods in psychiatric epidemiology.

At the core of epidemiology is the use of quantitative methods to study health, and how it may be improved, in populations. It is important to note that epidemiology concerns not only the study of diseases but also of all health-related events. Rational health-promoting public policies require a sound understanding of causation. The epidemiological analysis of a disease or activity from a population perspective is vital in order to be able to organize and monitor effective preventive, curative and rehabilitative services. All health professionals and health-service managers need an awareness of the principles of epidemiology. They need to go beyond questions relating to individuals to challenging fundamentals such as ‘Why did this person get this disease at this time?’, ‘Is the occurrence of the disease increasing and, if so, why?’ and ‘What are the causes or risk factors for this disease?’

Chapter 16 covers AN INTRODUCTION TO MULTIPLE REGRESSION and includes the following specific topics, among others: Confidence Intervals, Statistical Significance of b-Weight, Fit of the Overall Regression Equation, R and R-squared,Adjusted R-squared, Semipartial Correlation, Partial Slope, Confounding, and Statistical Control.

Chapter 16 covers an introduction to multiple regression and includes the following specific topics, among others: confidence intervals, statistical significance of the b weight, fit of the overall regression Eeuation, R and R-squared, adjusted R-squared, semipartial correlation, partial slope, confounding, and statistical control.

Confronting models with data is only effective when the statistical model matches the biological one and the structure of your data collection is right for the statistical model. We outline some basic principles of sampling, emphasizing the importance of randomization. Randomization is also essential to experimental design, but so are controls, replication of experimental units, and independence of experimental units. This chapter emphasizes the distinction between sampling or experimental units representing independent instances and observational units representing things we measure or count from those units. Observational units may be subsamples of experimental units, but shouldn’t be confused with them. In this chapter, we also introduce methods for deciding how much data you need.

In Chapter 4, the modelling of the time variable in longitudinal data analysis is discussed. In general, a distinction can be made between time as a continuous variable and time as a categorical variable represented by dummy variables. The latter is only possible in a longitudinal study with fixed time-points. Basically, three different situations are explained. (1) Growth curve analysis; i.e. when the time variable is the covariate of interest. Regarding growth curve analysis, the chapter also includes a discussion about latent class growth curve modelling. (2) The time variable as a potential confounder. When the time variable is a potential confounder it is argued that it is important to distinguish the time variable from age and (3) the time variable as effect modifier. When the time variable is an effect modifier, the interest is either in a different development over time for different groups or in a different relationship between an outcome variable and a covariate in different parts of the longitudinal study. Both situations are discussed in detail. All methods are accompanied by extensive real-life data examples.

Bias means systematic error. Its most common form is confounding bias, where various factors in the context of treatment influence the results, without the awareness of clinician or patient. Incorrect claims are made when these confounding factors are ignored. Randomization is the best solution to confounding bias. Clinical examples are provided for antidepressant discontinuation in bipolar depression and for the relationship between substance abuse and antidepressant-related mania. Other forms of bias are discussed, such as measurement bias.

Social Science Experiments: A Hands-on Introduction is an accessible textbook for undergraduates. Why a hands-on approach that urges readers to roll up their sleeves and conduct their own experiments? When students design their own experiments, they must reflect on basic questions. What is the treatment … and control? Who are the participants? What is the outcome? The process of conducting an experiment builds other important skills: Creating a dataset, inspecting the results, and drawing inferences. Learning is easier when the motivation to acquire specific skills emerges organically through hands-on experience.

Chapter 11 aims to summarize the key messages in the book by applying them to our thinking during the coronavirus crisis. I show how many of the concepts – from psychology and formal modelling – recur in expert and lay reasoning during the pandemic. I argue that the danger of jumping to premature causal claims, without careful evidence evaluation, is particularly rife in situations of radical uncertainty. But causal thinking is also an essential tool for dealing with such crises.

The statistical methods used in projects conducted within the Taï Chimpanzee Project have changed considerably in the ongoing duration (about four decades) of this project. In particular, while initially classic tests focusing on statistical significance dominated the analyses, we now largely see the application of linear models. Here, I review this change and discuss the implications it has, and I also compare and contrast the classic statistical tests with contemporary analytical approaches. I argue that modelling not only allows for a better control of confounders and sources of non-independence, but also means to address more informative questions and, hence, reveals more informative answers. Finally, I discuss to what extent carefully designed models bridge the gap between the gold standard (randomized experiments) and observational studies.