5.2.2 Validity

Validity describes the extent to which a study measures what it intends to measure, without systematic bias. To understand validity, we need a few terms to describe different populations:

  • target (reference) population – the population to which the results will be applied or extrapolated
  • source (study) population – actual population from which eligible study subjects are drawn
  • study sample – the units selected from the source population
  • sampling unit – the epidemiological unit in which we are measuring exposure and outcome (e.g. individual animals or herds). The term ‘sampling unit’ has the same meaning as data unit in this context.

There is more information about these concepts in the modules on Sampling.

As shown in Figure 5, validity can be divided into:

  • internal validity – the degree to which study results are representative of true study population values: the ‘truth’ within the study
  • external validity – the degree to which study results can be extrapolated to the target population: the ‘truth’ outside the study.
Described image
Figure 5 External and internal validity.
Show description|Hide description

A schematic diagram showing a source population as a subset of the target population, and a study sample as a subset of the source population. External validity represents the extent to which the source population can be extrapolated to the target population, and internal validity the extent to which the study sample represents the source population.

Figure 5 External and internal validity.

Activity 16: Validity in your workplace

Timing: Allow about 15 minutes

Think about your own workplace. What populations are sampled? For example, does your organisation mainly treat or conduct testing on healthy individuals, or sick individuals (people or animals)? What are the implications for internal and external validity? What can be done to improve the validity of your studies?

To use this interactive functionality a free OU account is required. Sign in or register.
Interactive feature not available in single page view (see it in standard view).

Discussion

Here are some suggestions for improving validity:

  • Make sure you are sampling representative data points. For example, don’t just sample broiler chickens reared in a large commercial farm if you want to learn about AMR in chickens in a country where most chickens are raised by smallholders.
  • Evaluate the validity of a study when interpreting its results. Don’t make conclusions at a population level based on a study with a biased, non-representative sample.
  • Increase access to training like this module to educate your colleagues and peers on the importance of validity.

5.2.1 Accuracy and precision

6 End-of-module quiz