Generalisability (DP IB Psychology): Revision Note

Generalisability

• Generalisability in research refers to the extent to which a study's findings can be applied to a wider population, setting, or time frame

  • E.g., Kyle et al.'s (2016) study of the prevalence of obesity has good generalisability as they used a sample of 13,483 participants (this ensures secure statistical power)

    • However, as the sample were all nurses in Scotland this limits the extent to which the findings can be generalised to other populations

Types of generalisability

Sample generalisability

• Sample-population generalisability involves inferring the results derived from a sample and applying it to a population

• To do this, the sample must be:

  • a random and representative sample

  • a sufficiently large sample size - the larger the sample the stronger the generalisability

• Small, specific samples cannot easily be generalised, which is why (in quantitative research) there is power in numbers

Inferential generalisability

• Inferential generalisability means that the study's findings can be applied to other settings or populations outside the setting of the study

• This is linked to external validity, e.g.,

  • Dickerson (1992) investigated prosocial behaviour in a real-world context

  • Boyden (2003) documented the experiences of children in war zones

Theoretical generalisability

• Theoretical generalisability means that concepts or theories developed from findings can inform further research and theory-building

• This type of generalisability is more common with qualitative research, where the aim is often to generate new insights rather than to generalise statistically

  • Qualitative research aims for transferability, i.e., whether the insights derived from the research can be transferred to help our understanding of similar contexts

Link to validity

• Generalisability is a component of validity, particularly external validity

• External validity is the extent to which findings can be applied to real-life contexts, populations, or times

• High external validity is achieved when tasks are realistic or when participants are genuinely engaged, even in artificial settings