Unit 2 - Validity

What is meant by ‘validity’?

How truthful or accurate something is.

What are the two types of validity?

Internal validity and external validity.

What does ‘internal validity’ refer to?

Findings being accurate and the effects on the dependent variable are caused by the independent variable, meaning the study measures what it intends to measure.

What does ‘external validity’ refer to?

Whether the study paints a true picture of real-life behaviours (if the tasks have ‘mundane realism’) and whether the findings would apply to different places, times or people (population validity).

What does ‘mundane realism’ refer to?

Whether tasks are ‘everyday’ usual occurrences.

What type of validity refers to how representative a study is?

Population validity. If a study has high population validity, the study has been conducted on a diverse sample.

What can samples that lack external validity be considered as?

Ethnocentric (culturally biased) and androcentric (gender biased).

What are three validity issues that impact internal and external validity?

Researcher bias, demand characteristics and social desirability.

What is ‘researcher bias’?

Where the researcher either directly or indirectly influences the results of a study, either through the process of designing the study or through the way research is analysed or conducted. Double blind procedures eliminate researcher bias as they can’t give advice to participants.

What are ‘demand characteristics’?

A type of confounding variable where participants unconsciously work out the aim and act differently, usually through social desirability or the ‘screw you effect’ – where participants will act in a manner that ruins results. Single blind trials reduce demand characteristics, and double blind trials mean that participants can’t work out the aim and change their behaviour accordingly.

What is ‘social desirability’?

Where participants give the response that they think will show them in the best possible light, and their responses may not be a true reflection of their views as a result. This can be reduced by giving participants anonymity and confidentiality when they give their answers, so they are more inclined to answer honestly.

What are the methods of checking internal and external validity?

Face validity, predictive validity, content validity, concurrent validity and construct validity.

What is ‘face validity’?

The least sophisticated measure of validity, simply whether the test appears to measure what it claims, making it subjective.

What is ‘predictive validity’?

The degree to which a test accurately forecasts a future outcome or more broadly related topic.

What is ‘content validity’?

This objectively checks whether the method of measuring behaviour is accurate and decides whether it is a fair test which achieves the aim of a study (internal). This is carried out by asking an expert to assess the validity.

What is ‘concurrent validity’?

Validating a measurement by comparing it with an established one that has known validity. If there are similar results, the new test has concurrent validity.

What is ‘construct validity’?

The most sophisticated test of validity, looking at the overall results, reflecting the phenomena (external validity).