validity

• validity is whether an observed effect is genuine and represents what is actually 'out there' in the real world
• internal validity is the control within a study for example, reduce demand characteristics
• external validity is the ability to generalise results to the settings, populations or eras
• ecological validity refers to whether findings can be generalised from one setting to another, most particularly generalised to everyday life. This may not relate to the setting like a lab but more to the realism of the participants' task
• temporal validity is when findings are consistent over time
• face validity is when a test looks like measures what it claims to
• concurrent validity refers to whether findings are similar to those on a well-established test. For example, a new intelligence test may be administered to a group of participants. Their scores at then compared with performance on a well-established test
• the 4 ways of improving validity are:

  • questionnaires
  • experiments
  • observations
  • qualitative research
• experiments improve validity by using a control group so that a researcher is more sure that changes in the dependent variable were due to the effect of the independent variable. Standardised procedure and single/double blind minimise impact of participant reactivity and investigator effects
• questionnaire improve validity as lies can control the effects of social desirability bias. Respondents are assured that all data submitted is confidential
• observations improve validity as behavioural categories are well-established, throughly operationalised and not ambiguous or overlappig
• qualitative research improves validity as it allows interpretive validity to be shown through the coherence of narrative and direct quotes from participants