Validity and reliability are a common barometer of quality when it comes to quantitative research. However, there is also a benefit in assessing quality and trustworthiness in qualitative research. In this article we will learn what validity and reliability are, how they are measured in quantitative research, and how we can assess the credibility of qualitative research.
What are Validity and Reliability?
Validity and reliability are collections of approaches that help determine the quality of quantitative research. Reliability is the extent to which a scale produces consistent results if repeated measurements are made on a characteristic. There are a few ways to test reliability, most notably:
- Test-retest– Respondents are administered identical sets of scales at different times, ideally under the same conditions.
- Alternative forms– Two equivalent forms of a scale are developed and then asked and measured twice.
Validity is the extent to which differences in scale scores reflect true differences among objects on the characteristic being measured – rather than errors. It helps determine whether the research truly measures what is intended. There are a few questions that can be asked to assess the validity of your research:
- Construct – What construct or characteristic is the scale measuring?
- Content – How representative is the content of the scale that is used to measure?
- Criterion – Does the scale perform as expected in relation to other variables (that were selected as meaningful criteria)?
How Are Validity and Reliability Applied to Qualitative Research?
Qualitative research is fundamentally different than quantitative research. The purpose of the research is different, the methodologies typically used are different, and the way data is collected and analyzed is different. Therefore, it is to be expected that the trustworthiness of the research would have to be measured differently as well. Although we cannot apply the same exact validity and reliability approaches for qualitative research as we do for quantitative, we can still run tests and ask ourselves questions that are inspired by quantitative approaches to get the same type of confidence in our qualitative research.
To check validity and reliability in our research, we need to ensure that the themes that are emerging are dependable and consistent. To do that we need to focus on ensuring that our research is impartial and does not suffer from any bias originating from the researcher, the sampling, or the way we are collecting and analyzing data. Some good ways to do that:
- Collaborate with other researchers to ensure your personal biases are not getting in the way.
- Keep accurate and detailed documentation to ensure your themes are represented authentically and reflect the data that was collected.
- Incorporate as much verbatim and quotes from respondents as possible to support and demonstrate your themes and findings.
- Maintain a “decision-trail” so that your decisions as a researcher are transparent and clear. Try to think, ‘Would another researcher reach the same conclusions independently?’
It is also advantageous to use a methodology that combines the best of both qualitative and quantitative research. At Invoke, we are able to ensure the validity, reliability, and trustworthiness of our research by using the methods described above. Armed with an arsenal of highly experienced researchers and our patented technology, every small piece of data is captured and accounted for. On top of that, the collaborative nature of our sessions ensures an unbiased view into respondents’ thoughts and feelings.