My master’s thesis method is based on qualitative content analysis. After the interviews, I did the coding and analysis. Since I am the only coder, I can not use methods that compare two coders, what methods should I use to determine the validity and reliability of the codes and their results?
Dear Aida,
Yes it is not possible to test for validity and reliability of qualitative data. However, you can ensure that your findings is valid and reliable through the processes of collecting, analysing and presenting your findings. It is called trustworthiness and rigour.
Check this link on rigour in qualitative research. ... https://doi.org/10.5014/ajot.45.3.214.
After coding and analysing you data, you need another person or even two who are experienced in qualitative data analysis, to also code and analyse so you can compare. When there is conflict and consensus is not reached, you might need a third person's opinion to resolve.
You can also get an expert in qualitative data analysis to review your coding and analysis process and the themes generated. This is called peer-debriefing. Your supervisor(s) may be the best person(s) to help you out with this.
Reliability and validity is to quantitative research as trustworthiness and rigour is to qualitative research.
Kind regards!
Eric
Yes, I agree with Eric Nkansah Opoku; the terms you mention are more associated with quantitative research.
His response and the link he suggests are very good; you might also like to look at:
Ghafouri, R., & Ofoghi, S. (2016). Trustworth and rigor in qualitative research. International Journal of Advanced Biotechnology and Research, 7(4), 1914-1922.
Article Trustworth and Rigor in Qualitative Research
I used Guba and Lincoln and Lincoln and Guba when I wrote my thesis, but I couldn't see the references in the article above, so these are my references:
Lincoln YS, Guba EG. Naturalistic Inquiry. Newbury Park, CA: Sage; 1985.
Guba EG, Lincoln YS. Fourth Generation Evaluation. Newbury Park, CA: Sage; 1989.
I think the reference regards the latter, in which Guba and Lincoln discuss the qualitative terms and relate them to the quantitative values; e.g. dependability for reliability. Prof Raziyeh Ghafouri and Sudabeh Ofoghi give a very good description of qualitative terms in relation to quantitative terms.
Also agree with Eric and Mary that trustworthiness is critical for qualitative data.
Here is the 4th in a series of short readings that we give to our research students.
Aida Aminifar - Guba and Lincoln (1989) propose the research should satisfy four criteria. They are credibility, transfer-ability, dependability, and confirm-ability. In qualitative research, validity is discussed in terms of the credibility, transfer-ability, dependability, and confirm-ability of the instrumentation and results of the study. The validity of a content analysis study is the correspondence of the categories to the conclusions, and the generalization of results to a theory.
I think, you can use triangulation method and it refers to gain a good understanding from different perspectives of an investigated phenomenon by using multiple methods or data sources in qualitative research. It is a qualitative research strategy to test validity through the convergence of information from different sources and its purpose is to increase the credibility and validity of the results. Norman (1978) Denzin has identified four basic types of triangulation: 1) data triangulation: the use of multiple data sources in a single study; 2) investigator triangulation: the use of multiple investigators/researchers to study a particular phenomenon; 3) theory triangulation: the use of multiple perspectives. Please see Alan Bryman (Social Research Methods, Oxford) for further reference.
I think it depends on just how qualitative your qualitative content analysis was. If the work that you did was primarily inductive and interpretive, then I certainly agree with the previous comments.
But, if you used a predetermined, deductive codebook and counted codes to reach your conclusions, then it would be traditional to have a second coder for inter-rater reliability.
Dear Mrs Aminifar,
Doing qualitative content analysis, I have really been helped by this book: Schreier, M. (2012). Qualitative content analysis in practice. Especially on pages 166-193 Professor Schreier has refered how to ensure validity and reliability. She has proposed that a solo coder can ensure reliability by doing the analysis after at least ten days after the first.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Probability
- Probability Theory
- Reliability