Validity and reliability are two ways to measure the quality of a research study. Reliability refers to the consistency of the results, while validity refers to how accurately the study measures what it is supposed to measure.
Validity is assessed by comparing the results of the measure to established theories, other measures of the same concept, or real-world criteria. Reliability is assessed by comparing the results of the measure when it is administered on different occasions, by different raters, or in different forms.
Validity can be ensured by choosing appropriate methods of measurement and using appropriate sampling methods to select subjects. On the other hand, reliability can be ensured by applying the chosen methods consistently and standardizing the conditions of the research. While conducting experimental research, one needs to consider the internal and external validity of the experiment.
While validity and reliability are closely related, they mean different things. A measurement can be reliable without being valid, but a valid measurement is usually also reliable. Validity and reliability are essential considerations in quantitative research, from the design of the study to the interpretation of the results. Failing to adequately address these concepts can lead to bias and the production of inaccurate findings.
List of recommended resources #
For a broad overview #
This performance monitoring and evaluation TIPS guide by the USAID provides practical advice and suggestions about the five major data quality standards – validity, reliability, precision, integrity, and timeliness.
This DAC Guidelines and Reference Series developed by the OECD provides a broad overview of the overarching considerations regarding development evaluation.
For in depth understanding #
Co-written by Jos Vaessen, Sebastian Lemire and Barbara Befani, this book provides an overview of the approaches and methodological principles of evaluation design.
Written by Jerome Kirk and Marc L. Miller, this book discusses the role of reliability and validity and the problems that arise when these issues are neglected while conducting research.
Case study #
Written by Alice Danon, Jishnu Das, Andreas de Barros and Deon Filmer, this paper assesses the reliability and validity of cognitive and socioemotional skills measures and investigates the correlation between schooling, skills acquisition, and labor earnings using primary data from Pakistan.
This paper by Rachid Laajaj and Karen Macours tests the reliability and validity of some of the most commonly used skills measures in a rural developing context.
The blog post by Jim Frost provides a succinct overview of the relationship between reliability and validity and the various ways of assessing reliability in research.
This blog post provides a broad overview of reliability and validity, the different types of reliability and validity and ways of ensuring validity and reliability in research.