What are validity and reliability in Quantitative research?
Question
how validity and reliability are achieved in quantitative research?
Answer
Quantitative research is the process of a systematic investigation, primarily using numerical techniques (statistical, mathematical or computational), to test hypothetical generalisations. As a way of measuring the likelihood of the researcher’s result being misleading, statisticians developed procedures for expressing the likelihoods and accuracy of the results. These procedures help demonstrate the rigour and usefulness of the researcher’s work.
Rigour, in quantitative studies, refers to the extent the researchers worked to enhance the quality of the study; this is achieved through measurement of reliability and validity.
Reliability refers to the consistency of the measurements or the degree to which an instrument measures the same with every use under the exact same conditions. Reliability is usually estimated using internal consistency – the relationship/correlation between different results of a test, or instrument. These correlations are most commonly measured using Cronbach’s α coefficient; a statistical test that ‘splits’ all the results in half and calculates the correlations between the two sets. From this, a single value between 0-1 is generated and the closer the coefficient generated is to 1, the higher the reliability estimate of your instrument/test.
Validity is defined as the extent to which a measure or concept is accurately measured in a study. In essence, it is how well a test or piece of research measures what it is intended to measure. In quantitative studies, there are two broad measurements of validity – internal and external.
Internal validity is an estimate of the degree to which conclusions about causal relationships can be made based on the research design. Internal validity utilises three approaches (content validity, criterion-related validity and construct validity) to address the reasons for the outcome of the study.
External validity is the extent the results of a study can be generalised to other populations, settings or situations; commonly applied to laboratory research studies. This validity can usually be divided into population validity and ecological validity; essential elements in judging the strength of an experimental design.