Reliability Quantitative Research
Reliability is the degree of consistency of the results obtained from a given research instrument. Researchers determine this by comparing the different versions of the same measurement. Internal consistency reliability methods like Cronbach’s Alpha looks into how consistent an individual item’s score is, with those of a set or subset of items.
On the other hand, the test-retest method involves determining the correlation between the same population datasets collected at different times, mostly within a two to three weeks (Bloomfield et al., 2019). On the other hand, the degree of agreement is the degree to which the various raters who completed times in a research instrument agree.
Validity Quantitative Research
Validity is the degree of accuracy of a given research instrument and is determined using content validity, whether the extent to which items of a research instrument represents the population’s actual traits (Bloomfield et al., 2019). Construct validity determines how accurate a measurement method represents the construct, while criterion-related validity where the researcher determines the extent to which the score collected using a given instrument correlate the future or external criterion.
Solvik & Struksnes (2018) used the test-retest reliability, by sending the participants two questionnaires within a six-month interval, ensuring that the dataset is stable over time and representative of the population under study. However, this type of reliability takes a long time to determine, thus slowing the overall research process (Bloomfield et al., 2019). Criterion-related validity was used, which is simple but costly and time-consuming.
- Bloomfield, J., & Fisher, M. J. (2019). Quantitative research design. Journal of the Australasian Rehabilitation Nurses Association, 22(2), 27.
- Solvik, E., & Struksnes, S. (2018). Training nursing skills: a quantitative study of nursing students’ experiences before and after clinical practice. Nursing research and practice, 2018.