Validity is the extent to which a tool measures a variable it is intended to measure (Ellis, Harley & Walsh, 2010). It refers to the ability of a tool to give an accurate measurement of a variable. Validity is a method of measuring accuracy in research. Validity can be assessed using various methods. They include face validity, comparative validity, external validity, and theoretical validity.
Face validity is an assessment method based on the appearance of the measuring tool. That is, it relies on its face value. If at a glance, a tool appears to measure a variable accurately, then it can be considered valid. However, face validity must be combined with others when assessing validity.
Comparative validity is an assessment tool that compares two or more tools of measurement. If similar results are obtained, then the tools can be considered valid. If different results are obtained, then one of the tools is invalid.
External validity tests the relationship between tools. External validity can be classified into concurrent external validity and predictive external validity.
Theoretical validity assesses the degree to which agrees with basic theories. This tool requires variables that are associated with refined theoretical concepts.
Reliability refers to the ability of a tool to produce consistent results (Ellis, Harley & Walsh, 2010). If the results obtained using a particular tool are consistent, then the tool can be said to be reliable. Reliability can also be defined as the degree to which a tool of measurement can reproduce particular results. For example, a tape measure that produces a similar error in all measurements can be said to be reliable. This is because the error is consistently reflected in all the values obtained. Forms of reliability include test-retest reliability, inter-rater reliability, inter-item reliability, and cross-test reliability.
Test-retest reliability involves assessment of reliability on two separate occasions then comparing the results. This is used to assess the reliability of tools in situations that remain constant over a period of time. If the results obtained do not show consistency, then the tool can be considered unreliable. Cross-test reliability compares different tests intended to measure a certain variable. Inter-rater reliability is an indirect method of assessment (uses raters/judges). The results obtained by raters are used to construct the reliability of the tools of measurement. That is, if different raters appear to settle on a certain outcome, then the tool can be considered reliable. Inter-item reliability refers to an assessment of outcomes associated with different items in a tool that has different levels of variables.
None of the two measures of accuracy (validity and reliability) is more important than the other. Both measures are important in research. Improvement of one measure may lead to improvement of the other. Validity and reliability improve the generalizability of research results. However, it is important to strike a balance between the two measures of accuracy. When examining these tools, it is important to remember that it is difficult to find absolutely valid or reliable values in qualitative research (Golafshani, 2003).
Measures of accuracy include reliability, validity, and precision. Precision refers to the ability of a tool of measurement to produce a value that is as close to the real value as possible.
Ellis, L., Harley, R., & Walsh, A. (2010). Research Methods in Criminal Justice and Criminology: An Interdisciplinary Approach. Maryland: Rowman & Littlefield Publishing Group.
Golafshani, N. (2003). Understanding reliability and validity in qualitative research. The Qualitative Report, 8(4), 597-606. Web.