This document discusses validity and reliability in quantitative research studies. Validity refers to how accurately a research instrument measures the concept it intends to measure. There are three types of validity: content validity, construct validity, and criterion validity. Reliability refers to the consistency of research instrument measurements and is assessed through homogeneity, equivalence, and stability. Ensuring validity and reliability of research instruments is important for conducting and evaluating rigorous quantitative studies.
This document discusses validity and reliability in quantitative research studies. Validity refers to how accurately a research instrument measures the concept it intends to measure. There are three types of validity: content validity, construct validity, and criterion validity. Reliability refers to the consistency of research instrument measurements and is assessed through homogeneity, equivalence, and stability. Ensuring validity and reliability of research instruments is important for conducting and evaluating rigorous quantitative studies.
This document discusses validity and reliability in quantitative research studies. Validity refers to how accurately a research instrument measures the concept it intends to measure. There are three types of validity: content validity, construct validity, and criterion validity. Reliability refers to the consistency of research instrument measurements and is assessed through homogeneity, equivalence, and stability. Ensuring validity and reliability of research instruments is important for conducting and evaluating rigorous quantitative studies.
Roberta Heale,1 Alison Twycross2 10.1136/eb-2015-102129 Evidence-based practice includes, in part, implementa- have a high degree of anxiety? In another example, a tion of the findings of well-conducted quality research test of knowledge of medications that requires dosage 1 studies. So being able to critique quantitative research is calculations may instead be testing maths knowledge. School of Nursing, Laurentian an important skill for nurses. Consideration must be There are three types of evidence that can be used to University, Sudbury, Ontario, given not only to the results of the study but also the demonstrate a research instrument has construct Canada 2 Faculty of Health and Social rigour of the research. Rigour refers to the extent to validity: Care, London South Bank which the researchers worked to enhance the quality of 1 Homogeneity—meaning that the instrument mea- University, London, UK the studies. In quantitative research, this is achieved sures one construct. through measurement of the validity and reliability.1 2 Convergence—this occurs when the instrument mea- Correspondence to: Validity sures concepts similar to that of other instruments. Dr Roberta Heale, Validity is defined as the extent to which a concept is Although if there are no similar instruments avail- School of Nursing, Laurentian accurately measured in a quantitative study. For able this will not be possible to do. University, Ramsey Lake Road, example, a survey designed to explore depression but Sudbury, Ontario, Canada 3 Theory evidence—this is evident when behaviour is P3E2C6; which actually measures anxiety would not be consid- similar to theoretical propositions of the construct rheale@laurentian.ca ered valid. The second measure of quality in a quantita- measured in the instrument. For example, when an tive study is reliability, or the accuracy of an instrument. instrument measures anxiety, one would expect to In other words, the extent to which a research instru- see that participants who score high on the instru- ment consistently has the same results if it is used in the ment for anxiety also demonstrate symptoms of same situation on repeated occasions. A simple example anxiety in their day-to-day lives.2 of validity and reliability is an alarm clock that rings at 7:00 each morning, but is set for 6:30. It is very reliable The final measure of validity is criterion validity. A cri- (it consistently rings the same time each day), but is not terion is any other instrument that measures the same valid (it is not ringing at the desired time). It’s important variable. Correlations can be conducted to determine the to consider validity and reliability of the data collection extent to which the different instruments measure the tools (instruments) when either conducting or critiquing same variable. Criterion validity is measured in three research. There are three major types of validity. These ways: are described in table 1. 1 Convergent validity—shows that an instrument is The first category is content validity. This category highly correlated with instruments measuring similar looks at whether the instrument adequately covers all variables. the content that it should with respect to the variable. In other words, does the instrument cover the entire 2 Divergent validity—shows that an instrument is domain related to the variable, or construct it was poorly correlated to instruments that measure differ- designed to measure? In an undergraduate nursing ent variables. In this case, for example, there should course with instruction about public health, an examin- be a low correlation between an instrument that mea- ation with content validity would cover all the content sures motivation and one that measures self-efficacy. in the course with greater emphasis on the topics that had received greater coverage or more depth. A subset of 3 Predictive validity—means that the instrument content validity is face validity, where experts are asked should have high correlations with future criterions.2 their opinion about whether an instrument measures the For example, a score of high self-efficacy related to concept intended. performing a task should predict the likelihood a Construct validity refers to whether you can draw participant completing the task. inferences about test scores related to the concept being studied. For example, if a person has a high score on a Reliability survey that measures anxiety, does this person truly Reliability relates to the consistency of a measure. A par- ticipant completing an instrument meant to measure Table 1 Types of validity motivation should have approximately the same Type of responses each time the test is completed. Although it is validity Description not possible to give an exact calculation of reliability, an estimate of reliability can be achieved through differ- Editor’s choice Content The extent to which a research instrument Scan to access more validity accurately measures all aspects of a ent measures. The three attributes of reliability are out- free content construct lined in table 2. How each attribute is tested for is Construct The extent to which a research instrument described below. validity (or tool) measures the intended construct Homogeneity (internal consistency) is assessed using Criterion The extent to which a research instrument item-to-total correlation, split-half reliability, Kuder- validity is related to other instruments that Richardson coefficient and Cronbach’s α. In split-half measure the same variables reliability, the results of a test, or instrument, are
66 Evid Based Nurs July 2015 | volume 18 | number 3 |