I have to present a seminar on Types of Validity -
In that perspective
1. How do you pretest and pre-design a questionnaire? Is it same as Pilot study?
2. In context to medical parlance - how would we explain criterion , content , face , concurrent and translational validity and other types?
Appreciate your cooperation
Kindly please attach any relevant pdf and please if possible give suitable examples
Thanking you
Dear Ashish,
To answer your first question, a pilot study can assist you to validate or pre-test a questionnaire. However, designing a questionnaire is a separate process which may involve a literature review. Questions on a questionnaire are valid when they measure what they are supposed to.
Another important issue is testing the reliability of a group of questions on a questionnaire to refer to the same thing. This is known as a scale.
I can't help with your second question, sorry.
Yes, a small pilot study would help to establish the validity of the measure you were trying to develop.
For your second question, I think you need to develop a teaching example that you could use to demonstrate various forms of validity. In other words, pick an area where there is a need for a new measurement instrument and then describe how that instrument would be assessed according to face validity etc.
Ashish,
Face validity is when there is a discussion between people who have general idea about the topic of the relevant research and they express their opinions on the first draft of the questionnaire. It is hardly scientific, yet it is just a starting point before you run a pilot study.
Concurrent validity - if your measure e.g. of anxiety is correlated with other well established measures on anxiety... it it is low, say .3 it would mean you are measuring something else, if it is very high say .9 it would mean that the need for your measure if one already exists is under question...
Good luck with your research
Dear Ashish,
1. The validity of a research instrument such as questionnaire is generally determined by conducting a reconnaissance or scouting survey on a small sample with similar baseline characteristics (but not the same study sample). This will provide you the opportunity to make adjustments and modifications to the questionnaire items so that the items will appropriately measure issues they are meant to measure.
2. These list are the various forms of validity ranging from the lowest to the highest level. First understand validity as the extent and or the ability of a scale/measure to measure what it is intended to measure.
Face validity represents the simplest or the least scientific form of validity and it is based on the normative judgement of the researcher to see whether the scale measures what it claims to measure.
Content validity is more scientific because the researcher goes beyond mere value judgements and makes sure all measurement devices provide adequate coverage of the investigative questions.
Criterion validity is concerned with how the measure or the scale agrees or correlates with other standard measures of the same construct. For example how does the teacher's assignment of a student's intelligence agrees with the student's IQ test results?
Concurrent validity is a form of criterion validity which demonstrates when scores obtained from a new measure are directly related to scores from a more established measure of the same variables. See also predictive validity.
Wishing you the very best in your research endeavours.
Dear Ashish,
I have already explained to you that validity is achieved when a particular scale or measure is able to measure accurately what it intends to measure. On this score, validity of a questionnaire is confirmed by a pre-test of the instrument with a smaller sample of common features as the sample/target and or accessible population of your study. Notice that the pretest process encompasses the subsequent analysis of the data collected. Then, compare the results of this scouting survey with your research questions/ objectives. This will give you the clue whether the questionnaire items agree with what they suppose to measure. If they do, we say that the validity of the questionnaire is confirmed.
Regard to first question: YES, pilot survey is already pre-test, this gives a good feedback for your questionnaire if any edit needed such as delet or add some items.
Second one: sorry, i dont have an idea
Please how do l measure construct validity in a pretest intervention study using self directed learning readiness scale
Construct validity determines the extent to which a new measures performs as expected with regard to other variables. One example is criterion validity, as described by Razak M Gyasi above, which looks at the correlation between the new variable and an established measure of the same thing. Other aspects of construct validity include discriminate validity, so that there is no correlation with variables that are supposed to different from the new measures.
The are four authentic test to determine the validity of a questionnaire.
1. Content validity which is determined by content validity index (CVI). Content validation, which plays a primary role in the development of any new instrument, provides evidence about the validity of an instrument by assessing the degree to which the instrument measures the targeted construct .
2. Construct validity determined by factorial analysis.Construct validity is used to determine how well a test measures what it is supposed to measure. In other words, is the test constructed in a way that it successfully tests what it claims to test? Construct validity is usually verified by comparing the test to other tests that measure similar qualities to see how highly correlated the two measures are.
3. Face validilty: Does the content of the test appear to be suitable to its aims? In other words, a test can be said to have face validity if it "looks like" it is going to measure what it is supposed to measure.
4. Criterion validity: Do the results correspond to a different test of the same thing?
Yes small pilot study can be used for validity. it would be better to review the survey from a group of researchers and then send it to a small number of respondents.
Can I know how to test the construct validity when there are no other similar tools?
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Applied Statistics
- Survey Design
- Questionnaire