|Image credit: http://www.restore.ac.uk/srme/www/fac/soc/wie/research-new/srme/modules/mod1/1/|
What is a good psychometric test? What conditions are required for a test to be considered "good"?I asked myself the above questions when I was doing my Honours dissertation. We have learnt in our research methods classes that a good psychometric test has validity and reliability. This is very important as your data collection methods will affect your results collected. and within your data collection methods, the psychological test used is one of the important components to be considered.
So I went to read up on validity and reliability, and stumbled upon this website: Social Research Methods Knowledge Base. After extensive reading and researching on this website and others, I concluded that as a student, it is very important to know the different types of validity and reliability:
Types of validity (from Social Research Methods Knowledge Base Measurement Validity Types)
- Face validity
- Content validity
- Predictive validity
- Concurrent validity
- Convergent validity
- Discriminant validity
- Inter-rater reliability
- Test-retest reliability
- Parallel-forms reliability
- Internal consistency reliability
Why do we need to know the psychometric properties of the tests that we are performing with our participants or doing to find out our own personal traits?Remember Issues with Horoscopes and Some Personality tests?? As psychological researchers, we have to make that the tests used are measuring what they are supposed to measure and also producing consistent results over time, even before we use them. This is to ensure that we are able to "trust" the test.
So how do we make sure that the tests used have been validated for their psychometric properties?This can be easily done by researching on the test regarding their validity and reliability properties. One good example is the Depression Anxiety Stress Scale (DASS), where different research have been done and published to demonstrate its psychometric strengths.
This way we know that we can "trust" the test, use it with confidence, and be convinced with the results produced, as we know that the test used is valid and reliable.