I am currently doing an investigation using a standardized tool, however, I am confused as to whether I need to have a reliability test first or have an actual field survey without having a reliability test?
Reliability is fundamentally the consistency between a series of measurement. It is idealistic to observe no measurement error between series of measurement and therefore reliability is measured as the amount of error that can be acceptable for a measurement/instrument/tool.
In other words, if you are using a particular tool to measure the outcome of an intervention, you are accounting the random measurement error (variability in the measure due to number of factors) before taking any difference in scores as the effect of the intervention.
In your case, the need for you to do or not do a reliability for a measure actually depends on what you mean as "standardised tool". It might be oversimplification of the concept of reliability to say 'yes' or 'no' to your question without knowing the actual tool, design etc., of your research. But by rule of thumb, if the tool that you are going to use has been standardised to be used in general population and you would want to use it in some special population then you would need to look at the reliability of the tool in your population of interest; provided if you think the random errors of your population of interest would be different from the general population. If your population of interest is same as the population on which the instrument/tool has been "standardised", you would be better off to go ahead with the previously published error scores, and again only if you follow the measurement procedure/protocol as suggested by the reference standard.
However, this is my understanding of reliability of measurements.
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Probability
- Probability Theory
- Reliability