Validity analysis

[rockyallen7771]

Hi

What is the proper way of carrying out the following validity analysis,

1. Construct validity
2. Concurrent validity

[Outlier]

What is the proper way of carrying out the following validity analysis,

By now I know the starting point for everyone who asks this type of question is to
Google each phrase with the suffix Wiki,
then without the suffix Wiki.

But, thank you for giving me two more key phrases to study up on.

[rockyallen7771]

I googled with Wiki and without Wiki. Nit not much satisfactory answer.

But I think some body here in the forum can help me.

If any body has done that pls explain the steps to conduct the analysis.

[CowboyBear]

I don't think there's a quick and easy answer to this question; you're basically asking "how do I establish validity of measures?", which is essentially an entire sub-field of psychometrics. Construct validity is arguably an overarching term for all types of validity, for example. Concurrent validity is a more specific concept; Wikipedia defines it like this: "Concurrent validity is demonstrated where a test correlates well with a measure that has previously been validated."

The way you carry concurrent validity analysis out is then reasonably clear: you administer the measure you're validating to some sample along with a previously "validated" measure of the same construct. You then calculate the correlation between the two: the bigger the better (although there's no firm standard for how large a concurrent validity correlation needs to be to indicate "good enough" validity).

You might need to look at a behavioural science/statistics textbook to give you a bit more of a well-rounded understanding of validity concepts. What sources have you looked at so far?