blue_ocean

Validity

11 posts in this topic

You develop a blood test for a disease and find that patients with that disease mostly test positive on it whereas patients with another (albeit similar) disease mostly test negative on it. What does this establish about your test?

 

A.    Case Validity

B.     Concurrent Validity

C.     Content Validity

D.    Construct Validity

E.     Convergent Validity

F.      Criterion Validity

G.    Divergent Validity

H.    External Validity

I.       Face Validity

J.       Predictive Validity

Share this post


Link to post
Share on other sites

divergent validity.

Please correct me if I am wrong. You need Convergent validity and divergent validity to get construct validity. 

Convergent validity; tests that constructs that are related are actually related

Divergent Validity; tests that constructs that appear to be related are not actually related. 

 

Share this post


Link to post
Share on other sites

Can you please explain this Carole

 

Share this post


Link to post
Share on other sites

Construct Validity.

 

Construct Validity: The extent to which the test measures a theoretical construct by a specific measuring device or procedure*.  But, not completly sure.

*The Doctor's guide to critical appraisal. Gosall N, Gosall Gurpal. 2012

However, I think that example could also be related to predictive validity. I hope blue-ocean can give us the answer :)  

Share this post


Link to post
Share on other sites

I found this question on a stat course I went to. The answer is given: Divergent Validity. 

Share this post


Link to post
Share on other sites

when i read the question my straight answer was divergent validity after I read the answer of most members were divergent validity.

Share this post


Link to post
Share on other sites

I think its divergent validity

Share this post


Link to post
Share on other sites
On September 15, 2015 at 03:10, Yousuf said:

divergent validity.

Please correct me if I am wrong. You need Convergent validity and divergent validity to get construct validity. 

Convergent validity; tests that constructs that are related are actually related

Divergent Validity; tests that constructs that appear to be related are not actually related. 

 

Thank you Yousuf it clear

Share this post


Link to post
Share on other sites

I will agree with Carole:

Question says.......  You develop a blood test for a disease and find  that patients with that disease mostly test positive on it whereas patients with another (albeit similar) disease mostly test negative on it. What does this establish about your test?

My thoughts are:

What they are describing here is that this test have a good convergence and divergence.  In other words we can say that this test has a good construct validity 

So I will go for the answer Construct Validity

But I am not sure if this is the correct answer

1 person likes this

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!


Register a new account

Sign in

Already have an account? Sign in here.


Sign In Now