Millisecond Forums

Thank you very much for responding so quickly Dave. This is very helpful.

To add yet another way of looking at this, as noted at https://millisecond.com/forums/Topic3444.aspx

"D scores can be positive or negative. A positive score indicates an
association of targetA with attributeA  and targetB with attributeB.  A
negative score indicates an association of targetA with attributeB and
targetB with attributeA. Translating the score into a preference or
attitude thus depends on how you have assigned your real world
categories to these 4 groups. You can determine the mappings by looking
at the topmost section of your IAT script, where you'll see the
<item> definitions for each category."

Thus, if you do not want to reverse D's sign to bring it in line with the stereotypical compatible / incompatible mapping (as suggested in my previous reply), you can leave everything as is as long as you take the above into account when interpreting your data.

Regards,

~Dave

It should be obvious that this is simple matter of reversing D's sign. In greatly simplified terms, D is traditionally defined as

incompatible - compatible

which corresponds to

b - a

in the available scripts.

As RTs to incompatible combinations will usually be larger than RTs to compatible combinations, a positive D score indicates an effect in the expected "stereotypical" direction.

Due to your mistake you have effectively computed

compatible - incompatible

This changes nothing whatsoever re. the resulting D's *absolute* numerical value. It only affects its sign. I.e., now a *negative* D score indicates an effect in the expected "stereotypical" direction.