I've used one of your IAT scripts as my implicit attitudes' instrument, and then, to analyse my data, I also used the SPSS syntax that you also provide in your website. However, I've been struggling with it, since I am not an experienced user, and would like to clear some questions.
Before importing my .dat file to SPSS, I introduced some alterations to it because:
1) I had to discard two participants for not meeting my eligibility criteria (to avoid descriptive statistics based in an erroneous N). and,
2) I made a mistake when introducing one participant's ID before running Inquisit... leaving me with two participants with the ner. 48 ... So I recoded this participant to the next available even slot (n.er 52 - it's a small sample), since IAT counterbalanced participants according to that property (odd or even ID number).
After this I tried to import my data to SPSS and, in the last step from the importing procedure, I've chosen to paste the syntax (and I've indicated the respective file path in it too). I got one Output window, a .sav data file based on my IAT's raw data, and an aggregated file, with all the relevant data necessary to calculate D index (and the actual index)/ per participant.
My results only revealed negative D_biep values. And now... my doubts and the problems found...
1 - The doubt.
- to verify the correctness of the data obtained, I calculated the D_Biep index of some of the participants by hand. I noticed that for participants with an even number ID, the values obtained - although the same in module to the ones indicated in SPSS - were positive instead of negative; and that didn't make sense given that the mean latencies and respective differences indicated negative implicit attitudes toward my main target of interest... I then remembered that maybe there's some "built-in recoding" in IAT's syntax (but I couldn't really find it there - I'm a rookie in this so...). I just need you to confirm (or not) this idea:
In what concerns even numbered ID's (order 2), the block order is "incompatible first", instead of "compatible first" so, in order the data to make sense, the syntax recodes the blocks' order, as if they had been ran in order 1.
According to the algorithm used:
Mean latency Incompatibletest 1 (Block 5 when "compatible first") - Mean latency Compatible test 1 (Block 3 when "compatible first");
So, when in order 2,
Mean latency Incompatibletest 1 (Block 3 when "incompatible first") - Mean latency Compatible test 1 (Block 5 when "incompatible first").
And this is how we get a negative value for this operation…
Is this right? If so, what are the following code lines for:
2 - And now, the problems (mixed up with some other doubts)…
As already stated above, after I ran the SPSS syntax I obtained one Output window, a data file based on my IAT's raw data, and an aggregated file, with all the relevant data necessary to calculate D index (and the actual index)/ per participant.
I haven’t altered anything in SPSS syntax besides my file name, and haven´t altered anything in IAT script besides deleting the summary block from the script's <expt> elements' /blocks attributes (with your help), so that the participants didn’t receive feedback about their performance.
After analysing the output file, it revealed several errors… One of which prevented the respective variables flagging the <300ms, <400ms and >10 000ms trials from appearing in the respective .sav file(for every trial), although their descriptive statistics appear in the mentioned output file (I attached a file with it, in order to make myself clearer (the errors are highlighted in yellow).
What has happened? Why are these errors occurring? I’ve tried to overcome this “N times” :p and haven’t reached any conclusion… Is it due to the “holes” in my sample (there aren’t participants ner 32 and 46, for they didn’t meet my eligibility criteria and I deleted them before running the script), the "recoding" of the doubled 48 participant, or any other alteration that I have made in my raw data file?
Please help… I don’t know what else to do!