3dLME 3 factor design and missing data

AFNI Message Board
1

Hello,

We have a dataset with 3 factors: 2 within subject factors (Pain, Faces), 1 between subjects factor (Group),

A 2 x 3 x 2 design.

Factors: Pain (Levels: pain, nopain)
Faces (Levels: neutral, positive, negative)
Group (Levels: patients, controls)

Here is our setup

3dLME -prefix result-lme_group -jobs 10
-mask myMask+tlrc
-model "painfaces + group"
-ranEff ‘~1’
-SS_type 3
-num_glt 6
-gltLabel 1 ‘pos-neu’ -gltCode 1 'faces : 1pos -1neu’
-gltLabel 2 ‘neg’ -gltCode 2 'faces : 1neg ’
-gltLabel 3 ‘pos+nue-neg’ -gltCode 3 ‘faces : 1pos +1neu -1neg’
-gltLabel 4 ‘pat_pos-neu’ -gltCode 4 'faces : 1pos -1neu group : 1pat’
-gltLabel 5 ‘pat_neg-neu’ -gltCode 5 ‘faces : 1neg -1neu group : 1pat’
-gltLabel 6 ‘pat_pos-neg’ -gltCode 6 'faces : 1pos -1neg group : 1pat’
-dataTable
Subj pain faces group InputFile
s1 pain pos ctr s1+tlrc’[pain-pos#0_Coef]’
s1 nopain neg ctr s1+tlrc’[nopain-neg#0_Coef]’
s1 pain neu ctr s1+tlrc’[pain-neu#0_Coef]’
…
s21 pain pos pat s21+tlrc’[pain-pos#0_Coef]’
s21 nopain neg pat s21+tlrc’[pain-neg#0_Coef]’ \

  1. Does our setup look correct for a 3way design, 2 within and 1 between subjects factor?

  2. Using 3dLME, does one just enter the available datasets and 3dLME recognizes what data points are missing? Or do you we have to code it a certain way (adding NA or “.”)

Thanks.

Michael

2

Does our setup look correct for a 3way design, 2 within and 1 between subjects factor?

It looks fine. You could set a finer model

-model “painfacesgroup” \

Using 3dLME, does one just enter the available datasets and 3dLME recognizes what data points are missing? Or do you we have to code it a certain way (adding NA or “.”)

Just provide the complete cases (available datasets). You should not fill in the rows for those missing cases.

3

Thanks, Gang.