I would look into using the GENLIN command to estimate a logistic regression model to address the comparison of different conditions. You'd have to use generalized estimating equations (GEE) to account for the repeated measures structure of the data. One option that might be useful is the {events-var} of {n} form of GENLIN. See the help file for more info.

• https://www.ibm.com/support/knowledgecenter/en/SSLVMB_25.0.0/statistics_reference_project_ddita/spss/advanced/syn_genlin.html

HTH.

PS- I don't have time to work up a carefully tested example, so please take the following as a very rough and ready guide to get you started!

* Generate some data to illustrate.

NEW FILE.

DATASET CLOSE ALL.

DATA LIST LIST / id cond Y (3F1).

BEGIN DATA

1 1 0

1 1 0

1 1 1

1 2 1

1 2 0

1 2 1

1 3 0

1 3 0

1 3 1

2 1 0

2 1 1

2 1 1

2 2 1

2 2 1

2 2 1

2 3 1

2 3 1

2 3 0

3 1 1

3 1 1

3 1 1

3 2 1

3 2 1

3 2 0

3 3 1

3 3 1

3 3 1

4 1 0

4 1 0

4 1 0

4 2 0

4 2 0

4 2 0

4 3 1

4 3 0

4 3 0

5 1 1

5 1 0

5 1 0

5 2 1

5 2 0

5 2 0

5 3 0

5 3 1

5 3 1

END DATA.

* Reduce data to one row for each ID x Cond combination.

* Let Correct = the # of 1s.

AGGREGATE

/OUTFILE=* MODE=REPLACE

/BREAK=id cond

/Correct=SUM(Y)

/Trials=N.

* GENLIN with Generalized Estimating Equations.

GENLIN Correct of Trials BY cond

/MODEL cond INTERCEPT=YES

DISTRIBUTION=BINOMIAL LINK=LOGIT

/CRITERIA METHOD=FISHER(1) SCALE=1 MAXITERATIONS=100 MAXSTEPHALVING=5 PCONVERGE=1E-006(ABSOLUTE)

SINGULAR=1E-012 ANALYSISTYPE=3(WALD) CILEVEL=95 LIKELIHOOD=FULL

/EMMEANS TABLES=cond SCALE=ORIGINAL COMPARE=cond CONTRAST=PAIRWISE PADJUST=LSD

/REPEATED SUBJECT=id WITHINSUBJECT=cond SORT=YES CORRTYPE=EXCHANGEABLE ADJUSTCORR=YES COVB=ROBUST

MAXITERATIONS=100 PCONVERGE=1e-006(ABSOLUTE) UPDATECORR=1

/MISSING CLASSMISSING=EXCLUDE

/PRINT CPS DESCRIPTIVES MODELINFO FIT SUMMARY SOLUTION (EXPONENTIATED).

hi,

you arrange all the correct data on one side and all the incorrect data on the other hand, run one way anova by vassarstats with three variables and see the statistical significance between them. now you can see the level of significance between the 3 parameters tested. this may help you

Please check this:

https://libguides.library.kent.edu/SPSS/OneSampletTest

Noha A. Mostafa Avinash Vs

My concerns with both ANOVA and T-tests are that percentage values obtained through a dichotomous tasks are not truly ratio scale variables.

Ratio scale dependent variables are not required for ANOVA and t-tests--they work just fine with interval scale DVs. The more important problem with percentages is that they are bounded at 0% and 100%. If you use methods for unbounded variables (like t-tests or ANOVA), it is possible to obtain fitted values that fall outside that range. The method I suggested above (GENLIN with binomial error distribution & logit link function) will produce fitted values within the possible range. HTH.