Unbalanced mixed Anova in R

General
,
1

Hello!
I have an unbalanced data, that made participants to complete the same task two different times.

The independent variables are the levels of stress measured and the task order (one and two). The stress level is between-subjects and the task is within-subjects. The dependent variable is their reaction time in that task. I tried to run an Anova using the ezAnova function but I keep getting this error message.

this was the code that I used to run the Anova,

m <- ezANOVA(data = data, dv = RT, wid = ID, within = task_order,
between = level, observed = NULL,
diff = NULL, reverse_diff = FALSE, type = 2,
white.adjust = FALSE, detailed = TRUE,
return_aov = FALSE)
summary(m)

and this is the warning and error message I got each time.
"Error in ezANOVA_main(data = data, dv = dv, wid = wid, within = within, : One or more cells is missing data. Try using ezDesign() to check your data."

Does anyone know how to fix this error? Please help.

Thank you!

2

I would start by considering this possibility, that One or more cells is missing data; Is that something that you've explored in any way ?
and I might look online for examples of how ezDesign() might be used; is that something you've searched for perhaps ?

3

I have checked and none of my data is missing and also explored how ezDesign works (I will attach a copy of the output).
The output of ezDesign

Although participants did the same task, it was labelled differently to allow me to understand the data and compare between them, and I think the ezAnova function does not understand that.

4

I'm not authorised to view your link.

This seems like the critical insight. How about relabelling so that the common tasks have names in common, and then trying ezANOVA again ?

5

I considered trying that might make it harder but it seems it is better to just do that.

I have tried re-labelling them and it worked.

Thank you!

1 Like
6

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.