When people give me access to lovely nationally representative data sets, I am a happy man.

I got my hands on the data set from the most recent Omnibus Survey run by the Kiev International Institute of Sociology. Every three months KIIS surveys 2,000 Ukrainians about everything from who they’d vote for to what kind of presents they’d like to get for New Year’s. The most recent data is from February 5-16, and fieldwork for the next round is beginning in just a few days.

One of the first questions they asked was about attitudes towards the EU (KIIS’s translation from the Ukrainian and Russian versions of the questionnaire):

Please, imagine, that now is a referendum on whether Ukraine should join the European Union. You can vote for, against or abstain from voting. What would you choose?”

Just under half (49%) of Ukrainians said they’d vote in favour of EU accession, and 28% would vote no. A few (9%) said they’d abstain, but about one in seven (14%) said they didn’t know how they’d vote – a figure I’ll talk more about below.

UA and EU accession

Not surprisingly, there are some pretty stark regional differences, with more western Ukrainians (77%) inclined to support EU accession than anyone else, particularly eastern Ukrainians (25%).

EU UA region

I’ve tried to unpack those figures from southern and eastern Ukraine, to the extent that the sample size allows me to make confident comparisons – and for some of the larger oblasts, it does:

  • Donetsk oblast (including DNR): 57% of those surveyed said there weren’t in favour of EU accession; only 19% said yes
    • Just in the DNR, 74% said no, and only 6% said yes
  • Luhansk oblast (not including LNR): 56% said no; only 23% said yes
  • Odessa oblast: 38% said no; only 26% said yes and, interestingly, 21% said they didn’t know how they’d vote
  • Kharkiv oblast: 28% said no; 37% said yes

A few other differences of note:

  • Women were more likely than men to say they didn’t know how they’d vote (17% of women compared to 11% of men)
  • Younger people (between the ages of 18-29 and 30-39) were more likely to say they’d vote yes (57% and 58%, respectively) than those aged 60-69 (39%)
  • People with the lowest levels of education (less than ten years of education) were least likely to vote yes (23%), but at the same time most likely to say they didn’t know how they’d vote (31%)

Do these differences matter?

Well, some matter more than others.

I ran a few logistic regression analyses, because a) this is something I know how to do despite never really ever wanting to, and b) it’s a good way to parse out what matters most in yes/no survey questions.

What did I find?

Yes: Living in western Ukraine was by far the strongest predictor of voting Yes. This is probably the least surprising finding I’ve ever found running one of these things and I assume no one even remotely connected to the Ukraine-watching universe is shocked by this. The other differences I mentioned above (age, etc.) come up insignificant in the regression analysis.

No: Living in southern and eastern Ukraine were strong predictors of voting No. Interestingly, living in southern Ukraine was a stronger predictor than living in eastern Ukraine – I’m curious to see whether this holds in up in future surveys. Also, self-identification as Russian or ‘mostly Russian’, as well as being a member of the Moscow Patriarchate, predicted voting No. Not particularly shocking.

Don’t know: The only predictor of saying Don’t Know was being a woman.

What does this all mean?

Most of this is obvious and confirms what we all already know, but what I’m intrigued by are the relatively high numbers of Don’t Knows in the overall figures (14%).

I’m curious about the high Don’t Knows in Odessa oblast (21%), and whether this speaks to something below the surface there or whether it’s just something that’ll fall out in the wash in future surveys.

What I’m most curious about though is so many of the Don’t Knows being women – almost one in six women don’t know how they’d vote, compared to just over one in ten men.

Are they less willing to give a yes/no answer, (i.e., is there some sort of gender-related social desirability bias here?) or do they genuinely not know how they’d vote? If so, why?

And, most importantly, what would convince them to say Yes or No?