Turnout-Adjusted Poll Calculator
Adjust a candidate's raw support for differing turnout between two voter groups to estimate the likely-voter result.
How it works
adjusted = (w₁·s₁ + w₂·s₂) ÷ (w₁ + w₂), where wᵢ = groupᵢ share × turnoutᵢ
Support among all registered voters can differ sharply from support among those who actually vote, because turnout is uneven across groups. This calculator reweights each group by its likely turnout: the group that votes more heavily gets a larger say in the final number. When your candidate's strong group turns out at a higher rate, the adjusted figure rises above the raw one; when their base is low-turnout, it falls.
Worked example
Group 1 is 50% of the electorate, turns out 70% and backs the candidate 55%; group 2 turns out 50% and backs them 40%. Likely-voter weights: 0.35 and 0.25. Adjusted = (0.35·0.55 + 0.25·0.40) ÷ 0.60 = 0.2925 ÷ 0.60 = 48.75%, versus 47.5% raw.
Frequently asked questions
What is a likely-voter model?
It is any method pollsters use to weight or screen respondents by their probability of voting. This calculator shows the simplest version — two groups with different turnout rates — but real models use many demographic and behavioural signals.
Why can turnout swing the result so much?
Because a group that both leans strongly one way and votes at a high rate is over-represented among actual ballots. Small turnout gaps between opposing groups can shift the headline number by several points.
Can I use more than two groups?
The same weighted-average logic extends to any number of groups: multiply each group's share by its turnout to get its weight, then average the support figures using those weights. This tool covers the common two-group case.
Related calculators
This calculator is for educational purposes. Double-check important results before acting on them.