Part of the Maths & Statistics suite · 235 calculators

Exponential Regression Calculator

Fit y = ae^(bx) to data that grows or decays by a constant percentage — populations, compound growth, radioactive decay, cooling.

Take logarithms of y and the model becomes linear: ln y = ln a + bx.

All must be above zero
Results update as you type
Results
Growth rate b
0.403453
Initial value a
Equation
Growth per unit of x
Doubling (or halving) time
R² in log space
R² against the original data
Prediction
Reviewed September 2026. Pure mathematics: the result does not depend on where you are. Terminology follows the national curriculum (maths, brackets, decimal point).
No account required · Google Analytics off unless allowedCalculator arithmetic runs in your browserResults update as you type
All calculations run 100% in your browser. The calculator code does not submit your figures to GlobalCalc to obtain a result.
About exponential regression

How the exponential regression calculator works

Take logarithms of y and the model becomes linear: ln y = ln a + bx. Fit a straight line to (x, ln y), then exponentiate the intercept to recover a.

That linearisation is what makes it easy, and it also changes what is being minimised — squared error in log space, which weights small values more heavily than a direct nonlinear fit would. For most purposes it is what you want; the calculator reports R² in both spaces so you can see the difference.

Formula: y = a e^(bx); ln y = ln a + bx

Worked examples

InputsGrowth rate bNote
50% growth per step0.403453b ≈ 0.405, doubling every 1.71 steps
Exact doubling0.693147b = ln 2, doubling time exactly 1
Decay-0.693147b negative, half-life 1

Frequently asked questions

When is exponential the right model?

When the *rate of change* is proportional to the current value — populations, compound interest, radioactive decay, epidemics in their early phase.

Why must Y be positive?

Because the fit works on logarithms, and the logarithm of zero or a negative number is undefined.

What is the doubling time?

ln 2 ÷ b. For decay the same formula gives the half-life.

Why are there two R² figures?

Because linearising fits in log space. The log R² is what was minimised; the ordinary R² is how well the curve fits the actual data. They can differ noticeably.

Is exponential growth really unlimited?

Never, in reality. Every real exponential turns over — the logistic curve is usually the honest model once the resource runs short.

Where these figures come from

Last checked: September 2026. Formulas are fixed by mathematics and do not change with tax years or regulations.