Measure autocorrelation at a given lag and test for serial dependence.
Autocorrelation measures whether a series is correlated with its own past. Positive serial correlation violates the independence assumption of ordinary regression and understates standard errors. Ignoring autocorrelation in time-series regression produces standard errors that are far too small, making spurious relationships look significant.
Autocorrelation
r_k = covariance at lag k ÷ variance; significance bound ≈ 1.96 ÷ √n
r_k = covariance at lag k ÷ variance; significance bound ≈ 1.96 ÷ √n Autocorrelation measures whether a series is correlated with its own past. Positive serial correlation violates the independence assumption of ordinary regression and understates standard errors.
Ignoring autocorrelation in time-series regression produces standard errors that are far too small, making spurious relationships look significant.
This calculator takes 4 inputs: Covariance at the chosen lag, Variance of the series, Number of observations, Lag. The pre-filled defaults are a realistic starting point — replace them with figures from your own environment for a result you can act on.