Statistics

Autocorrelation

Also known as: Serial Correlation

Correlation of a series with its own lagged values.

Effects on inference: positive autocorrelation makes observations less informative than they appear, so effective sample size is smaller than n and standard errors computed naively are far too small.

In returns: typically very weak at short horizons - which is roughly what market efficiency predicts. But squared or absolute returns are strongly autocorrelated, which is volatility clustering.

The Sharpe warning. Positive autocorrelation inflates a naively annualised Sharpe ratio, which is one route by which reported figures overstate performance, especially for illiquid strategies with smoothed marks.

Related terms

Practise this

Put it into practice

Knowing the definition is not the same as spotting where it applies under time pressure. Work the question bank free.

Start practising free

Browse the full quant interview glossary