Chernoff: exponential tail rates and asymptotic test efficiency

What changed

Chernoff used the optimized exponential moment of a real random variable to bound tails of sums of independent identically distributed observations and identify their exponential decay rate. He then defined an asymptotic efficiency index for threshold tests between two simple hypotheses: the smallest fixed-positive-weight sum of the two error probabilities has a rate independent of that weight. Ratios of the logarithms of these indices compare asymptotic sample requirements.

Scientific scope

Chernoff used the optimized exponential moment of a real random variable to bound tails of sums of independent identically distributed observations and identify their exponential decay rate. He then defined an asymptotic efficiency index for threshold tests between two simple hypotheses: the smallest fixed-positive-weight sum of the two error probabilities has a rate independent of that weight. Ratios of the logarithms of these indices compare asymptotic sample requirements. This record refers to Stanford Technical Report 6, dated 9 November 1951; the 1952 Annals article is a separate publication version. The sum observations are independent copies; finite-tail inequalities require the appropriate side of the mean, and an optimized moment value 1 can give no useful exponential decay. Exponential-rate equivalence does not give exact finite-sample probabilities or Gaussian far-tail accuracy. The testing theorem concerns two simple hypotheses and threshold tests with fixed finite positive error weight, not arbitrary composite/adaptive/dependent testing. No claim of inventing the exponential Markov method or all modern concentration inequalities.

Evidence

The linked original works support the scoped statement and contribution attribution. WRS has not independently replayed experiments or reconstructed a full mathematical proof. This record refers to Stanford Technical Report 6, dated 9 November 1951; the 1952 Annals article is a separate publication version. The sum observations are independent copies; finite-tail inequalities require the appropriate side of the mean, and an optimized moment value 1 can give no useful exponential decay. Exponential-rate equivalence does not give exact finite-sample probabilities or Gaussian far-tail accuracy. The testing theorem concerns two simple hypotheses and threshold tests with fixed finite positive error weight, not arbitrary composite/adaptive/dependent testing. No claim of inventing the exponential Markov method or all modern concentration inequalities.

Contributors

• The named authors in the research record · SCIENCE: Source-listed authors for the exact contribution; experimental subjects are not autonomous scientific authors. Source support and predecessor work retain separate roles. Individual effort shares and unresolved identities are not inferred.

• A measure of asymptotic efficiency for tests of an hypothesis based on the sum of observations (Stanford Technical Report6)

Provisional WRS assessment, edition 2026-10-23.3. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction