Testing Statistical Hypotheses

By E. L. Lehmann. 1959

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Revisiting Classifier Two-Sample Tests (2016, background): “One of the most fundamental problems in statistics is to assess whether two samples, S P ∼ P n and S Q ∼ Q m , are drawn from the same probability distribution. tests To this end, two-sample ( ?”
Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo (2015, background): “In addition, the trade-oﬀ with (cid:15) and the test power is also explicitly described, so in cases where the power of the tests are well-studied (Lehmann & Romano, 2006), the same handle can be used to analyze the most-powerful-test under privacy constraints.”
Causal Inference on Discrete Data Using Additive Noise Models (2009, methodology): “Lehmann (2005)), which is most commonly used. It computes the difference between observed frequencies and expected frequencies in the contingency table. The test statistic is known to converge towards a χ2 distribution, which is taken as an approximation even in the finite sample case. For very few ”
Pros and Cons of GAN Evaluation Measures (2018, neutral): “The goal of two-sample tests is to assess whether two samples are drawn from the same distribution [47].”
The Right Complexity Measure in Locally Private Estimation: It is not the Fisher Information (2018, neutral): “[40, 52]).”
Does Management Matter? Evidence from India (2011, unknown): “20 See Lehmann and Romano (2005) for a textbook exposition of permutation tests.”
Maximum Likelihood Theory for Incomplete Data from an Exponential Family (2016, background): “Most of the material can also be found in Lehmann (1959). p(x; a) as introduced in (1.”
Should we go one step further? An accurate comparison of one-step and two-step procedures in a generalized method of moments framework (2018, unknown): “V̂1T = h G1T 1 est(̂1T ) G1T i 1 h G1T 1 est(̂1T ) est(̂1T ) 1 est(̂1T ) G1T i h G1T 1 est(̂1T ) G1T i 1 (16) V̂2T = h G2T 1 est(̂2T ) G2T i 1”
Confidence Sets for the Date of a Single Break in Linear Time Series Regressions (2004, background): “A level C confidence set can be thought of as a collection of parameter values that cannot be rejected with a level 1− C hypothesis test; see, for instance, Lehmann (1986), p. 90. In standard set-ups, estimators are asymptotically unbiased and Gaussian with a variance that, at least locally, does no”