Simple and Effective Confidence Intervals for Proportions and Differences of Proportions Result from Adding Two Successes and Two Failures

By Alan Agresti, Brian C. Caffo. 2000

552 citations recorded by the source corpus.

Subfields: Soil Science, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/ed5808ff30a00b33b06bfb823359e5ea17d40c47

How researchers see this paper

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

In Soil Science

In Statistics and Probability

Citations in the corpus

Measuring Discrimination in Socially-Sensitive Decision Records (2009, methodology): “Later on, we will consider the simple but effective plus-4 method [3], consisting of adding Z(2) α/4 cases to each cell in the contingency table.”
Better than random? A closer look on BCI results (2008, unknown): “Thus, a confidence interval around the expected value of can be calculated as follows [Agresti & Caffo, 2000]: This unbiased estimator is replaced by and the confidence intervals are then given by In the equation above, is the quantile of the standard normal distribution and is the significance…”
Interval Estimation for a Binomial Proportion (2001, background): “Agresti and Caffo (2000) discussed this and showed that adding four pseudo observations also dramatically improves the Wald two-sample interval for comparing proportions, although again at the cost of rather severe conservativeness when both parameters are near 0 or near 1.”
An Introduction to Categorical Data Analysis (2008, methodology): “These updates include the Agresti and Coull (1998) confidence interval for a single proportion and mid-p methods as alternatives to exact inference.”
Measures of Location for Confidence Intervals for Proportions (2011, background): “Furthermore, in view of the favorable performance of Bayesian intervals with uninformative conjugate priors in a frequentist sense (Carlin and Louis, 1996 , cited by Agresti and Caffo, 2000 ; and Agresti and Min, 2005 ), it is now appropriate to regard them as confidence interval methods in their”
A multidisciplinary survey on discrimination analysis (2013, methodology): “…normal or log-normal distribution, several ‘corrections for continuity’ have been proposed, such as Yates’s correction and the Mid-p method (Agresti, 2002), or the simple but effective plus-4 method (Agresti & Brian, 2000), which consists of adding Z2a=4 cases to each cell in the contingency table.”