Variations of Box Plots

By R. McGill, J. Tukey, W. A. Larsen. 1978

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

Using geometric and non-geometric internal evaluators to compare eight vegetation classification methods (2008, methodology): “Ninety-five percent confidence intervals for medians were calculated from the interquartile range, and are based on the asymptotic normality of the median, and roughly equal sample sizes for the medians being compared (McGill et al. 1978, p. 16).”
Discriminating between the end products of the earlier Middle Stone Age sub-stages at Klasies River using biplot methodology (2003, background): “If notches do not overlap then a hypothesis of no difference between population medians can be rejected at an approximate 5% level of significance [33].”
Scientiﬁc Benchmarking of Parallel Computing Systems Twelve ways to tell the masses when reporting performance results (2017, background): “Box plots [40] o ﬀ er a rich set statistical information for arbitrary distributions: the box indicates the 25% (lower border) and the 75% (upper border) percentile.”
Ranges of human mobility in Los Angeles and New York (2011, methodology): “We could have shown the variability in our data using “notched box plots” [6], where the size of a notch around the median represents the variation of the median.”
Generalized Network Psychometrics: Combining Network and Latent Variable Models (2016, unknown): “Data is represented in standard boxplots (McGill et al., 1978): the box shows the 25th, 50th (median) 75th quantiles, the whiskers range from the largest values in 1.5 times the inter-quantile range (75th - 25th quantile) and points indicate outliers outside that range.”
Assessing the Type Annotation Burden (2018, methodology): “Tukey’s method identifies outliers using a scaling factor k times the interquartile range plus the third quartile, and suggests k = 3 [28].”
Conditioned Choropleth Maps and Hypothesis Generation (2005, methodology): “Our approach follows the notion of adjacent values used in Tukey’s box plots (see McGill, Tukey, and Larsen 1978).”
Evaluating calibration methods for predicting soil available nutrients using hyperspectral VNIR data (2018, background): “The outliers were determined by boxplot (McGill et al., 1978), and eight samples with extremely large N concentrations beyond the upper whisker were removed.”
Visualization and Visual Analysis of Multifaceted Scientific Data: A Survey (2013, unknown): “Box plots [162] encode important characteristics of data distributions such as minimum and maximum values, mean, median, and other quartile information.”