Data Science: Standard Deviation (Definitions)

"A commonly used measure that defines the variation in a data set." (Glenn J Myatt, "Making Sense of Data: A Practical Guide to Exploratory Data Analysis and Data Mining", 2006)

"A measure of the variability in a set of data. It is calculated by taking the square root of the variance. Standard deviations are not additive; the variances are." (Clyde M Creveling, "Six Sigma for Technical Processes", 2006)

"The degree of dispersion of a group of scores around the average. If most scores are close to the average, the standard deviation is low. Conversely, if the scores are widely dispersed, the standard deviation is large." (Ruth C Clark, "Building Expertise: Cognitive Methods for Training and Performance Improvement", 2008)

"The measured range of economic volatility that can occur during the course of doing business." (Annetta Cortez & Bob Yehling, "The Complete Idiot's Guide® To Risk Management", 2010)

"A measure of how distributed the values of a probability curve are, relative to the average." (Jon Radoff, "Game On: Energize Your Business with Social Media Games", 2011)

"The amount of dispersal among test scores or other outcome results. A larger standard deviation indicates greater spread among test scores, while a smaller standard deviation indicates greater consistency among scores." (Ruth C Clark & Richard E Mayer, "e-Learning and the Science of Instruction", 2011)

"Describes dispersion about the data set’s mean. You can think of a standard deviation as an average deviation from the mean. See also average; variance." (E C Nelson & Stephen L Nelson, "Excel Data Analysis For Dummies ", 2015)

"Square root of variance. The standard deviation is an index of variability in the distribution of scores." (K  N Krishnaswamy et al, "Management Research Methodology: Integration of Principles, Methods and Techniques", 2016)

"the square root of the variance of a sample or distribution. For well-behaved, reasonably symmetric data distributions without long tails, we would expect most of the observations to lie within two sample standard deviations from the sample mean." (David Spiegelhalter, "The Art of Statistics: Learning from Data", 2019)