This page gathers the 397 dictionary entries belonging to the domain “Statistics”, as labelled by Wiktionary. Each word leads to its full entry: definitions, etymology, pronunciation, examples. Page 4 of 4: from “regulize” to “ziggurat algorithm”.
- regulize verb To manipulate data so that it is on a comparable scale; normalize.
- rejection sampling noun A technique used to generate observations from a distribution by repeatedly sampling an approximation function that bounds the distribution…
- residual noun The difference between the observed value and the estimated value of the quantity of interest.
- residual sum of squares noun The sum of the squared residuals between some model and a data set; a measure of how well the model fits with the data.
- resistant adj Not greatly influenced by individual members of a sample.
- reweight verb To adjust the weighting given to a value.
- Rice distribution noun The probability distribution of the magnitude of a circular bivariate normal random variable with potentially non-zero mean.
- robust adj Not greatly influenced by errors in assumptions about the distribution of sample errors.
- RSL noun Initialism of regional screening level.
- sample noun A subset or portion of a population that is systematically selected for measurement, observation, or questioning, with the objective of…
- sample mean noun Given a random sample mathbf x₁,…, mathbf x_N from an n-dimensional random variable mathbf X, a mean defined as
- sample path noun Any set of possible values to which the appropriate random variables determined by a stochastic process might map a given point in the…
- sampling noun The analysis of a group by determining the characteristics of a significant percentage of its members chosen at random.
- scatter plot noun A type of display using Cartesian coordinates to display values for two variables for a set of data.
- scedasticity noun The distribution of error terms. Error terms are distributed either randomly and with constant variance (homoscedasticity) or with some…
- self-selection noun A form of nonprobability sampling bias in which individuals select themselves into a group.
- semimean noun The result obtained by taking either the largest or smallest half of the values and calculating the mean.
- semipartial adj Being or relating to a form of partial correlation that holds the third variable constant for either X or Y but (unlike a partial…
- sensitivity noun The probability, in a binary classification test, of a true positive being correctly identified.
- septile noun Any of the quantiles that divide an ordered sample population into seven equally numerous subsets.
- sequential probability ratio test noun A type of statistical test used to evaluate a hypothesis to within a specified level of confidence while minimizing the number of samples…
- sextile noun A quantile of six equal proportions; any of the subsets thus obtained.
- sigma noun The symbol σ, used to indicate one standard deviation from the mean, particularly in a normal distribution.
- sigmoid function noun Any of various real functions whose graph resembles an elongated letter "S"; specifically, the logistic function y=(eˣ)/(eˣ+1)=1/(1+e⁻ˣ).
- sigmoidal adj Characterized by a sigmoid curve or function
- significance level noun A measure of how likely it is to draw a false conclusion in a statistical test, when the results are really just random variations.
- significant adj Having a low probability of occurring by chance (for example, having high correlation and thus likely to be related).
- skew verb To cause (a distribution) to be asymmetrical.
- skew normal distribution noun A continuous probability distribution that generalizes the normal distribution to allow for nonzero skewness.
- skewed adj Biased, distorted
- skewness noun A measure of the asymmetry of the probability distribution of a real-valued random variable; is the third standardized moment, defined as…
- smooth noun The analysis obtained through a smoothing procedure.
- smoothing noun creation of an approximating function that attempts to capture important patterns in the data, while leaving out noise or other fine-scale…
- snowball sampling noun A nonprobability sampling technique where existing study subjects recruit future subjects from among their acquaintances.
- softmax noun A generalization of the logistic function that "squashes" a K-dimensional vector mathbf z of arbitrary real values to a K-dimensional…
- sojourn time noun The time spent in a state of a stochastic process.
- Sørensen-Dice coefficient noun A statistic used to gauge the similarity of two samples. It is equal to twice the number of elements common to both sets, divided by the…
- spaghetti model noun An illustration of different statistical outcomes that may be plotted from the same set of data.
- sparsistency noun Let mathbf b be a vector and define the support operatorname supp( mathbf b)=i: mathbf bᵢ≠0 where mathbf bᵢ is the ith element of mathbf b.…
- specificity noun The probability, in a binary classification test, of a true negative being correctly identified.
- spherical adj Of a multivariate probability distribution, to have a covariance matrix equal to the identity matrix up to a multiplicative factor.
- spread noun A measure of how far the data tend to deviate from the average.
- SS noun Initialism of sum of squares.
- standard deviation noun A measure of how spread out data values are around the mean, defined as the square root of the variance. Represented with the Greek letter…
- standard error noun A measure of how likely a mean of means is to be wrong. It is the standard deviation of the sample sizes in each to the sample means.
- statistical inference noun The drawing of conclusions about a population from a random sample drawn from it, or, more generally, about a random process from its…
- statistical power noun The probability that a statistical test will reject a false null hypothesis, that is, that it will not make a type II error, producing a…
- statistically significant adj Having a p-value of 0.05 or less (having a probability of 5% or less of occurring by random chance)
- Student's t distribution noun A distribution that arises when the population standard deviation is unknown and has to be estimated from the data.
- Student's t test noun Any statistical hypothesis test in which the test statistic has a Student's t-distribution if the null hypothesis is true.
- studentization noun The use of Student's t-test.
- subaverage noun A subordinate or local average.
- subcohort noun A subset of a cohort.
- subdistribution noun A subset of a distribution.
- superdistribution noun Any of various generalizations of a distribution, especially a common distribution that results from applying a single mapping to any…
- supramedian adj Greater than median
- sympercent noun A symmetric percentage difference (used to simplify the presentation of logarithmically transformed data)
- t distribution noun Ellipsis of Student's t distribution.
- t test noun Ellipsis of Student's t test.
- tail noun The part of a distribution most distant from the mode.
- tertile noun Either of the two points that divide an ordered distribution into three parts, each containing a third of the population.
- test-retest method noun A technique used to estimate the reliability or consistency of some measurement by correlating the results of multiple measurements, spread…
- tie noun One or more equal values or sets of equal values in the data set.
- time series noun A set of data points, each of which represents the value of the same variable at different times, normally at uniform intervals.
- time-use survey noun A statistical survey which aims to report data, on average, on the manners and ways of people spending their time.
- timeweighted adj Describing a statistic (especially an average) in which some time periods are given more weight than others.
- TOI noun Icetime; Abbreviation of time on ice.
- transdimensional adj Applicable to multiple dimensionalities; Having components or subspaces of different dimension.
- trimean noun A measure of a probability distribution's location defined as a weighted average of the distribution's median and its two quartiles.
- Tukey lambda distribution noun A continuous, symmetric probability distribution defined in terms of its quantile function, typically used to identify an appropriate…
- two-way adj Of a table, etc., having or involving exactly two variables; bivariate.
- unassociated adj Having no statistical association.
- unconfidence noun The complement of confidence; the probability that something is not the case.
- uncorrelated adj Having a covariance of zero
- universe noun The set of all admissible observations.
- update noun An adjustment of parameters in a model, or the rule by which they are adjusted.
- upweight verb To give a greater weight (or importance) to.
- URL noun Initialism of upper reference limit.
- var noun Abbreviation of variance.
- variance noun The second central moment in probability; the square of the standard deviation.
- variate noun Random variable.
- varimax adj Describing a rotation that maximizes the sum of the variances of the squared loadings, often used in surveys to see how groupings of…
- ventile noun Any of the nineteen points that divide an ordered distribution into twenty parts, each containing one twentieth of the population.
- vigintile noun Any of the values in a series that divides the distribution of individuals in that series into twenty groups of equal frequency.
- vincentization noun The technique of averaging three or more subjects' estimated or elicited quantile functions in order to define group quantiles from which F…
- Wald test noun A test that assesses constraints on statistical parameters based on the weighted distance between the unrestricted estimate and its…
- weight noun A variable which multiplies a value for ease of statistical manipulation.
- weighted adj With the components of an average multiplied by particular factors so as to take account of their relative importance.
- whisker noun A graphic element that shows the maxima and minima in a box plot.
- whiten verb To normalize data so that the covariance matrix becomes the identity matrix; i.e., to remove correlations so each variable has unit…
- whiteness noun The quality of being white noise.
- Wilson score interval noun An improvement over the normal binomial approximation interval in that the actual coverage probability is closer to the nominal value.
- window function noun A function that limits a signal to a restricted portion of time or frequencies.
- Wishart distribution noun A generalisation of the chi-square distribution to an arbitrary (integer) number of dimensions, or of the gamma distribution to a…
- within one sigma prep_phrase Describing the range from the mean, plus or minus one standard deviation, usually covering 68% of the data points in a normal distribution.
- z-test noun Any statistical test for which the distribution of the test statistic under the null hypothesis can be approximated by a normal…
- ziggurat algorithm noun An algorithm for pseudorandom number sampling, relying on an underlying source of uniformly-distributed random numbers as well as computed…