MerQuR+Statistics Glossary

Statistics Glossary → Standard error

Standard errorconcept

The standard deviation of an estimate's sampling distribution, showing how much an estimate (such as a mean or a regression coefficient) would vary from sample to sample.

If we drew many samples from the same population and computed the mean each time, the means would differ slightly. The standard error is the standard deviation of those estimates, so it measures how precise the estimate is. For the mean, SE = s / √n: the standard error shrinks as the sample grows, but quadrupling the sample only halves it.

It should not be confused with the standard deviation: the standard deviation describes the spread of individual observations, the standard error the uncertainty of an estimate. Confidence intervals and test statistics (such as t = estimate / SE) are built on the standard error. When observations are not independent (clustered data, repeated measures) or the variance is not constant, the classical formula can understate the standard error; robust or cluster-robust standard errors are then used.

An everyday example

A café checks how much coffee goes into each cup. Individual cups differ by about 4 grams (the standard deviation). If 16 random cups are weighed and averaged, the standard error of that average is 4 / √16 = 1 gram, so a 16-cup average lands much closer to the true mean than any single cup does.

In MerQur

It accompanies estimates in almost every analysis: the standard error of the mean in Descriptive Statistics, the standard error of the mean difference in the t-tests, and the SE column of the coefficient tables in regression and mixed models. In Quantile Regression, 'SE / CI method (Robust kernel, nid, ker, boot)' chooses how the standard error is computed; Cohen's Kappa reports the SE of κ, and Weighted Total reports an SE computed by Taylor linearization.

Analyses where this concept appears

Descriptive StatisticsOne-Sample t-TestIndependent-Samples t-TestPaired t-TestOne-Way ANOVATwo-Way ANOVARepeated Measures ANOVAANCOVABootstrap CIMann-Whitney UWilcoxon Signed-RankKruskal-WallisFriedmanCohen's Kappa (including Fleiss κ and Krippendorff α)Cochran-Mantel-Haenszel (CMH) TestLog-Linear ModelCorrelation AnalysisBland-Altman Agreement AnalysisMeta-AnalysisMultiple Linear RegressionLogistic RegressionPoisson / Negative Binomial Regression (Count Regression)Multinomial Logistic RegressionOrdinal Logistic RegressionRidge RegressionLasso RegressionLinear Mixed Models (LMM)Nested Mixed Model (Nested LMM, Multi-Level Hierarchical Mixed Model)Crossed Mixed Model (Crossed LMM, Crossed Random Effects Mixed Model)Generalized Estimating Equations (GEE)Generalized Linear Mixed Models (GLMM)Panel Data RegressionInstrumental Variables Regression (2SLS)Propensity Score AnalysisDifference-in-Differences (DiD)ROC CurveTrue Skill Statistic (TSS)Confusion Matrix MetricsDecision Tree (CART)K-Means ClusteringLikert Scale AnalysisIntraclass Correlation Coefficient (ICC)Confirmatory Factor Analysis (CFA)Structural Equation Modeling (SEM)Item Response Theory (IRT / Rasch)Weighted Mean (Survey Means)Weighted Frequency (Survey Freq)Weighted Total (Survey Total)Weighted Linear Regression (Survey Regression)Weighted Logistic Regression (Survey Logistic Regression)Variance Components Analysis (VARCOMP)Nonlinear RegressionQuantile RegressionRegularized Regression (LASSO / Ridge / ElasticNet)Partial Least Squares Regression (PLS)Probit RegressionTobit Regression (Censored Regression)Conditional Logit (Choice Model)Bayesian t-Test (JZS Bayes Factor)Hierarchical Bayesian RegressionSAR (Spatial Autoregressive Lag)Spatial Error Model (SEM)GWR (Geographically Weighted Regression)Mediation AnalysisPath AnalysisMultiple ImputationKaplan-Meier Survival AnalysisCox Regression (Proportional Hazards Model)Parametric Survival (AFT)Competing RisksTime-dependent Cox RegressionSurvey-PHREG (Weighted Cox)Cluster-Robust Cox (Marginal and Frailty Models)Time SeriesARIMA ForecastVAR (Vector Autoregression)GARCH (Volatility Model)LOESS (Local Regression)Response Surface Regression (RSREG)Variogram + Kriging (Spatial Interpolation)

Related concepts

Confidence level and confidence intervalRobust (sandwich) standard errors (HC0-HC3)