Statistics and Models

Statistic/Model	OnlineStat
Univariate Statistics:
Mean	`Mean`
Variance	`Variance`
Quantiles	`Quantile` and `P2Quantile`
Maximum/Minimum	`Extrema`
Skewness and kurtosis	`Moments`
Sum	`Sum`
Time Series:
Difference	`Diff`
Lag	`Lag`
Autocorrelation/autocovariance	`AutoCov`
Tracked history	`StatHistory`
Multivariate Analysis:
Covariance/correlation matrix	`CovMatrix`
Principal components analysis	`CovMatrix`
K-means clustering (SGD)	`KMeans`
Multiple univariate statistics	`Group`
Nonparametric Density Estimation:
Histograms	`Hist`
Approximate order statistics	`OrderStats`
Count for each unique value	`CountMap`
Parametric Density Estimation:
Beta	`FitBeta`
Cauchy	`FitCauchy`
Gamma	`FitGamma`
LogNormal	`FitLogNormal`
Normal	`FitNormal`
Multinomial	`FitMultinomial`
MvNormal	`FitMvNormal`
Statistical Learning:
GLMs with regularization	`StatLearn`
Logistic regression	`StatLearn`
Linear SVMs	`StatLearn`
Quantile regression	`StatLearn`
Absolute loss regression	`StatLearn`
Distance-weighted discrimination	`StatLearn`
Huber-loss regression	`StatLearn`
Linear (also ridge) regression	`LinReg`, `LinRegBuilder`
Other:
Statistical Bootstrap	`Bootstrap`
Approx. count of distinct elements	`HyperLogLog`
Reservoir sampling	`ReservoirSample`
Callbacks	`CallFun`, `eachrow`, `eachcol`
Big Data Viz	`Partition`, `IndexedPartition`
Collections of Stats:
Applied to same data stream	`Series`, `FTSeries`
Applied to different data streams	`Group`
Calculated stat by group	`GroupBy`