criterium.stats.core — org.hugoduncan/criterium 0.5.245-ALPHA

Core statistical functions: min, max, mean, sum, variance, median, quartiles, quantile.

All functions require typed arrays (ITypedArray) as input. Primitive-optimized implementations avoid boxing overhead.

accumulate-variance! clj

(accumulate-variance! acc x)

central-moment clj

(central-moment data mean r)

Compute the r-th central moment: (1/n) * Σ(xᵢ - μ)^r Requires a typed array (ITypedArray).

cv clj

(cv data)

Coefficient of variation (CV), also known as relative standard deviation. Computed as σ/μ (standard deviation divided by mean).

Returns Double/NaN if mean is zero or data has fewer than 2 elements. CV is dimensionless and useful for comparing variability across datasets with different units or scales. Requires a typed array (ITypedArray).

kurtosis clj

(kurtosis data)

(kurtosis data type)

Compute sample excess kurtosis using one of three methods.

Type 1: g₂ = m₄ / m₂² - 3 - typical textbook definition Type 2: G₂ = ((n+1)g₂ + 6)(n-1) / ((n-2)(n-3)) - unbiased under normality (SAS/SPSS) Type 3: b₂ = (g₂ + 3)((n-1)/n)² - 3 - used in MINITAB/BMDP

Where m_r = sample central moment of order r: Σ(xᵢ - μ)^r / n

Default is type 2 (unbiased under normality). Returns excess kurtosis (normal distribution has excess kurtosis of 0). Returns 0.0 for constant data (zero variance). Requires a typed array (ITypedArray).

Reference: Joanes & Gill (1998), Comparing measures of sample skewness and kurtosis. The Statistician, 47, 183-189.

max clj

(max data)

(max data _count)

Maximum value in data. Requires a typed array (ITypedArray).

mean clj

(mean data)

(mean data count)

Arithmetic mean of data. Requires a typed array (ITypedArray).

median clj

(median data)

Calculate the median of a sorted data set. Return [median nil nil] (partitions not supported for typed arrays). Requires a typed array (ITypedArray). References: http://en.wikipedia.org/wiki/Median

median-value clj

(median-value data)

Calculate the median value of a sorted data set. Returns just the median value (not the lower/upper partitions). Requires a typed array (ITypedArray). References: http://en.wikipedia.org/wiki/Median

min clj

(min data)

(min data _count)

Minimum value in data. Requires a typed array (ITypedArray).

quantile clj

(quantile quantile data)

Calculate the quantile of a sorted data set. Requires a typed array (ITypedArray). References: http://en.wikipedia.org/wiki/Quantile

quartiles clj

(quartiles data)

Calculate the quartiles of a sorted data set. Returns [q1 median q3]. Requires a typed array (ITypedArray). References: http://en.wikipedia.org/wiki/Quartile

skewness clj

(skewness data)

(skewness data type)

Compute sample skewness using one of three methods.

Type 1: g₁ = m₃ / m₂^(3/2) - typical textbook definition Type 2: G₁ = g₁ × √(n(n-1)) / (n-2) - unbiased under normality (SAS/SPSS) Type 3: b₁ = g₁ × ((n-1)/n)^(3/2) - used in MINITAB/BMDP

Where m_r = sample central moment of order r: Σ(xᵢ - μ)^r / n

Default is type 2 (unbiased under normality). Returns 0.0 for constant data (zero variance), since constant data is symmetric. Requires a typed array (ITypedArray).

Reference: Joanes & Gill (1998), Comparing measures of sample skewness and kurtosis. The Statistician, 47, 183-189.

sum clj

(sum data)

Sum of each data point. Requires a typed array (ITypedArray).

sum-of-squares clj

(sum-of-squares data)

Sum of the squares of each data point. Requires a typed array (ITypedArray).

transpose clj

(transpose data)

Transpose a vector of vectors.

variance clj

(variance data)

(variance data df)

Return the variance of data.

By default returns the sample variance with (- (count data) 1) degrees of freedom.

The population variance can be returned using (variance data 0), which uses (count data) degrees of freedom.

Requires a typed array (ITypedArray).

Ref: Chan et al. Algorithms for computing the sample variance: analysis and recommendations. American Statistician (1983).

variance* clj

(variance* data mean df)

Variance based on subtracting mean. Requires a typed array (ITypedArray).