Outlier detection using boxplot thresholds.
Provides both standard symmetric boxplot and adjusted boxplot for skewed distributions using the medcouple statistic.
All functions require typed arrays (ITypedArray) as input.
Outlier detection using boxplot thresholds. Provides both standard symmetric boxplot and adjusted boxplot for skewed distributions using the medcouple statistic. All functions require typed arrays (ITypedArray) as input.
(adjusted-boxplot-outlier-thresholds q1 q3 mc)Outlier thresholds for given quartiles adjusted for skewness. Returns [low-severe low-mild high-mild high-severe].
Uses the adjusted boxplot method from Hubert & Vandervieren (2008) which accounts for skewness via the medcouple statistic.
When mc = 0 (symmetric), reduces to standard boxplot thresholds. When mc > 0 (right-skewed), upper fence widens, lower fence narrows. When mc < 0 (left-skewed), lower fence widens, upper fence narrows.
Outlier thresholds for given quartiles adjusted for skewness. Returns [low-severe low-mild high-mild high-severe]. Uses the adjusted boxplot method from Hubert & Vandervieren (2008) which accounts for skewness via the medcouple statistic. When mc = 0 (symmetric), reduces to standard boxplot thresholds. When mc > 0 (right-skewed), upper fence widens, lower fence narrows. When mc < 0 (left-skewed), lower fence widens, upper fence narrows.
(boxplot-outlier-thresholds q1 q3)Outlier thresholds for given quartiles. Returns [severe-low mild-low mild-high severe-high].
Outlier thresholds for given quartiles. Returns [severe-low mild-low mild-high severe-high].
(medcouple sorted-data)Compute the medcouple, a robust measure of skewness. Returns a value in [-1, 1] where positive indicates right-skew and negative indicates left-skew.
The medcouple is the median of the kernel function h(x_i, x_j) evaluated over all pairs where x_i ≤ median ≤ x_j.
Uses the naive O(n²) algorithm. For criterium's typical sample sizes (hundreds to low thousands), this is acceptable.
Requires a typed array (ITypedArray). Takes sorted data as input. Returns 0.0 for constant data or n < 3.
Compute the medcouple, a robust measure of skewness. Returns a value in [-1, 1] where positive indicates right-skew and negative indicates left-skew. The medcouple is the median of the kernel function h(x_i, x_j) evaluated over all pairs where x_i ≤ median ≤ x_j. Uses the naive O(n²) algorithm. For criterium's typical sample sizes (hundreds to low thousands), this is acceptable. Requires a typed array (ITypedArray). Takes sorted data as input. Returns 0.0 for constant data or n < 3.
(medcouple-kernel xi xj med)Compute the medcouple kernel h(x_i, x_j). For values not both at the median: h = ((x_j - median) - (median - x_i)) / (x_j - x_i) For values both at the median, returns 0.
Compute the medcouple kernel h(x_i, x_j). For values not both at the median: h = ((x_j - median) - (median - x_i)) / (x_j - x_i) For values both at the median, returns 0.
cljdoc builds & hosts documentation for Clojure/Script libraries
| Ctrl+k | Jump to recent docs |
| ← | Move to previous article |
| → | Move to next article |
| Ctrl+/ | Jump to the search field |