@mark1russell7/rigor-statistics 0.1.18 → 0.1.20

package/README.md

@@ -111,7 +111,8 @@ The default expansion has one product for each pair of levels of two dimensions.
 | `bootstrapMedian`, `bootstrapClusters` | The interval of the median, and a bootstrap that draws whole clusters (boards, seeds, sites). |
 | `bootstrapTwo(a, b, statistic, options)` | A bootstrap interval of a statistic of two independent samples, for example two arms of a benchmark. Each run draws all of `a`, then all of `b`. |
 | `bootstrapMedianRatio(numerator, denominator, options)` | The interval of `median(numerator) / median(denominator)`. It is the uncertainty of the ratio, not the spread of the samples. |
-| `sampleTotalInterval(values, { population, scale })` | The interval of the total of a population from a uniform sample of `m` of its `n` items without replacement. The deviations get the finite population correction `sqrt(1 - m / n)`. `scale` is `n / m` by default. When `m` is `n`, the interval is the estimate. For a small `m`, the interval is too narrow: at `m = 8` of `n = 40`, the coverage is 0.865. |
+| `sampleTotalInterval(values, { population, scale })` | The interval of the total of a population from a uniform sample of `m` of its `n` items without replacement. The deviations get the finite population correction `sqrt(1 - m / n)`. `scale` is `n / m` by default. When `m` is `n`, the interval is the estimate. For a small `m`, the interval is too narrow: at `m = 8` of `n = 40`, the coverage is 0.865. For a total over pairs, use `uStatisticInterval`. |
+| `uStatisticInterval(totals, { order, population, method, level, range })` | The interval of a total over all sets of `r` units of a population, for example the crossings of all pairs. The input is the total of each unit of a sample without replacement. The estimate is `S * C(n, r) / C(m, r)`. The method `"conservative"` uses the Hoeffding bound of a U-statistic with `floor(m / r)` draws and the `range` of the kernel. It holds at each `m`. The method `"tight"` uses the jackknife variance times `1 - m / n`, and the t quantile with `m - 1` degrees of freedom. This variance is exact for a linear kernel and larger for others. When all the totals are equal, the method `"tight"` uses the method `"conservative"`, or it throws without `range`. The result gives the `method` that it used. At `m = 8`, the coverage of `"tight"` is 0.885 to 0.915 for a skewed kernel. The method `"auto"` needs `range`. It uses `"tight"` from `m = U_STATISTIC_TIGHT_MIN_SAMPLE`. The calibration study `u-statistic-interval` sets this constant with `coverageMinSample`. Until a run of the study gives a value, it is infinite. |
 | `leastSquares(x, y, { intercept })` | The ordinary least-squares fit of `y` on the rows of `x`, with a QR decomposition. It gives the coefficients, `residualSd`, `r2`, `n` and `k`. A singular design gives NaN coefficients. |
 | `bootstrapLeastSquares(x, y, options)` | One bootstrap interval for each coefficient of `leastSquares`, from the same draws of whole rows. A singular draw does not count. |
 | `ridgeSolve(gram, moment, lambda, { free })` | The ridge coefficients from the normal equations `X'X` and `X'y`, with a Cholesky factorization. The `free` coefficients have no penalty. A matrix that is not positive definite gives NaN coefficients. |
@@ -126,6 +127,8 @@ The default expansion has one product for each pair of levels of two dimensions.
 | `quantileSamples(p, level)` | The fewest independent values that give a quantile an upper bound. At the level 0.95: 72 values for p95, 368 for p99 and 3,688 for p99.9. |
 | `binomialInterval(n, p, level)`, `negativeBinomialInterval(successes, p, level)` | The central interval of a binomial count, and of a count of failures before `successes` successes. Each tail outside holds `(1 - level) / 2` or less. |
 | `holm(pValues, level)` | The Holm correction of a family of tests. |
+| `binomialTest(k, n, p, side)` | The p of the exact one-sided binomial test of `k` successes in `n` trials. The side `"less"` gives `P(X <= k)`, and `"greater"` gives `P(X >= k)`. |
+| `coverageMinSample(cells, { level, alpha, pooledLow })` | The smallest sample size `m` from which an interval method keeps its level, from the hits of seeded cells. A size qualifies when the cells with a sample of that size or more pass two tests. No cell rejects `level` in `binomialTest` after `holm` at `alpha`, and the `wilson` lower end of the pooled hits is `pooledLow` or more. The set is closed upward: the result is the smallest `m` such that each size of `m` or more qualifies. `blocking` gives the largest size that fails. When the largest size fails, the result is `Infinity`. Fix the bar before the run. |
 | `partialConjunction(pValues, need)` | The p of the claim that at least `need` of these tests have a real effect. |
 | `spearman`, `kendallTau`, `ranks` | The rank correlations, with mean ranks for ties. |
 | `compareRatios`, `noiseFloor`, `noiseVerdict` | The comparison with a baseline, the noise floor of the 5-seed rule with a margin of practical effect, and the state of a difference over the seeds. |

package/build/index.d.ts

@@ -172,7 +172,7 @@ interface SampleTotalOptions extends BootstrapOptions {
  * The interval is narrow for a small sample. The draws give the variance of the sample with the divisor `m`, not
  * `m - 1`, so the width gets the factor `sqrt((m - 1) / m)`. The skew of the values adds to the miss. In the tests,
  * 400 samples of `m = 8` of `n = 40` hold the total 346 times (Wilson 0.828 to 0.895). At `m = 100` of `n = 200`,
- * the coverage agrees with 95%.
+ * the coverage agrees with 95%. For a total over the pairs of the items, use `uStatisticInterval`.
  */
 export declare function sampleTotalInterval(values: readonly number[], options: SampleTotalOptions): Interval;
 /** The smooth laws that `smoothLawScores` compares. Each law has 2 fitted numbers. */
@@ -938,6 +938,23 @@ interface CountInterval {
  * or less. The two tails are separate sums, so that a small upper tail keeps its digits.
  */
 export declare function binomialInterval(n: number, p: number, level?: number): CountInterval;
+/** The side of `binomialTest`: `"less"` gives `P(X <= k)`, and `"greater"` gives `P(X >= k)`. */
+type BinomialSide = "less" | "greater";
+/**
+ * This function gives the p of the exact one-sided binomial test of `k` successes in `n` trials, with
+ * X ~ Binomial(n, p). The side `"less"` gives `P(X <= k)`. A small value rejects the claim "the chance is `p` or
+ * more". The side `"greater"` gives `P(X >= k)`. A small value rejects the claim "the chance is `p` or less".
+ *
+ * The sum starts at the largest term of the tail, so a small tail keeps its digits. At `p = 1/2`, the side
+ * `"greater"` is equal to the one-sided `signTest(k, n - k)`.
+ *
+ * @param k - The count of successes, a whole number from 0 to `n`.
+ * @param n - The count of trials, a whole number of 0 or more.
+ * @param p - The chance of a success under the claim, from 0 to 1.
+ * @param side - The side of the tail.
+ * @returns The p of the test, from 0 to 1.
+ */
+export declare function binomialTest(k: number, n: number, p: number, side: BinomialSide): number;
 /**
  * The central interval of a negative binomial count. X is the count of failures before `successes` successes, and
  * `p` is the chance of a success at each try. `low` is the smallest k with P(X <= k) > (1 - level) / 2.
@@ -1090,5 +1107,214 @@ interface OptionFloorOptions {
  * @returns A whole number of 2 or more.
  */
 export declare function optionFloor(options: OptionFloorOptions): number;
-export type { BootstrapOptions, CalibrationLevel, CategoricalDimension, CompareOptions, Comparison, ContinuousDimension, Corrected, CountInterval, Effect, Forecast, Interval, Kappa, LeastSquaresFit, LeastSquaresOptions, MedianInterval, ModeOptions, NoiseOptions, NoiseState, NoiseVerdict, OptionFloorOptions, OrdinalDimension, ParsedResponseRecord, PermutationOptions, PermutationResult, Proportion, QuantileInterval, QuantileMethod, ResponseAbsentPoint, ResponseBand, ResponseCurvePoint, ResponseData, ResponseDimension, ResponseDimensionBase, ResponseFactor, ResponseFault, ResponseFitOptions, ResponseFold, ResponseFoldError, ResponseHeldOutError, ResponseInputValue, ResponseMeasure, ResponseModel, ResponseModelBase, ResponsePoint, ResponseReason, ResponseRecord, ResponseSlice, ResponseSliceOptions, ResponseSlicePoint, ResponseSurface, ResponseSurfaceAbsentPoint, ResponseSurfaceOptions, ResponseSurfacePoint, ResponseTableCell, ResponseValue, ResponseViewOptions, ResponseWhen, RidgeInput, RidgeInputBase, RidgeLevelInput, RidgeNumberInput, RidgeOptions, RidgeRankInput, RidgeResponseModel, RidgeTerm, SampleTotalOptions, SideP, SmoothLaw, SmoothLawScore, Summary, TableResponseModel, TwoSamplePermutationOptions, TwoSamplePermutationResult };
+/** One cell of a coverage study: the hits of a method on the true value in `draws` seeded samples of size `sample`. */
+interface CoverageCell {
+  /** The name of the cell, for example `"skewed 120/108"`. The result names the rejected cells with it. */
+  readonly name: string;
+  /** The sample size `m` of the cell, a whole number of 1 or more. */
+  readonly sample: number;
+  /** The count of samples whose interval holds the true value, a whole number from 0 to `draws`. */
+  readonly hits: number;
+  /** The count of samples of the cell, a whole number of 1 or more. */
+  readonly draws: number;
+}
+/** The bar of `coverageMinSample`. Fix it before the run, and do not change it after the run. */
+interface CoverageBar {
+  /** The coverage that the method claims, for example 0.95. Each cell has a one-sided exact binomial test of it. */
+  readonly level: number;
+  /** The level of the Holm family of the cell tests, for example 0.05. */
+  readonly alpha: number;
+  /** The smallest Wilson lower end of the pooled coverage, for example 0.94. */
+  readonly pooledLow: number;
+  /** The z of the Wilson interval. The default is `Z95`. */
+  readonly z?: number;
+}
+/** The reason of one step: `"qualifies"`, or the test or tests that failed. */
+type CoverageReason = "qualifies" | "cell-rejected" | "pooled-low" | "cell-rejected-and-pooled-low";
+/** The result of the bar at one sample size `m`, over each cell with a sample of `m` or more. */
+interface CoverageStep {
+  /** The sample size `m` of the step. */
+  readonly sample: number;
+  /** The count of cells with a sample of `m` or more. */
+  readonly cells: number;
+  /** The names of the cells that reject the coverage `level`, after the Holm correction. */
+  readonly rejected: readonly string[];
+  /** The smallest Holm-adjusted p of the cells of the step. */
+  readonly smallestAdjusted: number;
+  /** The sum of the hits of the cells of the step. */
+  readonly hits: number;
+  /** The sum of the draws of the cells of the step. */
+  readonly draws: number;
+  /** The Wilson interval of the pooled coverage `hits / draws`. */
+  readonly pooled: Proportion;
+  /** The sample size `m` passes the two tests of the bar. */
+  readonly qualifies: boolean;
+  readonly reason: CoverageReason;
+}
+/** The result of `coverageMinSample`. */
+interface CoverageMinSample {
+  /**
+   * The smallest sample size `m` of the cells such that each size of `m` or more passes the bar. It is infinite when
+   * the largest size fails.
+   */
+  readonly minSample: number;
+  /** The largest sample size that fails the bar. It blocks each smaller size. The result has no `blocking` when each size passes. */
+  readonly blocking?: number;
+  /** One step for each sample size of the cells, from the smallest to the largest. */
+  readonly steps: readonly CoverageStep[];
+}
+/**
+ * This function applies a fixed bar of coverage to the cells of a study. It gives the smallest sample size `m` from
+ * which an interval method keeps its level. The method qualifies at `m` when the cells with a sample of `m` or more
+ * pass two tests:
+ *
+ * 1. No cell rejects the coverage `level`. Each cell has the exact one-sided binomial test `P(X <= hits)`, with
+ *    X ~ Binomial(draws, level). The family of these tests gets the Holm correction at `alpha`.
+ * 2. The Wilson lower end of the pooled coverage, the sum of the hits over the sum of the draws, is `pooledLow`
+ *    or more.
+ *
+ * Each step tells the result of the two tests at its `m`. A step does not depend on the steps of other sizes. At a
+ * small `m`, the pool also holds the cells of the larger sizes. Thus a small `m` can pass while a larger `m` fails
+ * alone, for example near `m = n`.
+ *
+ * Thus the set of sizes is closed upward. The result is the smallest `m` of the cells such that each size of `m` or
+ * more qualifies. The field `blocking` gives the largest size that fails. When the largest size fails, the result is
+ * infinite.
+ *
+ * @param cells - The hits and the draws of each cell. Each cell has its own sample size.
+ * @param bar - The level, the alpha of the Holm family and the pooled lower end.
+ * @returns The smallest size from which each size qualifies, the size that blocks, and the result at each size.
+ */
+export declare function coverageMinSample(cells: readonly CoverageCell[], bar: CoverageBar): CoverageMinSample;
+/** The methods of `uStatisticInterval`. The method `"auto"` selects one of the other two for each sample. */
+type UStatisticMethod = "conservative" | "tight" | "auto";
+/**
+ * The smallest sample `m` at which the method `"auto"` uses the method `"tight"`. The calibration study
+ * `u-statistic-interval` gives the value with `coverageMinSample`. The value is the smallest `m` of the grid such that
+ * each `m` of the grid from this value up passes the bar. Until a run of the study gives a value, the value is
+ * infinite. The TSDoc of `uStatisticInterval` gives the bar of the study.
+ */
+export declare const U_STATISTIC_TIGHT_MIN_SAMPLE: number;
+/** The options of `uStatisticInterval`. */
+interface UStatisticOptions {
+  /** The order `r` of the kernel: the number of units in each set. It is a whole number of 1 or more. */
+  readonly order: number;
+  /** The number of units in the whole population, `n`. It is a whole number, and it is not less than the sample. */
+  readonly population: number;
+  /** The method of the interval. The methods `"conservative"` and `"auto"` need `range`. */
+  readonly method: UStatisticMethod;
+  /** The level of the interval. The default is 0.95. */
+  readonly level?: number;
+  /** The smallest and the largest value of the kernel. With it, the interval stays in this range. */
+  readonly range?: readonly [low: number, high: number];
+}
+/** The mean of the kernel over all the sets of `r` units of the population, with its interval. */
+interface UStatisticMean {
+  /** The U-statistic: the mean of the kernel over the sets of `r` units of the sample. */
+  readonly estimate: number;
+  readonly low: number;
+  readonly high: number;
+}
+/** The result of `uStatisticInterval`. The total is the mean of the kernel times `subsets`. */
+interface UStatisticInterval {
+  /** The estimate of the total of the population: `S * C(n, r) / C(m, r)`, with `S` the total of the sample. */
+  readonly estimate: number;
+  readonly low: number;
+  readonly high: number;
+  readonly level: number;
+  /** The method that made the interval. It is not `requested` after a fallback or a choice of the method `"auto"`. */
+  readonly method: "conservative" | "tight";
+  /** The method of the options. */
+  readonly requested: UStatisticMethod;
+  /** The mean of the kernel, with its interval. */
+  readonly mean: UStatisticMean;
+  /** The number of sets of `r` units in the population, `C(n, r)`. */
+  readonly subsets: number;
+  /** The standard error of the total. Only an interval of the method `"tight"` has it. */
+  readonly standardError?: number;
+  /** The degrees of freedom of the t quantile, `m - 1`. Only an interval of the method `"tight"` has it. */
+  readonly df?: number;
+}
+/**
+ * This function gives the interval of a total over all the sets of `r` units of a population. The data is a uniform
+ * sample of `m` of the `n` units, without replacement. An example is the count of crossings between all pairs of
+ * routes. The input is the total of each sampled unit: the sum of the kernel over the sets of `r` sampled units
+ * that hold the unit. Thus the sum of the totals is `r * S`, with `S` the total of the sample. The kernel is
+ * symmetric.
+ *
+ * The estimate is `S * C(n, r) / C(m, r)`. It is the U-statistic `U = S / C(m, r)` times `C(n, r)`. At `r = 1`,
+ * the estimate is `n / m` times the sum of the sample. When `m` is `n`, the interval is the estimate.
+ *
+ * The method `"conservative"` uses the inequality of Hoeffding (1963) for U-statistics, with `k = floor(m / r)`. The
+ * half width of the mean is `(b - a) * sqrt(ln(2 / (1 - level)) / (2 k))`, with `[a, b]` the range of the kernel.
+ * The bound is also true for a sample without replacement (Ai, Kuželka and Wang 2022, Blanc 2023 Theorem 6).
+ * Thus the interval holds at each `m`. It is wide at a small `m`.
+ *
+ * The method `"tight"` uses the jackknife variance of `U`, from the totals only, times the finite population
+ * correction `1 - m / n`. The interval is `U` plus or minus the t quantile with `m - 1` degrees of freedom, times
+ * the standard error.
+ *
+ * The correction comes from the inclusion probabilities of a sample without replacement. The variance of the linear
+ * part of `U` (its Hájek projection) gets exactly the factor `1 - m / n`. The variance of the remainder gets a
+ * smaller factor, near `(1 - m / n)^2`, relative to an independent sample. For `r = 2` this factor is
+ * `(n - m)(n - m - 1) / ((n - 2)(n - 3))`. Thus this estimate of the variance is exact for a linear kernel, and
+ * larger than the variance for other kernels. The tests read the two facts over all samples of small populations.
+ *
+ * The method `"tight"` does not give an interval of width 0 when `m` is less than `n`. When all the totals are
+ * equal, the jackknife variance is 0. Then the function uses the method `"conservative"` for the sample, and the
+ * result has `method: "conservative"`. Without `range`, the function throws a `RangeError` for this sample.
+ *
+ * The method `"tight"` has no proof of its coverage. The tests use 200 samples of made-up populations at the level
+ * 0.95. The table gives the hits of 200 for each population `n` and sample `m`. Each count includes the fallback.
+ *
+ * | n / m | sparse | crossings | skewed |
+ * | --- | --- | --- | --- |
+ * | 40 / 8 | 200 | 200 | 183 |
+ * | 40 / 10 | 200 | 200 | 187 |
+ * | 40 / 12 | 200 | 183 | 189 |
+ * | 40 / 20 | 180 | 183 | 188 |
+ * | 40 / 36 | 192 | 189 | 193 |
+ * | 60 / 8 | 200 | 200 | 181 |
+ * | 60 / 10 | 200 | 200 | 180 |
+ * | 60 / 12 | 200 | 195 | 186 |
+ * | 60 / 20 | 184 | 190 | 183 |
+ * | 60 / 40 | 186 | 193 | 180 |
+ * | 120 / 8 | 200 | 200 | 177 |
+ * | 120 / 10 | 200 | 192 | 175 |
+ * | 120 / 12 | 200 | 189 | 178 |
+ * | 120 / 20 | 191 | 193 | 182 |
+ * | 120 / 40 | 194 | 192 | 185 |
+ * | 120 / 60 | 195 | 189 | 185 |
+ * | 120 / 108 | 187 | 185 | 190 |
+ *
+ * The sparse kernel holds 2% to 3% of the pairs. The skewed kernel has a few large values. At `m = 8`, the skewed
+ * kernel gets 177 to 183 of 200, a coverage of 0.885 to 0.915. No row has 190 or more in each kernel.
+ *
+ * The method `"auto"` needs `range`. It uses the method `"tight"` when `m` is `U_STATISTIC_TIGHT_MIN_SAMPLE` or more
+ * and the variance is more than 0. Otherwise, it uses the method `"conservative"`.
+ *
+ * The calibration study `u-statistic-interval` sets `U_STATISTIC_TIGHT_MIN_SAMPLE`. Its bar was fixed before its run.
+ * The study draws 1000 samples in each cell of the 3 kernels and the 17 cells of the table. The method `"tight"`
+ * qualifies at `m` when the cells with a sample of `m` or more pass two tests.
+ *
+ * First, no cell rejects the coverage 0.95 in a one-sided exact binomial test at alpha 0.05, with the Holm
+ * correction over these cells. Second, the Wilson lower end of the pooled coverage of these cells is 0.94 or more.
+ * `coverageMinSample` applies this bar.
+ *
+ * The set of sizes is closed upward. The constant is the smallest `m` of the grid such that each `m` of the grid from
+ * this value up qualifies. A small `m` pools the good cells of the larger sizes, so it can pass while a larger `m`
+ * fails alone. The upward rule keeps the method `"auto"` away from a size that failed.
+ *
+ * When the largest `m` fails, the constant is infinite. Until a run of the study gives a value, the constant is infinite. Thus the method `"auto"`
+ * uses the method `"conservative"` at each `m` less than `n`.
+ *
+ * With `range`, the interval of the mean stays in `[a, b]`, and each total is in the range of a sum of
+ * `C(m - 1, r - 1)` kernel values.
+ *
+ * @param totals - The total of each unit of the sample. The sample has more units than `r`.
+ * @param options - The order, the population, the method, the level and the range of the kernel.
+ * @returns The estimate and the interval of the total, and of the mean of the kernel.
+ */
+export declare function uStatisticInterval(totals: readonly number[], options: UStatisticOptions): UStatisticInterval;
+export type { BinomialSide, BootstrapOptions, CalibrationLevel, CategoricalDimension, CompareOptions, Comparison, ContinuousDimension, Corrected, CountInterval, CoverageBar, CoverageCell, CoverageMinSample, CoverageReason, CoverageStep, Effect, Forecast, Interval, Kappa, LeastSquaresFit, LeastSquaresOptions, MedianInterval, ModeOptions, NoiseOptions, NoiseState, NoiseVerdict, OptionFloorOptions, OrdinalDimension, ParsedResponseRecord, PermutationOptions, PermutationResult, Proportion, QuantileInterval, QuantileMethod, ResponseAbsentPoint, ResponseBand, ResponseCurvePoint, ResponseData, ResponseDimension, ResponseDimensionBase, ResponseFactor, ResponseFault, ResponseFitOptions, ResponseFold, ResponseFoldError, ResponseHeldOutError, ResponseInputValue, ResponseMeasure, ResponseModel, ResponseModelBase, ResponsePoint, ResponseReason, ResponseRecord, ResponseSlice, ResponseSliceOptions, ResponseSlicePoint, ResponseSurface, ResponseSurfaceAbsentPoint, ResponseSurfaceOptions, ResponseSurfacePoint, ResponseTableCell, ResponseValue, ResponseViewOptions, ResponseWhen, RidgeInput, RidgeInputBase, RidgeLevelInput, RidgeNumberInput, RidgeOptions, RidgeRankInput, RidgeResponseModel, RidgeTerm, SampleTotalOptions, SideP, SmoothLaw, SmoothLawScore, Summary, TableResponseModel, TwoSamplePermutationOptions, TwoSamplePermutationResult, UStatisticInterval, UStatisticMean, UStatisticMethod, UStatisticOptions };
 //# sourceMappingURL=index.d.ts.map

package/build/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","names":[],"sources":["../src/describe.ts","../src/regression.ts","../src/bootstrap.ts","../src/distribution.ts","../src/ridge.ts","../src/response.ts","../src/response-parse.ts","../src/response-fit.ts","../src/tests.ts","../src/agreement.ts","../src/rank.ts","../src/discrete.ts","../src/compare.ts","../src/power.ts"],"mappings":";;;;;;KAOY;;wBAmBI,OAAO;wBAIP,KAAK;;;;;wBAgBL,GAAG;;;;;;;wBAgBH,eAAe,iCAAiC,WAAW,SAAQ;;wBAkBnE,SAAS,2BAA2B,WAAW,SAAQ;;;;;wBASvD,OAAO;;UAQN;WACN;WACA;;WAEA;WACA;;WAEA;WACA;;WAEA;WACA;;WAEA;;wBAGK,UAAU,4BAA4B;;;;;;UC3GrC;;WAEN;;UAGM;;WAEN;;WAEA;;;;;WAKA;;WAEA;;WAEA;;;;;;;;;;;wBAkBK,aAAa,mCAAmC,sBAAsB,UAAS,sBAA2B;UC7BzG;;WAEN;;WAEA;;WAEA;;WAEA,SAAS;;;;;;WAMT;;;;;WAKA;;;UAIM;;WAEN;;WAEA;;WAEA;;UAGM,iBAAiB,QAAQ;;WAE/B;WACA;WACA;WACA;WACA;;WAEA;;WAEA;;;;;;wBAOK,UAAU,GAAG,eAAe,KAAK,YAAY,iBAAiB,gBAAgB,UAAS,mBAAwB;;;;;;;;wBAsB/G,aAAa,GAAG,GAC9B,YAAY,KACZ,YAAY,KACZ,YAAY,YAAY,KAAK,YAAY,gBACzC,UAAS,mBACR;;;;;;wBAwBa,qBAAqB,8BAA8B,gCAAgC,UAAS,mBAAwB;;;;;;;wBAUpH,sBACd,mCACA,sBACA,UAAS,mBAAmB,sBAC3B;;wBAoGa,gBAAgB,2BAA2B,UAAS,mBAAwB;;;;;;wBAS5E,kBAAkB,GAChC,eAAe,KACf,UAAU,KAAK,cACf,YAAY,eAAe,gBAC3B,UAAS,mBACR;UAec,2BAA2B;;WAEjC;;WAEA;;;;;;;;;;;;;;;;wBAiBK,oBAAoB,2BAA2B,SAAS,qBAAqB;;KC9QjF;;UAGK;WACN,KAAK;;WAEL;;;UAIM;;;;;WAKN;;WAEA;;;;;;;;;;;;;;;;;;;wBA0MK,UAAU,2BAA2B,UAAS;;;;;;;;wBAqB9C,gBAAgB,qCAAqC;;;;;;wBAwBrD,cAAc,4BAA4B;;;;;;;UCxQzC;;WAEN;;;;;;;;;;;;wBAoBK,WAAW,MAAM,mBAAmB,QAAQ,mBAAmB,gBAAgB,UAAS;;qBCd3F;;KAGD;;KAGA,qBAAqB;;UAGhB;;WAEN;WACA,iBAAiB;;;UAIX;;WAEN;;WAEA;;WAEA;;WAEA,OAAO;;;UAID,4BAA4B;WAClC;;WAEA;;WAEA;;;UAIM,yBAAyB;WAC/B;WACA;;WAEA;;;UAIM,6BAA6B;WACnC;WACA;;;KAIC,oBAAoB,sBAAsB,mBAAmB;;UAGxD;;WAEN;WACA;;WAEA;;WAEA;;;;;WAKA;;;UAIM;;WAEN;;WAEA;;;UAIM;WACN;;WAEA,QAAQ,SAAS,eAAe;;WAEhC,UAAU,SAAS;;WAEnB;;WAEA,SAAS,SAAS;;;KAIjB;WAA4B;WAA4B;;WAA6B;WAA4B,OAAO;;;UAGnH;WACN;;WAEA;;;UAIM,yBAAyB;WAC/B;WACA;WACA;WACA;;;UAIM,uBAAuB;WAC7B;WACA;WACA;WACA;;;UAIM,wBAAwB;WAC9B;WACA;;;KAIC,aAAa,mBAAmB,iBAAiB;;UAG5C;WACN,kBAAkB;WAClB;;;UAIM;;WAEN;;WAEA;;WAEA;;;UAIM,2BAA2B;WACjC;;WAEA;WACA,iBAAiB;WACjB;WACA,gBAAgB;;;UAIV;;WAEN,aAAa;;WAEb;;WAEA;;;UAIM,2BAA2B;WACjC;WACA;;WAEA;WACA,gBAAgB;;WAEhB;;;KAIC,gBAAgB,qBAAqB;;UAGhC;;WAEN;;WAEA;;WAEA;;WAEA;;;UAIM;;WAEN;;WAEA,QAAQ,SAAS,eAAe;;;;;WAKhC,cAAc,SAAS,eAAe,SAAS;;;UAIzC;WACN,eAAe;WACf;WACA,qBAAqB;WACrB,mBAAmB;;WAEnB,mBAAmB;WACnB,iBAAiB;;;UAIX,uBAAuB;WAC7B,iBAAiB;WACjB,gBAAgB;;;UAIV;;WAEN;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA;;;UAIM;;WAEN,OAAO,SAAS,eAAe;;WAE/B;;;;;WAKA;;WAEA;;;UAIM,6BAA6B;;WAEnC;;;UAIM,+BAA+B;;WAErC;;;;;;UAOM;WACN;WACA;WACA;;;;;;;WAOA;;WAEA;;;UAIM,2BAA2B;;WAEjC,IAAI;;;UAIE;WACN;;WAEA,IAAI;WACJ;WACA;;;UAIM;WACN;;WAEA,IAAI;;WAEJ;WACA;;;UAIM;WACN;WACA;;WAEA,MAAM,SAAS,eAAe;WAC9B,gBAAgB;WAChB,iBAAiB;;WAEjB,iBAAiB;WACjB,OAAO;;WAEP;;;UAIM;WACN;;WAEA,cAAc,eAAe;WAC7B;WACA;;;UAIM;WACN;;WAEA,cAAc,eAAe;;WAE7B;WACA;;;UAIM;WACN;WACA;;WAEA,MAAM,SAAS,eAAe;WAC9B,YAAY;WACZ,YAAY;;WAEZ,0BAA0B;WAC1B,iBAAiB;;WAEjB,iBAAiB;WACjB,OAAO;;WAEP;;;wBAuBK,UAAU,WAAW,mBAAmB,QAAQ,SAAS;;;;;;;;;;;wBA4FzD,gBAAgB,OAAO,eAAe,QAAQ,SAAS,eAAe;;;;;wBAQtE,aAAa,QAAQ,KAAK,0BAA0B,kBAAkB;;;;;;;;;;;;wBAqCtE,eAAe,QAAQ,gBAAgB,iBAAiB,yBAAyB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;wBAgPjF,cAAc,QAAQ,gBAAgB,iBAAiB,SAAS,uBAAuB;;;;;;;wBAsBvF,gBAAgB,QAAQ,gBAAgB,iBAAiB,SAAS,yBAAyB;;;;;;;;wBA4B3F,cAAc,QAAQ,KAAK,+BAA+B,0CAA0C;;qBC3yBvG;;UAGI;;WAEN;;WAEA;;;KAIC;WAAkC;WAAmB,QAAQ;;WAA8B;WAAoB,iBAAiB;;;;;;;;;;;;;;;;;;;;;;;;;;wBAgf5H,oBAAoB,iBAAiB;;UC/dpC;;WAEN;;WAEA;;WAEA;;WAEA;;;;;;;;;WASA;;WAEA,2BAA2B;;WAE3B;;WAEA;;WAEA;;;;;WAKA;;;qBAIE;;qBAGA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;wBAoTG,YAAY,MAAM,cAAc,UAAS,qBAA0B;;;;;;wBCvVnE,SAAS,gBAAgB,eAAe;;;;;wBAaxC,cAAc,WAAW,gBAAc;;qBAO1C;;UAGI;WACN;WACA;;;;;;wBAOK,OAAO,WAAW,WAAW,aAAkB;;UAc9C;;WAEN;;WAEA;;WAEA;;;;;;;wBAQK,KAAK,4BAA4B,iBAAe;;;;;;wBAkBhD,mBAAmB,4BAA4B;UAS9C;;WAEN;;WAEA;;WAEA,aAAa;;UAGP;;WAEN;;WAEA;WACA;;;;;;wBAOK,kBAAkB,8BAA8B,6BAA6B,UAAS,qBAA0B;;UAmB/G;;WAEN;;WAEA;;WAEA,aAAa,sBAAsB;;;UAI7B,mCAAmC;;WAEzC;;;;;;;;;wBAuCK,qBAAqB,sBAAsB,sBAAsB,UAAS,8BAAmC;;;;;;wBA+B7G,iBAAiB,gBAAgB,kBAAkB,YAAiB;;UCrPnE;;WAEN;;WAEA;;WAEA;;WAEA;;;;;;wBAOK,WAAW,GAAG,YAAY,KAAK,YAAY,MAAM;;wBCHjD,MAAM;;;;;wBAgBN,SAAS,sBAAsB;;qBAmBlC;;;;;;wBAQG,WAAW,sBAAsB,sBAAsB;;UC1BtD;WACN;WACA;;WAEA;;WAEA;;;;;;;;;;wBAWK,eAAe,2BAA2B,iBAAe;;UAqBxD;;WAEN;;WAEA;;WAEA;;WAEA;;WAEA;;;;;;;;;wBAUK,iBAAiB,2BAA2B,WAAW,iBAAe;;;;;;wBAsCtE,gBAAgB,WAAW;;UAW1B;WACN;WACA;;WAEA;;;;;;;wBAQK,iBAAiB,WAAW,WAAW,iBAAe;;;;;;wBA2BtD,yBAAyB,mBAAmB,WAAW,iBAAe;UCvKrE;;WAEN;;WAEA;;;;;;WAMA;;;;;;wBAgBK,WAAW,2BAA2B,UAAS;;;;;KASnD;;UAGK;;WAEN;WACA;;WAEA;;WAEA;WACA;;WAEA;WACA,OAAO;;;;;;;;wBASF,aAAa,2BAA2B,UAAS;WAA0B;IAAqC;UAW/G;;WAEN;;WAEA;;WAEA;;;UAIM;WACN;WACA;;WAEA;;WAEA;;UAGM;;WAEN;WACA;;WAEA;;WAEA;;WAEA;;WAEA,QAAQ;;WAER;;WAEA;;WAEA;WACA,cAAc;;WAEd;WACA,cAAc;;;;;;;;wBAST,cAAc,2BAA2B,UAAS,iBAAsB;;UA6CvE;WACN;WACA;;;wBASK,MAAM,oBAAoB;;UAQzB;WACN;WACA;WACA;;WAEA;;WAEA,UAAU;;;wBAIL,YAAY,oBAAoB,aAAa;;;;;;;wBChJ7C,UAAU,WAAW;;UAgBpB;;WAEN;;WAEA;;WAEA;;WAEA;;WAEA;;;;;;;;;;;;;;;;wBAiBK,YAAY,SAAS"}
+{"version":3,"file":"index.d.ts","names":[],"sources":["../src/describe.ts","../src/regression.ts","../src/bootstrap.ts","../src/distribution.ts","../src/ridge.ts","../src/response.ts","../src/response-parse.ts","../src/response-fit.ts","../src/tests.ts","../src/agreement.ts","../src/rank.ts","../src/discrete.ts","../src/compare.ts","../src/power.ts","../src/coverage.ts","../src/u-statistic.ts"],"mappings":";;;;;;KAOY;;wBAmBI,OAAO;wBAIP,KAAK;;;;;wBAgBL,GAAG;;;;;;;wBAgBH,eAAe,iCAAiC,WAAW,SAAQ;;wBAkBnE,SAAS,2BAA2B,WAAW,SAAQ;;;;;wBASvD,OAAO;;UAQN;WACN;WACA;;WAEA;WACA;;WAEA;WACA;;WAEA;WACA;;WAEA;;wBAGK,UAAU,4BAA4B;;;;;;UC3GrC;;WAEN;;UAGM;;WAEN;;WAEA;;;;;WAKA;;WAEA;;WAEA;;;;;;;;;;;wBAkBK,aAAa,mCAAmC,sBAAsB,UAAS,sBAA2B;UC7BzG;;WAEN;;WAEA;;WAEA;;WAEA,SAAS;;;;;;WAMT;;;;;WAKA;;;UAIM;;WAEN;;WAEA;;WAEA;;UAGM,iBAAiB,QAAQ;;WAE/B;WACA;WACA;WACA;WACA;;WAEA;;WAEA;;;;;;wBAOK,UAAU,GAAG,eAAe,KAAK,YAAY,iBAAiB,gBAAgB,UAAS,mBAAwB;;;;;;;;wBAsB/G,aAAa,GAAG,GAC9B,YAAY,KACZ,YAAY,KACZ,YAAY,YAAY,KAAK,YAAY,gBACzC,UAAS,mBACR;;;;;;wBAwBa,qBAAqB,8BAA8B,gCAAgC,UAAS,mBAAwB;;;;;;;wBAUpH,sBACd,mCACA,sBACA,UAAS,mBAAmB,sBAC3B;;wBAoGa,gBAAgB,2BAA2B,UAAS,mBAAwB;;;;;;wBAS5E,kBAAkB,GAChC,eAAe,KACf,UAAU,KAAK,cACf,YAAY,eAAe,gBAC3B,UAAS,mBACR;UAec,2BAA2B;;WAEjC;;WAEA;;;;;;;;;;;;;;;;wBAiBK,oBAAoB,2BAA2B,SAAS,qBAAqB;;KC9QjF;;UAGK;WACN,KAAK;;WAEL;;;UAIM;;;;;WAKN;;WAEA;;;;;;;;;;;;;;;;;;;wBA0MK,UAAU,2BAA2B,UAAS;;;;;;;;wBAqB9C,gBAAgB,qCAAqC;;;;;;wBAwBrD,cAAc,4BAA4B;;;;;;;UCxQzC;;WAEN;;;;;;;;;;;;wBAoBK,WAAW,MAAM,mBAAmB,QAAQ,mBAAmB,gBAAgB,UAAS;;qBCd3F;;KAGD;;KAGA,qBAAqB;;UAGhB;;WAEN;WACA,iBAAiB;;;UAIX;;WAEN;;WAEA;;WAEA;;WAEA,OAAO;;;UAID,4BAA4B;WAClC;;WAEA;;WAEA;;;UAIM,yBAAyB;WAC/B;WACA;;WAEA;;;UAIM,6BAA6B;WACnC;WACA;;;KAIC,oBAAoB,sBAAsB,mBAAmB;;UAGxD;;WAEN;WACA;;WAEA;;WAEA;;;;;WAKA;;;UAIM;;WAEN;;WAEA;;;UAIM;WACN;;WAEA,QAAQ,SAAS,eAAe;;WAEhC,UAAU,SAAS;;WAEnB;;WAEA,SAAS,SAAS;;;KAIjB;WAA4B;WAA4B;;WAA6B;WAA4B,OAAO;;;UAGnH;WACN;;WAEA;;;UAIM,yBAAyB;WAC/B;WACA;WACA;WACA;;;UAIM,uBAAuB;WAC7B;WACA;WACA;WACA;;;UAIM,wBAAwB;WAC9B;WACA;;;KAIC,aAAa,mBAAmB,iBAAiB;;UAG5C;WACN,kBAAkB;WAClB;;;UAIM;;WAEN;;WAEA;;WAEA;;;UAIM,2BAA2B;WACjC;;WAEA;WACA,iBAAiB;WACjB;WACA,gBAAgB;;;UAIV;;WAEN,aAAa;;WAEb;;WAEA;;;UAIM,2BAA2B;WACjC;WACA;;WAEA;WACA,gBAAgB;;WAEhB;;;KAIC,gBAAgB,qBAAqB;;UAGhC;;WAEN;;WAEA;;WAEA;;WAEA;;;UAIM;;WAEN;;WAEA,QAAQ,SAAS,eAAe;;;;;WAKhC,cAAc,SAAS,eAAe,SAAS;;;UAIzC;WACN,eAAe;WACf;WACA,qBAAqB;WACrB,mBAAmB;;WAEnB,mBAAmB;WACnB,iBAAiB;;;UAIX,uBAAuB;WAC7B,iBAAiB;WACjB,gBAAgB;;;UAIV;;WAEN;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA;;;UAIM;;WAEN,OAAO,SAAS,eAAe;;WAE/B;;;;;WAKA;;WAEA;;;UAIM,6BAA6B;;WAEnC;;;UAIM,+BAA+B;;WAErC;;;;;;UAOM;WACN;WACA;WACA;;;;;;;WAOA;;WAEA;;;UAIM,2BAA2B;;WAEjC,IAAI;;;UAIE;WACN;;WAEA,IAAI;WACJ;WACA;;;UAIM;WACN;;WAEA,IAAI;;WAEJ;WACA;;;UAIM;WACN;WACA;;WAEA,MAAM,SAAS,eAAe;WAC9B,gBAAgB;WAChB,iBAAiB;;WAEjB,iBAAiB;WACjB,OAAO;;WAEP;;;UAIM;WACN;;WAEA,cAAc,eAAe;WAC7B;WACA;;;UAIM;WACN;;WAEA,cAAc,eAAe;;WAE7B;WACA;;;UAIM;WACN;WACA;;WAEA,MAAM,SAAS,eAAe;WAC9B,YAAY;WACZ,YAAY;;WAEZ,0BAA0B;WAC1B,iBAAiB;;WAEjB,iBAAiB;WACjB,OAAO;;WAEP;;;wBAuBK,UAAU,WAAW,mBAAmB,QAAQ,SAAS;;;;;;;;;;;wBA4FzD,gBAAgB,OAAO,eAAe,QAAQ,SAAS,eAAe;;;;;wBAQtE,aAAa,QAAQ,KAAK,0BAA0B,kBAAkB;;;;;;;;;;;;wBAqCtE,eAAe,QAAQ,gBAAgB,iBAAiB,yBAAyB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;wBAgPjF,cAAc,QAAQ,gBAAgB,iBAAiB,SAAS,uBAAuB;;;;;;;wBAsBvF,gBAAgB,QAAQ,gBAAgB,iBAAiB,SAAS,yBAAyB;;;;;;;;wBA4B3F,cAAc,QAAQ,KAAK,+BAA+B,0CAA0C;;qBC3yBvG;;UAGI;;WAEN;;WAEA;;;KAIC;WAAkC;WAAmB,QAAQ;;WAA8B;WAAoB,iBAAiB;;;;;;;;;;;;;;;;;;;;;;;;;;wBAgf5H,oBAAoB,iBAAiB;;UC/dpC;;WAEN;;WAEA;;WAEA;;WAEA;;;;;;;;;WASA;;WAEA,2BAA2B;;WAE3B;;WAEA;;WAEA;;;;;WAKA;;;qBAIE;;qBAGA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;wBAoTG,YAAY,MAAM,cAAc,UAAS,qBAA0B;;;;;;wBCvVnE,SAAS,gBAAgB,eAAe;;;;;wBAaxC,cAAc,WAAW,gBAAc;;qBAO1C;;UAGI;WACN;WACA;;;;;;wBAOK,OAAO,WAAW,WAAW,aAAkB;;UAc9C;;WAEN;;WAEA;;WAEA;;;;;;;wBAQK,KAAK,4BAA4B,iBAAe;;;;;;wBAkBhD,mBAAmB,4BAA4B;UAS9C;;WAEN;;WAEA;;WAEA,aAAa;;UAGP;;WAEN;;WAEA;WACA;;;;;;wBAOK,kBAAkB,8BAA8B,6BAA6B,UAAS,qBAA0B;;UAmB/G;;WAEN;;WAEA;;WAEA,aAAa,sBAAsB;;;UAI7B,mCAAmC;;WAEzC;;;;;;;;;wBAuCK,qBAAqB,sBAAsB,sBAAsB,UAAS,8BAAmC;;;;;;wBA+B7G,iBAAiB,gBAAgB,kBAAkB,YAAiB;;UCrPnE;;WAEN;;WAEA;;WAEA;;WAEA;;;;;;wBAOK,WAAW,GAAG,YAAY,KAAK,YAAY,MAAM;;wBCHjD,MAAM;;;;;wBAgBN,SAAS,sBAAsB;;qBAmBlC;;;;;;wBAQG,WAAW,sBAAsB,sBAAsB;;UC1BtD;WACN;WACA;;WAEA;;WAEA;;;;;;;;;;wBAWK,eAAe,2BAA2B,iBAAe;;UAqBxD;;WAEN;;WAEA;;WAEA;;WAEA;;WAEA;;;;;;;;;wBAUK,iBAAiB,2BAA2B,WAAW,iBAAe;;;;;;wBAsCtE,gBAAgB,WAAW;;UAW1B;WACN;WACA;;WAEA;;;;;;;wBAQK,iBAAiB,WAAW,WAAW,iBAAe;;KAuB1D;;;;;;;;;;;;;;;wBAgBI,aAAa,WAAW,WAAW,WAAW,MAAM;;;;;;wBA2BpD,yBAAyB,mBAAmB,WAAW,iBAAe;UC9MrE;;WAEN;;WAEA;;;;;;WAMA;;;;;;wBAgBK,WAAW,2BAA2B,UAAS;;;;;KASnD;;UAGK;;WAEN;WACA;;WAEA;;WAEA;WACA;;WAEA;WACA,OAAO;;;;;;;;wBASF,aAAa,2BAA2B,UAAS;WAA0B;IAAqC;UAW/G;;WAEN;;WAEA;;WAEA;;;UAIM;WACN;WACA;;WAEA;;WAEA;;UAGM;;WAEN;WACA;;WAEA;;WAEA;;WAEA;;WAEA,QAAQ;;WAER;;WAEA;;WAEA;WACA,cAAc;;WAEd;WACA,cAAc;;;;;;;;wBAST,cAAc,2BAA2B,UAAS,iBAAsB;;UA6CvE;WACN;WACA;;;wBASK,MAAM,oBAAoB;;UAQzB;WACN;WACA;WACA;;WAEA;;WAEA,UAAU;;;wBAIL,YAAY,oBAAoB,aAAa;;;;;;;wBChJ7C,UAAU,WAAW;;UAgBpB;;WAEN;;WAEA;;WAEA;;WAEA;;WAEA;;;;;;;;;;;;;;;;wBAiBK,YAAY,SAAS;;UC7FpB;;WAEN;;WAEA;;WAEA;;WAEA;;;UAIM;;WAEN;;WAEA;;WAEA;;WAEA;;;KAIC;;UAGK;;WAEN;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA;;WAEA,QAAQ;;WAER;WACA,QAAQ;;;UAIF;;;;;WAKN;;WAEA;;WAEA,gBAAgB;;;;;;;;;;;;;;;;;;;;;;;;wBA6BX,kBAAkB,gBAAgB,gBAAgB,KAAK,cAAc;;KCvFzE;;;;;;;qBAQC;;UAGI;;WAEN;;WAEA;;WAEA,QAAQ;;WAER;;WAEA,kBAAkB,aAAa;;;UAIzB;;WAEN;WACA;WACA;;;UAIM;;WAEN;WACA;WACA;WACA;;WAEA;;WAEA,WAAW;;WAEX,MAAM;;WAEN;;WAEA;;WAEA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;wBAmFK,mBAAmB,2BAA2B,SAAS,oBAAoB"}