moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses module

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.BasicStats(n: int, x_mean: float, S: float, S_x_mean: float, S_biased: float)

Bases: object

Clause 5. Estimate of the measured value and standard deviation.

n

Number of measurement results.

Type:

int

x_mean

Arithmetic mean value.

Type:

float

S

Standard deviation S.

Type:

float

S_x_mean

Standard deviation of the arithmetic mean.

Type:

float

S_biased

Biased standard deviation S*.

Type:

float

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.CompositeCriterion1Result(d: float, d_low: float, d_high: float, passed: bool)

Bases: object

Clause 7. Confidence limits for random error.

Clause 7.3 applies for 15 < n <= 50. Criterion 1, Appendix B.

d

Computed ratio d~.

Type:

float

d_low

Lower quantile of the distribution.

Type:

float

d_high

Upper quantile of the distribution.

Type:

float

passed

True if the criterion is satisfied.

Type:

bool

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.CompositeCriterion2Result(threshold: float, exceed_count: int, allowed_exceed_count: int, p_value_table: float, z_value: float, passed: bool)

Bases: object

Clause 7. Confidence limits for random error.

Clause 7.3 applies for 15 < n <= 50. Criterion 2, Appendix B.

threshold

Threshold value z_p/2 * S.

Type:

float

exceed_count

Number of values abs(x_i - x_mean) above the threshold.

Type:

int

allowed_exceed_count

Allowed count m from Table B.2.

Type:

int

p_value_table

Probability value from Table B.2.

Type:

float

z_value

Upper quantile from Table B.3.

Type:

float

passed

True if the criterion is satisfied.

Type:

bool

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.CompositeNormalityResult(n: int, x_mean: float, S: float, S_biased: float, criterion_1: CompositeCriterion1Result, criterion_2: CompositeCriterion2Result, passed: bool)

Bases: object

Clause 7. Confidence limits for random error.

Clause 7.3 applies for 15 < n <= 50. Result of the normality hypothesis test for measurement results.

n

Number of measurement results.

Type:

int

x_mean

Arithmetic mean value.

Type:

float

S

Standard deviation S.

Type:

float

S_biased

Biased standard deviation S*.

Type:

float

criterion_1

Result of Criterion 1 from Appendix B.

Type:

CompositeCriterion1Result

criterion_2

Result of Criterion 2 from Appendix B.

Type:

CompositeCriterion2Result

passed

True if both criteria are satisfied.

Type:

bool

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.GrubbsCheck(n: int, x_mean: float, S: float, x_min: float, x_max: float, g_min: float, g_max: float, g_crit: float)

Bases: object

Clause 6. Detection and elimination of gross errors.

n

Number of measurement results.

Type:

int

x_mean

Arithmetic mean value.

Type:

float

S

Standard deviation S.

Type:

float

x_min

Minimum measurement result.

Type:

float

x_max

Maximum measurement result.

Type:

float

g_min

Computed Grubbs criterion for the minimum value.

Type:

float

g_max

Computed Grubbs criterion for the maximum value.

Type:

float

g_crit

Theoretical Grubbs criterion.

Type:

float

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.GrubbsResult(cleaned_values: list, removed: list, checks: list[GrubbsCheck])

Bases: object

Clause 6. Detection and elimination of gross errors.

cleaned_values

Filtered measurement results.

Type:

list

removed

Removed measurement results.

Type:

list

checks

Results for each Grubbs test iteration.

Type:

list[GrubbsCheck]

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.MisesSmirnovNormalityResult(n: int, x_mean: float, S: float, n_omega2: float, a_value: float, alpha: float, threshold: float, passed: bool, rows: list[MisesSmirnovRow])

Bases: object

Appendix G. Result of the omega^2 normality test.

n

Number of measurement results.

Type:

int

x_mean

Arithmetic mean.

Type:

float

S

Standard deviation of the measurement results.

Type:

float

n_omega2

Computed statistic nOmega^2.

Type:

float

a_value

Function value a(x) from Table G.3.

Type:

float

alpha

Significance level.

Type:

float

threshold

Threshold equal to 1 - alpha.

Type:

float

passed

True if the normality hypothesis is not rejected.

Type:

bool

rows

Intermediate calculation rows.

Type:

list[MisesSmirnovRow]

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.MisesSmirnovRow(j: int, x_j: float, a_j: float, F_xj: float, ln_F_xj: float, one_minus_a_j: float, one_minus_F_xj: float, ln_one_minus_F_xj: float, term: float)

Bases: object

Appendix G. Intermediate values for the omega^2 criterion.

j

Index of the ordered measurement result.

Type:

int

x_j

Measurement result value.

Type:

float

a_j

Coefficient (2j - 1) / (2n).

Type:

float

F_xj

Theoretical normal distribution value F(x_j).

Type:

float

ln_F_xj

ln(F(x_j)).

Type:

float

one_minus_a_j

Value 1 - a_j.

Type:

float

one_minus_F_xj

Value 1 - F(x_j).

Type:

float

ln_one_minus_F_xj

ln(1 - F(x_j)).

Type:

float

term

Summand in formula (G.1).

Type:

float

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.PearsonInterval(index: int, left: float, right: float, center: float, observed: int, expected: float, y: float, contribution: float)

Bases: object

Clause 7. Confidence limits for random error.

Clause 7.4 applies for n > 50.

index

Interval index i.

Type:

int

left

Left interval boundary.

Type:

float

right

Right interval boundary.

Type:

float

center

Interval center x_i0.

Type:

float

observed

Observed count of measurements in the interval.

Type:

int

expected

Expected count of measurements in the interval.

Type:

float

y

Probability of falling into interval i.

Type:

float

contribution

Computed Pearson criterion contribution.

Type:

float

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.PearsonNormalityResult(n: int, r: int, h: float, x_mean: float, S: float, chi2_value: float, df: int, alpha: float, chi2_low: float, chi2_high: float, passed: bool, intervals: list[PearsonInterval])

Bases: object

Clause 7. Confidence limits for random error.

Clause 7.4 applies for n > 50. Result of the Pearson normality hypothesis test.

n

Number of measurement results.

Type:

int

r

Number of grouping intervals.

Type:

int

h

Grouping interval width.

Type:

float

x_mean

Arithmetic mean value.

Type:

float

S

Standard deviation S.

Type:

float

chi2_value

Computed Pearson criterion value.

Type:

float

df

Degrees of freedom.

Type:

int

alpha

Significance level.

Type:

float

chi2_low

Lower critical bound for chi^2.

Type:

float

chi2_high

Upper critical bound for chi^2.

Type:

float

passed

True if the normality hypothesis is not rejected.

Type:

bool

intervals

Grouping intervals and Pearson parameters.

Type:

list[PearsonInterval]

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.RandomErrorConfidenceResult(n: int, p_conf: float, df: int, x_mean: float, S: float, S_x_mean: float, t_value: float, delta: float)

Bases: object

Clause 7.5. Confidence limits for the random error.

n

Number of measurement results.

Type:

int

p_conf

Confidence probability P.

Type:

float

df

Degrees of freedom n - 1.

Type:

int

x_mean

Arithmetic mean value.

Type:

float

S

Standard deviation S.

Type:

float

S_x_mean

Standard deviation of the arithmetic mean.

Type:

float

t_value

Student coefficient.

Type:

float

delta

Confidence limit of the random error without sign.

Type:

float

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.RoundedMeasurementResult(x_raw: float, delta_raw: float, p_conf: float, x_rounded: float, delta_rounded: float, delta_significant_digits: int, decimal_places: int, notation: str)

Bases: object

Clause 10. Presentation of the estimate of the measured value.

Appendix E. Rounding rules.

x_raw

Original estimate of the measured value.

Type:

float

delta_raw

Original unsigned error.

Type:

float

p_conf

Confidence probability.

Type:

float

x_rounded

Rounded estimate of the measured value.

Type:

float

delta_rounded

Rounded error.

Type:

float

delta_significant_digits

Number of significant digits retained in the error.

Type:

int

decimal_places

Number of decimal places in the final notation.

Type:

int

notation

Final formatted result, for example x ± Delta, P=....

Type:

str

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.SystematicComponent(name: str, theta: float, influence_coefficient: float = 1.0)

Bases: object

Clause 8. Confidence limits for the unexcluded systematic error.

One systematic error component.

name

Component name.

Type:

str

theta

Unsigned limit of the component.

Type:

float

influence_coefficient

Influence coefficient dX/dY. If not specified, it is assumed to be 1.

Type:

float

effective_theta

Effective component limit equal to abs(influence_coefficient) * abs(theta).

Type:

float

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.SystematicErrorResult(m: int, p_conf: float, k: float, theta_sum: float, method: str, components: list[SystematicComponent])

Bases: object

Clause 8. Confidence limits for the unexcluded systematic error.

m

Number of systematic components.

Type:

int

p_conf

Confidence probability.

Type:

float

k

Composition coefficient.

Type:

float

theta_sum

Final unsigned systematic error limit.

Type:

float

method

Calculation method: none, sum, or rss.

Type:

str

components

List of components.

Type:

list[SystematicComponent]

class moncenterlib.stats.stats_gost_R_8_736_2011.dataclasses.TotalErrorResult(p_conf: float, x_mean: float, delta_random: float, theta_systematic: float, s_x_mean: float, s_theta: float, s_total: float, k_total: float, delta_total: float, theta_mode: str, theta_k: float | None = None)

Bases: object

Clause 9. Confidence limits for the error in the estimate of the measured value.

p_conf

Confidence probability.

Type:

float

x_mean

Estimate of the measured value.

Type:

float

delta_random

Confidence limit of the random error.

Type:

float

theta_systematic

Systematic error limit.

Type:

float

s_x_mean

Standard deviation of the arithmetic mean.

Type:

float

s_theta

Standard deviation of the systematic error.

Type:

float

s_total

Total standard deviation of the estimate.

Type:

float

k_total

Coefficient K from formula (12).

Type:

float

delta_total

Final confidence limit of the total error.

Type:

float

theta_mode

Systematic error interpretation mode: plain for formula (14), or confidence for formula (15).

Type:

str

theta_k

Coefficient k from Clause 8, used only in confidence mode.

Type:

float | None