ScintriaEvidence, funding and
writing for research
ToolsHow it checksLearnPricing
Sign inStart free
Sign in

Validation

Every statistic, checked against reference software

Scintria's tests, models and sample sizes are computed by its own code. This page runs that code on data sets it was not tuned on and compares each number with the value established software gives for the same data. If a number stops matching, the automated tests fail and the change cannot ship.

numbers compared
277numbers compared
methods
33methods
match their reference
277 / 277match their reference

Largest relative difference: ⁦1.1 × 10⁻⁶⁩. P-values are required to agree to 6 significant figures, estimates and test statistics to 8 or more, sample sizes exactly. Computed by the code that serves this page.

Comparing groupsTables and epidemiologyCorrelationRegressionSample sizeSurvivalPost hoc comparisonsPaired and repeated measuresMixed modelsSurvey designsRe-run it yourself

Comparing groups

QuantityScintriaReferenceRelative differencematch their reference
Welch t-test (unequal variances)SciPy 1.18.1 ttest_ind(equal_var=False)
t-2.11759408-2.117594082.1 × 10⁻¹⁴Matches
degrees of freedom150.3279686150.3279686identicalMatches
p0.035854974360.035854975523.2 × 10⁻⁸Matches
95% CI, lower-9.170560632-9.1705607068.1 × 10⁻⁹Matches
95% CI, upper-0.3175029629-0.31750288832.3 × 10⁻⁷Matches
t-2.11759408-2.117594082.6 × 10⁻¹⁴Matches
degrees of freedom150.3279686150.32796867.6 × 10⁻¹⁶Matches
p0.035854974360.035854975523.2 × 10⁻⁸Matches
95% CI, lower-9.170560632-9.1705607068.1 × 10⁻⁹Matches
95% CI, upper-0.3175029629-0.31750288832.3 × 10⁻⁷Matches
Mann–Whitney U (ties, continuity correction)SciPy 1.18.1 mannwhitneyu(method="asymptotic")
U37323732identicalMatches
p0.3976426650.397642665identicalMatches
U37323732identicalMatches
p0.3976426650.3976426655.6 × 10⁻¹⁶Matches
One-way ANOVASciPy 1.18.1 f_oneway
F1.8283401351.8283401352.4 × 10⁻¹⁴Matches
p0.16370156250.16370156212.5 × 10⁻⁹Matches
F1.8283401351.8283401352.9 × 10⁻¹⁴Matches
p0.16370156250.16370156212.5 × 10⁻⁹Matches
Kruskal–Wallis (tie correction)SciPy 1.18.1 kruskal
H5.7172451065.717245106identicalMatches
p0.05734769930.05734769931.2 × 10⁻¹⁶Matches
H5.7172451065.7172451067.8 × 10⁻¹⁶Matches
p0.05734769930.05734769938.5 × 10⁻¹⁶Matches

Tables and epidemiology

QuantityScintriaReferenceRelative differencematch their reference
Chi-square test, 3 × 2 tableSciPy 1.18.1 chi2_contingency(correction=False)
χ²19.534934919.5349349identicalMatches
p5.7285246e-55.7285246e-56.6 × 10⁻¹³Matches
χ²19.534934919.53493492.0 × 10⁻¹⁵Matches
p5.7285246e-55.7285246e-56.6 × 10⁻¹³Matches
Fisher's exact test, 2 × 2SciPy 1.18.1 fisher_exact
p (two-sided)0.52162960320.52162960324.8 × 10⁻¹¹Matches
p (two-sided)0.52162960320.52162960324.8 × 10⁻¹¹Matches
Odds ratio, Woolf intervalstatsmodels 0.15.0 Table2x2
odds ratio0.78890600920.7889060092identicalMatches
95% CI, lower0.41860481060.41860481064.0 × 10⁻¹⁶Matches
95% CI, upper1.4867786411.4867786416.0 × 10⁻¹⁶Matches
Risk ratio, Katz log intervalstatsmodels 0.15.0 Table2x2
risk ratio0.84994523550.8499452355identicalMatches
95% CI, lower0.5492827960.549282796identicalMatches
95% CI, upper1.3151821041.315182104identicalMatches
Mantel–Haenszel odds ratio, 3 stratastatsmodels 0.15.0 StratifiedTable
pooled odds ratio0.77294262220.7729426222identicalMatches
95% CI, lower (Robins–Breslow–Greenland)0.40964137950.4096413795identicalMatches
95% CI, upper1.4584471371.458447137identicalMatches
pooled odds ratio0.77294262220.7729426222identicalMatches
95% CI, lower (Robins–Breslow–Greenland)0.40964137950.40964137951.4 × 10⁻¹⁶Matches
95% CI, upper1.4584471371.4584471371.5 × 10⁻¹⁵Matches
Mantel–Haenszel risk ratio, 3 stratastatsmodels 0.15.0 StratifiedTable
pooled risk ratio0.83541529170.8354152917identicalMatches
Breslow–Day test of homogeneitystatsmodels 0.15.0 test_equal_odds(adjust=False)
χ²3.7118437723.711843772identicalMatches
p0.15630877730.15630877731.1 × 10⁻¹³Matches

Correlation

QuantityScintriaReferenceRelative differencematch their reference
Pearson correlationSciPy 1.18.1 pearsonr
r0.43785684140.43785684141.3 × 10⁻¹⁶Matches
p7.9107143e-107.9107147e-104.4 × 10⁻⁸Matches
95% CI, lower (Fisher z)0.31154565390.31154565391.8 × 10⁻¹⁶Matches
95% CI, upper0.54896323840.54896323844.0 × 10⁻¹⁶Matches
r0.43785684140.43785684143.8 × 10⁻¹⁶Matches
p7.9107143e-107.9107147e-104.4 × 10⁻⁸Matches
95% CI, lower (Fisher z)0.31154565390.31154565391.4 × 10⁻¹⁵Matches
95% CI, upper0.54896323840.54896323848.1 × 10⁻¹⁶Matches
Spearman correlation (ties)SciPy 1.18.1 spearmanr
ρ0.07387927050.0738792705identicalMatches
p0.32431142510.32431140586.0 × 10⁻⁸Matches
ρ0.07387927050.07387927051.9 × 10⁻¹⁶Matches
p0.32431142510.32431140586.0 × 10⁻⁸Matches

Regression

QuantityScintriaReferenceRelative differencematch their reference
Linear regressionstatsmodels 0.15.0 OLS
Intercept coefficient98.0398610798.039861072.9 × 10⁻¹⁶Matches
Intercept standard error4.1364153594.1364153594.7 × 10⁻¹⁵Matches
age coefficient0.56497402850.56497402852.5 × 10⁻¹³Matches
age standard error0.088823990650.088823990656.5 × 10⁻¹⁴Matches
arm[T.B] coefficient4.8652840544.8652840548.0 × 10⁻¹⁵Matches
arm[T.B] standard error2.3319735692.3319735699.5 × 10⁻¹⁶Matches
arm[T.C] coefficient1.1138128051.1138128052.8 × 10⁻¹⁵Matches
arm[T.C] standard error2.4853954162.4853954161.3 × 10⁻¹⁵Matches
sex[T.M] coefficient3.2696694623.2696694621.2 × 10⁻¹⁴Matches
sex[T.M] standard error1.9849710381.9849710384.5 × 10⁻¹⁶Matches
R²0.22479900450.22479900451.5 × 10⁻¹⁵Matches
adjusted R²0.20708012460.20708012461.1 × 10⁻¹⁵Matches
F12.6869760312.686976031.7 × 10⁻¹⁵Matches
log-likelihood-717.139907-717.139907identicalMatches
Intercept coefficient98.0398610798.039861074.3 × 10⁻¹⁶Matches
Intercept standard error4.1364153594.1364153591.3 × 10⁻¹⁵Matches
age coefficient0.56497402850.56497402852.4 × 10⁻¹⁵Matches
age standard error0.088823990650.088823990651.6 × 10⁻¹⁶Matches
arm[T.B] coefficient4.8652840544.8652840542.2 × 10⁻¹⁵Matches
arm[T.B] standard error2.3319735692.3319735693.8 × 10⁻¹⁶Matches
arm[T.C] coefficient1.1138128051.1138128055.4 × 10⁻¹⁵Matches
arm[T.C] standard error2.4853954162.4853954162.1 × 10⁻¹⁵Matches
sex[T.M] coefficient3.2696694623.2696694622.4 × 10⁻¹⁵Matches
sex[T.M] standard error1.9849710381.9849710386.7 × 10⁻¹⁶Matches
R²0.22479900450.22479900451.1 × 10⁻¹⁵Matches
adjusted R²0.20708012460.20708012461.2 × 10⁻¹⁵Matches
F12.6869760312.686976034.9 × 10⁻¹⁵Matches
log-likelihood-717.139907-717.1399073.2 × 10⁻¹⁶Matches
Logistic regressionstatsmodels 0.15.0 Logit
Intercept coefficient-3.047973524-3.0479735244.4 × 10⁻¹¹Matches
Intercept standard error0.78075103820.78075103821.8 × 10⁻¹¹Matches
age coefficient0.029129719170.029129719171.4 × 10⁻¹¹Matches
age standard error0.015376477580.015376477588.9 × 10⁻¹²Matches
arm[T.B] coefficient1.6122931911.6122931917.4 × 10⁻¹¹Matches
arm[T.B] standard error0.45262045480.45262045492.8 × 10⁻¹¹Matches
arm[T.C] coefficient2.0193310162.0193310166.0 × 10⁻¹¹Matches
arm[T.C] standard error0.47351500350.47351500352.6 × 10⁻¹¹Matches
sex[T.M] coefficient-0.3398266523-0.33982665231.4 × 10⁻¹¹Matches
sex[T.M] standard error0.34830979420.34830979421.0 × 10⁻¹¹Matches
log-likelihood-99.68891422-99.688914225.7 × 10⁻¹⁶Matches
null log-likelihood-112.3796352-112.37963521.1 × 10⁻¹¹Matches
Intercept coefficient-3.047973524-3.0479735244.4 × 10⁻¹¹Matches
Intercept standard error0.78075103820.78075103824.3 × 10⁻¹⁶Matches
age coefficient0.029129719170.029129719171.4 × 10⁻¹¹Matches
age standard error0.015376477580.015376477584.5 × 10⁻¹⁶Matches
arm[T.B] coefficient1.6122931911.6122931917.4 × 10⁻¹¹Matches
arm[T.B] standard error0.45262045480.45262045484.9 × 10⁻¹⁶Matches
arm[T.C] coefficient2.0193310162.0193310166.0 × 10⁻¹¹Matches
arm[T.C] standard error0.47351500350.47351500352.3 × 10⁻¹⁶Matches
sex[T.M] coefficient-0.3398266523-0.33982665231.4 × 10⁻¹¹Matches
sex[T.M] standard error0.34830979420.34830979424.8 × 10⁻¹⁶Matches
log-likelihood-99.68891422-99.688914221.4 × 10⁻¹⁶Matches
null log-likelihood-112.3796352-112.3796352identicalMatches
Poisson regression, person-time offsetstatsmodels 0.15.0 GLM Poisson
Intercept coefficient-2.62823187-2.628231873.8 × 10⁻¹³Matches
Intercept standard error0.24757532260.24757532264.9 × 10⁻¹¹Matches
arm[T.B] coefficient0.11989576870.11989576874.7 × 10⁻¹³Matches
arm[T.B] standard error0.13024868430.13024868432.3 × 10⁻¹¹Matches
arm[T.C] coefficient-0.2747658976-0.27476589767.5 × 10⁻¹²Matches
arm[T.C] standard error0.15820616210.15820616216.8 × 10⁻¹¹Matches
age coefficient0.010580907240.010580907242.0 × 10⁻¹²Matches
age standard error0.0051534415030.0051534415033.9 × 10⁻¹¹Matches
log-likelihood-273.782855-273.782855identicalMatches
Intercept coefficient-2.62823187-2.628231873.8 × 10⁻¹³Matches
Intercept standard error0.24757532260.24757532262.7 × 10⁻¹⁵Matches
arm[T.B] coefficient0.11989576870.11989576875.0 × 10⁻¹³Matches
arm[T.B] standard error0.13024868430.13024868431.3 × 10⁻¹⁵Matches
arm[T.C] coefficient-0.2747658976-0.27476589767.5 × 10⁻¹²Matches
arm[T.C] standard error0.15820616210.15820616218.8 × 10⁻¹⁶Matches
age coefficient0.010580907240.010580907241.9 × 10⁻¹²Matches
age standard error0.0051534415030.0051534415033.4 × 10⁻¹⁶Matches
log-likelihood-273.782855-273.7828551.5 × 10⁻¹⁵Matches

Sample size

QuantityScintriaReferenceRelative differencematch their reference
Two means (normal approximation)statsmodels 0.15.0 NormalIndPower (rounded up)
n in group 1: Δ = 5, σ = 12, ratio 1:19191identicalMatches
n in group 1: Δ = 5, σ = 12, ratio 1:26868identicalMatches
n in group 1: Δ = 0.4, σ = 1, ratio 1:19999identicalMatches
Two proportions (pooled null variance)statsmodels 0.15.0 samplesize_proportions_2indep_onetail (rounded up)
n in group 1: 0.3 vs 0.45, ratio 1:1163163identicalMatches
n in group 1: 0.3 vs 0.45, ratio 1:2123123identicalMatches
n in group 1: 0.1 vs 0.05, ratio 1:1435435identicalMatches

Survival

QuantityScintriaReferenceRelative differencematch their reference
Kaplan–Meier, 3 arms, heavy tiesstatsmodels 0.15 SurvfuncRight
S(12) in arm A0.48777886310.48777886311.1 × 10⁻¹⁶Matches
S(24) in arm A0.37049044710.3704904471identicalMatches
median survival, arm A1212identicalMatches
S(12) in arm B0.4010905950.4010905951.4 × 10⁻¹⁶Matches
S(24) in arm B0.14560599750.14560599751.9 × 10⁻¹⁶Matches
median survival, arm B99identicalMatches
S(12) in arm C0.34224598930.34224598933.2 × 10⁻¹⁶Matches
S(24) in arm C0.16042780750.16042780753.5 × 10⁻¹⁶Matches
median survival, arm C77identicalMatches
S(12) in arm A0.48777886310.48777886319.1 × 10⁻¹⁶Matches
S(24) in arm A0.37049044710.37049044716.0 × 10⁻¹⁶Matches
median survival, arm A1212identicalMatches
S(12) in arm B0.4010905950.401090595identicalMatches
S(24) in arm B0.14560599750.14560599751.9 × 10⁻¹⁵Matches
median survival, arm B99identicalMatches
S(12) in arm C0.34224598930.34224598936.5 × 10⁻¹⁶Matches
S(24) in arm C0.16042780750.16042780751.7 × 10⁻¹⁶Matches
median survival, arm C77identicalMatches
Log-rank teststatsmodels 0.15 survdiff
χ²10.1261311810.126131181.2 × 10⁻¹⁵Matches
p0.0063261364110.0063261364111.8 × 10⁻¹⁴Matches
χ²10.1261311810.126131182.6 × 10⁻¹⁵Matches
p0.0063261364110.0063261364117.8 × 10⁻¹⁵Matches
Cox proportional hazards (Efron ties)statsmodels 0.15 PHReg
arm_B coefficient0.48454575220.48454575226.9 × 10⁻¹⁶Matches
arm_B standard error0.22527799530.22527799536.2 × 10⁻¹⁶Matches
arm_C coefficient0.72585227730.72585227737.6 × 10⁻¹⁶Matches
arm_C standard error0.25171771480.25171771482.2 × 10⁻¹⁶Matches
sex_M coefficient0.33660144840.33660144841.2 × 10⁻¹⁵Matches
sex_M standard error0.19380048880.19380048881.4 × 10⁻¹⁶Matches
age coefficient0.015297879840.015297879841.7 × 10⁻¹⁵Matches
age standard error0.0068145000830.0068145000837.6 × 10⁻¹⁶Matches
log partial likelihood-464.2144038-464.21440383.7 × 10⁻¹⁶Matches
arm_B coefficient0.48454575220.48454575224.4 × 10⁻¹⁵Matches
arm_B standard error0.22527799530.22527799531.5 × 10⁻¹⁵Matches
arm_C coefficient0.72585227730.72585227732.8 × 10⁻¹⁵Matches
arm_C standard error0.25171771480.25171771488.8 × 10⁻¹⁶Matches
sex_M coefficient0.33660144840.33660144845.1 × 10⁻¹⁵Matches
sex_M standard error0.19380048880.19380048881.7 × 10⁻¹⁵Matches
age coefficient0.015297879840.015297879841.1 × 10⁻¹⁵Matches
age standard error0.0068145000830.0068145000833.8 × 10⁻¹⁶Matches
log partial likelihood-464.2144038-464.21440381.5 × 10⁻¹⁵Matches

Post hoc comparisons

QuantityScintriaReferenceRelative differencematch their reference
Tukey–Kramer, unbalanced groups with unequal variancesstatsmodels 0.15 pairwise_tukeyhsd
adjusted p, G1 vs G20.23315807340.23315807344.2 × 10⁻¹¹Matches
adjusted p, G1 vs G30.0025627491940.0025627491844.1 × 10⁻⁹Matches
adjusted p, G1 vs G40.88943217430.88943217433.0 × 10⁻¹²Matches
adjusted p, G2 vs G30.16275207010.16275207018.1 × 10⁻¹¹Matches
adjusted p, G2 vs G40.58654781380.58654781387.9 × 10⁻¹²Matches
adjusted p, G3 vs G40.010243610540.010243610531.1 × 10⁻⁹Matches
adjusted p, G1 vs G20.23315807340.23315807343.3 × 10⁻¹¹Matches
adjusted p, G1 vs G30.0025627491940.0025627491843.9 × 10⁻⁹Matches
adjusted p, G1 vs G40.88943217430.88943217431.3 × 10⁻¹²Matches
adjusted p, G2 vs G30.16275207010.16275207015.2 × 10⁻¹¹Matches
adjusted p, G2 vs G40.58654781380.58654781387.1 × 10⁻¹²Matches
adjusted p, G3 vs G40.010243610540.010243610539.7 × 10⁻¹⁰Matches
Games–Howell, unbalanced groups with unequal variancespingouin 0.7 pairwise_gameshowell
adjusted p, G1 vs G20.10791053140.10791053142.6 × 10⁻¹¹Matches
adjusted p, G1 vs G32.0947839e-52.0947838e-51.4 × 10⁻⁸Matches
adjusted p, G1 vs G40.3833359340.3833359342.1 × 10⁻¹²Matches
adjusted p, G2 vs G30.30210473810.30210473814.6 × 10⁻¹²Matches
adjusted p, G2 vs G40.49310791620.49310791627.7 × 10⁻¹³Matches
adjusted p, G3 vs G40.00099900853680.00099900853472.1 × 10⁻⁹Matches
Dunn (Holm-adjusted), unbalanced groups with unequal variancesscikit-posthocs posthoc_dunn
adjusted p, G1 vs G20.13967396090.13967396094.8 × 10⁻¹⁵Matches
adjusted p, G1 vs G30.0025074000290.0025074000295.1 × 10⁻¹⁴Matches
adjusted p, G1 vs G40.42539796020.4253979602identicalMatches
adjusted p, G2 vs G30.37375911370.37375911371.2 × 10⁻¹⁵Matches
adjusted p, G2 vs G40.42539796020.4253979602identicalMatches
adjusted p, G3 vs G40.029392137660.029392137665.8 × 10⁻¹⁵Matches

Paired and repeated measures

QuantityScintriaReferenceRelative differencematch their reference
Paired t-testSciPy ttest_rel
t-5.249309053-5.2493090531.7 × 10⁻¹⁶Matches
p2.8868021e-52.8868021e-53.3 × 10⁻¹¹Matches
t-5.249309053-5.2493090536.8 × 10⁻¹⁶Matches
p2.8868021e-52.8868021e-53.3 × 10⁻¹¹Matches
Wilcoxon signed-rank (ties, zero differences)SciPy wilcoxon(correction=True)
p0.00030009124010.00030009124016.2 × 10⁻¹⁴Matches
p0.00030009124010.00030009124015.9 × 10⁻¹⁴Matches
Friedman testSciPy friedmanchisquare
χ²9.3333333339.333333333identicalMatches
p0.025172139980.025172139985.7 × 10⁻¹⁵Matches
χ²9.3333333339.3333333331.7 × 10⁻¹⁵Matches
p0.025172139980.025172139981.4 × 10⁻¹⁴Matches
Repeated-measures ANOVApingouin 0.7 rm_anova
F3.0456197783.0456197781.2 × 10⁻¹⁵Matches
Greenhouse–Geisser ε0.89940301630.89940301633.7 × 10⁻¹⁶Matches
p (Greenhouse–Geisser)0.042910930680.042910930021.5 × 10⁻⁸Matches
F3.0456197783.0456197784.4 × 10⁻¹⁵Matches
McNemar teststatsmodels 0.15 mcnemar(exact=True)
exact p0.16863754390.16863754399.9 × 10⁻¹⁶Matches
χ² p (continuity correction)0.16981050510.16981050512.3 × 10⁻¹³Matches
exact p0.16863754390.16863754392.6 × 10⁻¹⁵Matches
χ² p (continuity correction)0.16981050510.16981050512.1 × 10⁻¹³Matches

Mixed models

QuantityScintriaReferenceRelative differencematch their reference
Linear mixed model (REML): random intercept, 35 unbalanced clustersstatsmodels 0.15 MixedLM; standard errors (X′V⁻¹X)⁻¹ as lme4 and Stata, in NumPy
Intercept coefficient44.0706747544.070674726.4 × 10⁻¹⁰Matches
Intercept standard error2.5008202792.5008192274.2 × 10⁻⁷Matches
time coefficient1.0925446861.0925446661.8 × 10⁻⁸Matches
time standard error0.11086615280.11086616127.6 × 10⁻⁸Matches
arm[T.B] coefficient3.2658832633.2658832918.8 × 10⁻⁹Matches
arm[T.B] standard error1.3927970521.3927964564.3 × 10⁻⁷Matches
age coefficient0.13959584530.13959584583.6 × 10⁻⁹Matches
age standard error0.050687723340.050687701774.3 × 10⁻⁷Matches
REML log-likelihood-516.1068913-516.10689132.5 × 10⁻¹⁴Matches
random-intercept variance14.5283671714.528353049.7 × 10⁻⁷Matches
residual variance8.0905055968.0905070071.7 × 10⁻⁷Matches
Intercept coefficient44.0706747544.070674751.1 × 10⁻¹⁰Matches
Intercept standard error2.5008202792.5008204597.2 × 10⁻⁸Matches
time coefficient1.0925446861.0925446893.1 × 10⁻⁹Matches
time standard error0.11086615280.11086615131.3 × 10⁻⁸Matches
arm[T.B] coefficient3.2658832633.2658832581.5 × 10⁻⁹Matches
arm[T.B] standard error1.3927970521.3927971557.4 × 10⁻⁸Matches
age coefficient0.13959584530.13959584536.1 × 10⁻¹⁰Matches
age standard error0.050687723340.050687727047.3 × 10⁻⁸Matches
REML log-likelihood-516.1068913-516.10689136.6 × 10⁻¹⁵Matches
random-intercept variance14.5283671714.52836961.7 × 10⁻⁷Matches
residual variance8.0905055968.0905053543.0 × 10⁻⁸Matches
Linear mixed model (REML): random intercept and slope, 35 unbalanced clustersstatsmodels 0.15 MixedLM; standard errors (X′V⁻¹X)⁻¹ as lme4 and Stata, in NumPy
Intercept coefficient44.4419321844.441931591.3 × 10⁻⁸Matches
Intercept standard error2.2329909232.2329899624.3 × 10⁻⁷Matches
time coefficient1.0020081351.002008261.3 × 10⁻⁷Matches
time standard error0.20061362340.20061341611.0 × 10⁻⁶Matches
arm[T.B] coefficient3.2735789213.2735788322.7 × 10⁻⁸Matches
arm[T.B] standard error1.2469922791.2469917364.4 × 10⁻⁷Matches
age coefficient0.13353859380.13353860538.6 × 10⁻⁸Matches
age standard error0.0452746210.045274601394.3 × 10⁻⁷Matches
REML log-likelihood-497.8908023-497.89080231.7 × 10⁻¹³Matches
random-intercept variance11.6803868911.6803741.1 × 10⁻⁶Matches
residual variance5.2056443075.2056479497.0 × 10⁻⁷Matches
Intercept coefficient44.4419321844.441931935.4 × 10⁻⁹Matches
Intercept standard error2.2329909232.2329906151.4 × 10⁻⁷Matches
time coefficient1.0020081351.0020080221.1 × 10⁻⁷Matches
time standard error0.20061362340.20061373065.3 × 10⁻⁷Matches
arm[T.B] coefficient3.2735789213.2735789281.9 × 10⁻⁹Matches
arm[T.B] standard error1.2469922791.2469920931.5 × 10⁻⁷Matches
age coefficient0.13353859380.13353860176.0 × 10⁻⁸Matches
age standard error0.0452746210.045274614281.5 × 10⁻⁷Matches
REML log-likelihood-497.8908023-497.89080231.5 × 10⁻¹⁴Matches
random-intercept variance11.6803868911.68038671.6 × 10⁻⁸Matches
residual variance5.2056443075.2056434011.7 × 10⁻⁷Matches

Survey designs

QuantityScintriaReferenceRelative differencematch their reference
Weighted linear model, 4 strata of 2–5 clustersLinearisation formulas as R survey / Stata svy, in NumPy
(Intercept) coefficient20.3963861720.396386171.7 × 10⁻¹⁴Matches
(Intercept) standard error2.422021542.422021545.3 × 10⁻¹⁵Matches
x coefficient0.48708087940.48708087941.7 × 10⁻¹⁴Matches
x standard error0.048910989980.048910989982.1 × 10⁻¹⁵Matches
g_b coefficient3.4717127753.4717127751.3 × 10⁻¹⁶Matches
g_b standard error0.93800960360.93800960361.1 × 10⁻¹⁴Matches
g_c coefficient-2.507923016-2.5079230161.4 × 10⁻¹⁵Matches
g_c standard error0.69043106830.69043106832.0 × 10⁻¹⁴Matches
(Intercept) coefficient20.3963861720.396386173.8 × 10⁻¹⁵Matches
(Intercept) standard error2.422021542.422021542.0 × 10⁻¹⁴Matches
x coefficient0.48708087940.48708087943.5 × 10⁻¹⁵Matches
x standard error0.048910989980.048910989982.0 × 10⁻¹⁴Matches
g_b coefficient3.4717127753.4717127752.6 × 10⁻¹⁶Matches
g_b standard error0.93800960360.93800960368.3 × 10⁻¹⁶Matches
g_c coefficient-2.507923016-2.5079230161.9 × 10⁻¹⁵Matches
g_c standard error0.69043106830.69043106833.5 × 10⁻¹⁵Matches
Weighted meanLinearisation formulas as R survey / Stata svy, in NumPy
mean39.6041804439.604180445.4 × 10⁻¹⁶Matches
standard error0.83148034370.83148034376.7 × 10⁻¹⁶Matches
mean39.6041804439.604180441.3 × 10⁻¹⁵Matches
standard error0.83148034370.83148034371.1 × 10⁻¹⁵Matches

Re-run it yourself

The data sets and reference values are published. Load them in R, Stata, SPSS or Python and compare. The script that produced the core reference values is included.

  • core.csvCore data set: tests, tables, correlation, regression (180 rows)
  • ref-core.jsonReference values for the core data set (SciPy, statsmodels)
  • core_reference.pyPython script that made the core data and its reference values
  • surv.csvSurvival data: 3 arms, heavy ties
  • posthoc.csvGroups for post hoc comparisons
  • mixed.csvClustered data for mixed models
  • survey.csvSurvey data: weights, strata and clusters
  • ref.jsonReference values for the survival, post hoc, paired, mixed-model and survey checks
  • ref-r.jsonReference values from R (base R, survival, survey, lme4)
  • r_reference.RR script that produced the R reference values

What this shows, and what it does not

  • R 4.3 was run here: base R, survival, survey and lme4 give the same numbers as Scintria for every check R can make directly (124 of them), shown as separate rows. Stata is commercial software and was not run; its mixed-model standard errors and survey linearisation use the same formulas as lme4 and R's survey package, which are checked here.
  • The data are simulated from fixed seeds and include awkward features on purpose: ties, zero differences, unbalanced groups with unequal variances, sparse strata and random slopes.
  • Agreement with reference software shows that the arithmetic is right. It does not show that a method suits your study; Scintria states each test's assumptions beside the result.

Use the same code on your data

Open Data analysisCalculate a sample size
Scintria

Evidence, funding, statistics and writing for researchers, checked in code.

Appearance

Product

  • Funding search
  • Research writer
  • Tools
  • PhD corner
  • Postdoc corner
  • Pricing

Learn

  • Learn
  • Research method guides
  • Getting around Scintria
  • Sample size calculator
  • Power calculator
  • Study design chooser

Trust and legal

  • How Scintria checks its work
  • Validation
  • Sources and coverage
  • Privacy Policy
  • Cookie policy
  • Terms of Use
  • Refund Policy

Contact

  • Sign in
  • Create account
  • About
  • hello@scintria.com
© 2026 ScintriaScintria provides research assistance. It is not medical, statistical, regulatory or legal advice, and it does not decide eligibility for any funder.