Changes in version 0.99.2 - Updated R-universe installation documentation. Changes in version 0.99.1 Initial public development version. This is a pre-release: the API may change before 1.0.0. The largest changes are expected in the Category C methods (signal-difference regions, peak evidence, calibration transfer risk, kinetic discrimination, experiment fragility, drift uncertainty, detection reliability, and uncertainty-origin attribution), where the interface is still settling. Version pinning supports reproducible analyses. Added 32 user-facing functions, grouped into three categories. Category A: core statistics - sci_describe - descriptive statistics with explicit biological vs. technical replicate handling - sci_compare - two-group comparisons (Welch, Student, paired, permutation, Wilcoxon) with effect sizes - sci_anova - ANOVA and Welch alternatives with effect sizes - sci_regression - linear, weighted, and robust regression with diagnostics - sci_correlation - correlation analysis with confidence intervals (Pearson, Spearman, Kendall) - sci_normality - normality assessment with multiple tests - sci_outliers - outlier diagnostics (IQR, MAD, Grubbs, Dixon) - sci_power - power and sample-size calculation for common designs - sci_effect_size - standardized effect sizes (Cohen's d, Hedges' g) with CIs - sci_bootstrap - bootstrap resampling with percentile, BCa, and normal CIs Category B: domain methods - adaptive_baseline - asymmetric least squares / lowess baseline estimation for spectra - adaptive_smoothing - edge-preserving smoothing for noisy signals - batch_effect_quantify - quantify batch-to-batch variance via mixed-effects decomposition - calibration_compare - compare two calibration curves via ANCOVA - curve_similarity - similarity between two curves sampled on possibly different grids - drift_correct_stat - drift correction with uncertainty quantification - kinetic_model_compare - compare candidate kinetic models via likelihood-ratio tests - noise_characterize - summarise residual variation and autocorrelation - parameter_uncertainty - propagate parameter uncertainty to derived quantities - replicate_decompose - variance-component decomposition for nested and crossed replicates - robust_lod - limits of detection and quantification (Currie-style) - spectral_change_test - test for differences across complete spectra - timepoint_optimize - optimise sampling timepoints for a planned experiment - weighted_peak_fit - weighted multi-peak fitting (Gaussian/Lorentzian) Category C: advanced diagnostics - signal_difference_regions - statistical identification of regions where two groups of curves differ (simultaneous max-t band with Westfall-Young permutation) - peak_evidence - frequentist evidence assessment for signal peaks (likelihood ratio + permutation FPP) - calibration_transfer_risk - statistical framework for calibration transfer risk (TPE, OOD flag, parametric bootstrap) - kinetic_discrimination - discriminability of competing kinetic models via Monte Carlo simulation - experiment_fragility - quantitative experimental fragility assessment (leave-one-replicate-out, outlier, baseline, model, noise) - drift_uncertainty - statistical attribution of variance to instrument drift (linear/polynomial/exponential drift models) - detection_reliability - reliability analysis for analytical detection (PD/FNR/FPR curves with bootstrap CIs) - uncertainty_origin - stage-wise uncertainty attribution via Shapley value for correlated sources Infrastructure - S3 class system for results: crossstatr_result parent class with print, summary, tidy, as.data.frame methods - Internal validation helpers (.assert_*) and numeric helpers (.safe_sd, .ci_t, .cohens_d, .mcse_p, etc.) - testthat (3rd edition) test suite covering input validation, numerical correctness, and edge cases - MIT license, inst/CITATION, inst/extdata/ for example data