Markdown Editor
에디터 열기

응용 통계 분석가 키트

분석 계획, 검정력, A/B 테스트 계획, 데이터 정제, 탐색적 분석, 변환, 비율 검정과 t-검정, 비모수 및 재표본 방법, 계수 회귀, ARIMA 예측, 모형 보고서.

1단계

문제 정의

  1. Statistical Analysis Plan Template (Statistics, Thesis or Project)

    전체

    Statistical analysis plan for a thesis or project: estimands, hypotheses, sample size, primary model, pre-set assumption fallbacks, missing data, multiplicity, sensitivity, deviations log

    ICH E9(R1) estimand framework (name); Gamble et al. (2017) SAP content; Holm (1979); Rubin (1987); Borm et al. (2007)

  2. Power Analysis and Sample Size Template (Statistics, R and Python)

    전체

    Power analysis and sample size worksheet: t-tests, proportions, ANOVA, correlation, regression, simulation power, sensitivity table and justification sentence

    Cohen (1988); Lakens (2022) sample size justification; Hoenig and Heisey (2001); pwr 1.3.0 and statsmodels 0.15.0

  3. A/B Test Plan Template

    표준

    A/B test design – hypothesis, sizing, decision rule

2단계

데이터

  1. Data Cleaning Log Template (Statistics, Missing Data, R and Python)

    전체

    Reproducible data cleaning with an audit log: duplicates, range and consistency checks, pre-set outlier policy, missing data mechanisms (MCAR, MAR, MNAR), imputation choices, R and Python code

    Rubin (1976); Little (1988); Little and Rubin (2019); van Buuren and Groothuis-Oudshoorn (2011); Tukey (1977); NIST/SEMATECH e-Handbook

  2. Exploratory Data Analysis Report Template (Statistics, R and Python)

    전체

    Exploratory data analysis report – centre, spread, shape, frequency tables, Vega-Lite charts, outlier screen and questions for confirmatory analysis, with R and Python code

    Tukey (1977); NIST/SEMATECH e-Handbook ch. 1 (EDA); Hyndman and Fan (1996); GAISE College Report (ASA 2016, name)

  3. Data Transformations Method Card Template (Statistics, R and Python)

    전체

    Data transformations method card – log, sqrt, Box-Cox, Yeo-Johnson, logit, z-scores, centring and ranks, percent-change interpretation and smearing back-transformation, with R and Python

    Box and Cox (1964); Yeo and Johnson (2000); Duan (1983); Warton and Hui (2011); NIST/SEMATECH e-Handbook (Box-Cox)
3단계

방법과 패턴

  1. Proportion Tests Method Card Template (Statistics, R and Python)

    전체

    One- and two-proportion tests (exact binomial, z, 2x2 chi-square link), Wilson and Newcombe intervals, risk difference, relative risk and odds ratio, A/B test framing

    Wilson (1927); Clopper and Pearson (1934); Yates (1934); Newcombe (1998); Agresti and Coull (1998); NIST/SEMATECH e-Handbook; APA JARS-Quant (name)

  2. t-Tests Method Card Template (Statistics, R and Python)

    전체

    One-sample, Welch and pooled independent, and paired t-tests with hand calculation, R and Python code, Hedges' g and APA-style reporting

    Student (1908); Welch (1947); Satterthwaite (1946); Hedges (1981); NIST/SEMATECH e-Handbook 1.3.5.3; APA JARS-Quant (name)

  3. Nonparametric Rank Tests Method Card Template (Statistics, R and Python)

    전체

    Mann-Whitney U, Wilcoxon signed-rank, sign test, Kruskal-Wallis with Dunn (Holm) and Friedman, with R vs Python defaults, ties and effect sizes

    Wilcoxon (1945); Mann and Whitney (1947); Kruskal and Wallis (1952); Friedman (1937); Dunn (1964); Holm (1979); NIST/SEMATECH e-Handbook; APA JARS-Quant (name)

  4. Bootstrap and Permutation Methods Card Template (Statistics, R and Python)

    전체

    Bootstrap percentile, basic and BCa intervals, exact and Monte Carlo permutation tests, simulation checks and seeds, in R and Python

    Efron (1979); Efron and Tibshirani (1993); Davison and Hinkley (1997); NIST/SEMATECH e-Handbook; R boot and SciPy documentation

  5. Count Regression Method Card Template (Statistics, Poisson and NB, R and Python)

    전체

    Poisson and negative binomial regression for counts: rate ratios, offsets for exposure, overdispersion check, quasi-Poisson, theta vs alpha, zero-inflation note, with R and Python

    Nelder and Wedderburn (1972); Lawless (1987); Lambert (1992); Cameron and Trivedi (2013); Venables and Ripley (2002) MASS; NIST/SEMATECH e-Handbook (public domain)

  6. Time Series and ARIMA Method Card Template (Statistics, R and Python)

    전체

    Decomposition, ADF and KPSS, ACF and PACF, seasonal ARIMA identification, Ljung-Box checks, forecasts with intervals and hold-out accuracy, in R and Python

    Box and Jenkins (1970); Dickey and Fuller (1979); Kwiatkowski et al. (1992); Ljung and Box (1978); NIST/SEMATECH e-Handbook 6.4; R forecast and statsmodels documentation
4단계

문서화

  1. Regression Model Report Template (Statistics, R and Python)

    전체

    Working report for one regression model: purpose and estimand, data and sample, variables, specification, diagnostics checklist with evidence, results, model comparison, validation, sensitivity, limitations, reproducibility and sign-off

    Shmueli (2010) explain vs predict; Harrell (2015); TRIPOD (Collins et al. 2015) and TRIPOD+AI (Collins et al. 2024), names only; APA JARS-Quant (name); Akaike (1974); Schwarz (1978)

  2. Statistical Analysis Report Template (Statistics, Thesis or Client)

    전체

    Complete statistical analysis report for a thesis results chapter or client: plain-language summary, methods, descriptives, main analyses, assumption checks, sensitivity, limitations, reproducibility appendix, reviewer checklist

    APA JARS-Quant (name); ASA Statement on p-values (Wasserstein and Lazar 2016); Welch (1947); Mann and Whitney (1947); Cook (1977)

  3. Reporting Statistical Results Template (Statistics, APA Style, R and Python)

    전체

    Writing statistical results: complete-result anatomy, number formatting, model sentences for t, ANOVA, chi-square, correlation, regression, logistic, nonparametric and mixed models, tables, figures, checklist

    APA Publication Manual 7th ed. (name); APA JARS-Quant (name); ASA Statement on P-Values (Wasserstein and Lazar 2016)