{"id":"W4320020468","doi":"10.22148/001c.57764","title":"Theory-Driven Statistics for the Digital Humanities: Presenting Pitfalls and a Practical Guide by the Example of the Reformation","year":2023,"lang":"en","type":"article","venue":"Journal of Cultural Analytics","topic":"Data Analysis with R","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Credibility; Test (biology); Digital humanities; Statistical hypothesis testing; Bridge (graph theory); Protestantism; Logistic regression; Psychology; Data science; Computer science; Epistemology; Sociology; Political science; Statistics; Mathematics; Philosophy; Library science; Machine learning; Law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09985855,0.002484231,0.002760932,0.008120963,0.002555438,0.01228749,0.005660679,0.00873059,0.01007249],"category_scores_gemma":[0.3360718,0.002009732,0.002398024,0.008298953,0.02004618,0.01640166,0.008859033,0.02811421,0.008108797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00387844,"about_ca_system_score_gemma":0.006887257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001949427,"about_ca_topic_score_gemma":0.002488153,"domain_scores_codex":[0.8865472,0.09396466,0.005218316,0.002733828,0.01098009,0.0005559108],"domain_scores_gemma":[0.6015509,0.3529075,0.005321441,0.02468801,0.01394022,0.001591886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004745035,0.0000928211,0.0005029258,0.0007413154,0.00008113762,0.0002966264,0.001028538,0.003041727,0.0005433651,0.7889686,0.1287684,0.07588718],"study_design_scores_gemma":[0.00004333176,0.0000453649,0.0001630375,0.0007547896,0.00001248795,0.0003537197,0.0002473232,0.01020596,0.0003952079,0.8466297,0.1410764,0.00007273985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004049144,0.00846033,0.910154,0.07142575,0.003400659,0.000254756,0.0002824998,0.001255225,0.004361894],"genre_scores_gemma":[0.01214058,0.006535657,0.9520524,0.01764616,0.005351536,0.001990153,0.0003258385,0.001401446,0.002556252],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09985855,"threshold_uncertainty_score":0.5281088,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05892745187518311,"score_gpt":0.3221062691223329,"score_spread":0.2631788172471498,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}