{"id":"W4410908240","doi":"10.1007/s10182-025-00527-4","title":"Using penalized-distance likelihood functions to analyze high-dimensional sparse/non-sparse data","year":2025,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mathematics; Sparse approximation; Sparse matrix; Maximum likelihood; Lasso (programming language); Statistics; Computer science; Pattern recognition (psychology); Artificial intelligence; Algorithm; Gaussian; Physics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00108169,0.0003733162,0.001087418,0.0007340346,0.000216994,0.0001015761,0.0007028444,0.00009903529,0.001681695],"category_scores_gemma":[0.005472068,0.000335503,0.000118784,0.004369725,0.0002563655,0.0003072275,0.0005566875,0.0003568221,0.00006567621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001663233,"about_ca_system_score_gemma":0.0001832693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005341793,"about_ca_topic_score_gemma":0.003138462,"domain_scores_codex":[0.9960856,0.0003733312,0.001087082,0.001142216,0.0006161423,0.000695599],"domain_scores_gemma":[0.9934456,0.004423361,0.0001971011,0.001347174,0.0002700474,0.0003167064],"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":[0.0002889407,0.0006439368,0.01820717,0.0002126727,0.001047043,0.0001134495,0.00006484202,0.009331205,0.0001526344,0.9010068,0.003907801,0.06502358],"study_design_scores_gemma":[0.0007456694,0.00009328943,0.01926017,0.000260674,0.002864816,0.00000262913,0.0002413533,0.3589647,0.00002485894,0.6119826,0.004920505,0.000638801],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004141358,0.0002943007,0.9893227,0.0002372716,0.000221375,0.0002694786,0.003472057,0.00004788661,0.001993526],"genre_scores_gemma":[0.2463808,0.00004432571,0.7525713,0.0002572022,0.00004877909,0.00003091938,0.0002934076,0.00002002906,0.0003531344],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3496335,"threshold_uncertainty_score":0.9999097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08169404633416365,"score_gpt":0.4307900450660689,"score_spread":0.3490959987319052,"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."}}