{"id":"W2208611758","doi":"10.5539/ies.v9n1p161","title":"Developing a Numerical Ability Test for Students of Education in Jordan: An Application of Item Response Theory","year":2015,"lang":"en","type":"article","venue":"International Education Studies","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Cronbach's alpha; Item response theory; Test (biology); Psychology; Item analysis; Test validity; Mathematics education; Class (philosophy); Reliability (semiconductor); Psychometrics; Measure (data warehouse); Mathematics; Statistics; Developmental psychology; Computer science; Artificial intelligence","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":[0.006579001,0.0005373519,0.0006758896,0.002300039,0.0005340559,0.0009876258,0.001049954,0.0008387611,0.00366547],"category_scores_gemma":[0.0178741,0.0002401851,0.0007609802,0.001896017,0.0004747022,0.00151929,0.001249275,0.001000831,0.00111484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005616556,"about_ca_system_score_gemma":0.002659577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009965431,"about_ca_topic_score_gemma":0.001615555,"domain_scores_codex":[0.9960333,0.001833774,0.0006406073,0.0002210441,0.001099318,0.0001721375],"domain_scores_gemma":[0.9920873,0.003410088,0.001049197,0.000331952,0.002774474,0.0003469153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004570553,0.002242015,0.4494445,0.0006942275,0.0001915034,0.0003226226,0.002972139,0.004421488,0.006393136,0.002789138,0.00656602,0.5235063],"study_design_scores_gemma":[0.0005334843,0.00478195,0.8920451,0.0006947257,0.0001606813,0.001101169,0.01031656,0.03874452,0.01131497,0.009910367,0.03020889,0.0001877115],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9347742,0.0004631641,0.04524153,0.001213996,0.0001507743,0.004841268,0.001257231,0.0002848303,0.011773],"genre_scores_gemma":[0.8299729,0.0005692307,0.1575664,0.0003680831,0.0000746135,0.005336456,0.002146628,0.00003886329,0.003926759],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.006579001,"threshold_uncertainty_score":0.0347935,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09618380232866415,"score_gpt":0.5034121013097561,"score_spread":0.407228298981092,"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."}}