# Imputation on OpinionQA MNAR 140 opinion variables (W26 to W82) American Trends Panel Source: [Imputation on OpinionQA MNAR 140 opinion variables (W26 to W82) American Trends Panel]() Collection index: [llms.txt]() Data updated: 2026-06-09T10:45:32.886Z Evaluation of imputation models on the American Trends Panel dataset (OpinionQA subset W26 to W82), specifically assessing performance under Missing Not At Random (MNAR) conditions, using Median Absolute Error, Median Interval Width, and Coverage Rate. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Imputation | | Dataset (including any stated split) | OpinionQA MNAR 140 opinion variables (W26 to W82) American Trends Panel | | Metric | Median Absolute Error | | Unit | SCALAR | | Direction | Lower is better | | Results loaded | 36 of 36 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Median Absolute Error](): Lower is better; unit: SCALAR. - [Median Interval Width](): Lower is better; unit: SCALAR. - [Coverage Rate](): Higher is better; unit: PERCENT. - [Absolute Error IQR](): Lower is better; unit: SCALAR. - [Interval Width IQR](): Lower is better; unit: SCALAR. ## Recorded results | Method | Median Absolute Error | Result date | Report paper | | --- | --- | --- | --- | | Full Data | 0.026 | Not recorded | 6a279e5d90966ade919bfa89 | | Full Data | 0.026 | Not recorded | 6a279e5d90966ade919bfa89 | | gpt-oss-120b | 0.048 | Not recorded | 6a279e5d90966ade919bfa89 | | gpt-oss-120b | 0.048 | Not recorded | 6a279e5d90966ade919bfa89 | | gpt-oss-120b | 0.049 | Not recorded | 6a279e5d90966ade919bfa89 | | gpt-oss-120b | 0.049 | Not recorded | 6a279e5d90966ade919bfa89 | | gpt-oss-120b | 0.049 | Not recorded | 6a279e5d90966ade919bfa89 | | gpt-oss-120b | 0.049 | Not recorded | 6a279e5d90966ade919bfa89 | | Qwen3-30B-A3B-Inst. | 0.05 | Not recorded | 6a279e5d90966ade919bfa89 | | Qwen3-30B-A3B-Inst. | 0.05 | Not recorded | 6a279e5d90966ade919bfa89 | | Qwen3-30B-A3B-Think. | 0.051 | Not recorded | 6a279e5d90966ade919bfa89 | | Qwen3-30B-A3B-Inst. | 0.052 | Not recorded | 6a279e5d90966ade919bfa89 | | Qwen3-30B-A3B-Inst. | 0.052 | Not recorded | 6a279e5d90966ade919bfa89 | | Qwen3-8B | 0.053 | Not recorded | 6a279e5d90966ade919bfa89 | | Most Similar Embed. | 0.055 | Not recorded | 6a279e5d90966ade919bfa89 | | GLM-4.7-Flash | 0.055 | Not recorded | 6a279e5d90966ade919bfa89 | | Most Similar Embed. | 0.055 | Not recorded | 6a279e5d90966ade919bfa89 | | Qwen3-8B | 0.056 | Not recorded | 6a279e5d90966ade919bfa89 | | Qwen3-30B-A3B-Think. | 0.056 | Not recorded | 6a279e5d90966ade919bfa89 | | Mode Imputation | 0.058 | Not recorded | 6a279e5d90966ade919bfa89 | | GLM-4.7-Flash | 0.06 | Not recorded | 6a279e5d90966ade919bfa89 | | Complete Case | 0.062 | Not recorded | 6a279e5d90966ade919bfa89 | | Complete Case | 0.062 | Not recorded | 6a279e5d90966ade919bfa89 | | Olmo-3-7B-Instruct | 0.064 | Not recorded | 6a279e5d90966ade919bfa89 | | Qwen3-30B-A3B-Inst. | 0.065 | Not recorded | 6a279e5d90966ade919bfa89 | | Qwen3-30B-A3B-Inst. | 0.065 | Not recorded | 6a279e5d90966ade919bfa89 | | Olmo-3-7B-Instruct | 0.066 | Not recorded | 6a279e5d90966ade919bfa89 | | MICE PMM | 0.068 | Not recorded | 6a279e5d90966ade919bfa89 | | MICE PMM | 0.068 | Not recorded | 6a279e5d90966ade919bfa89 | | Qwen3-8B | 0.069 | Not recorded | 6a279e5d90966ade919bfa89 | | GLM-4.7-Flash | 0.074 | Not recorded | 6a279e5d90966ade919bfa89 | | Qwen3-30B-A3B-Think. | 0.075 | Not recorded | 6a279e5d90966ade919bfa89 | | Random Sample | 0.075 | Not recorded | 6a279e5d90966ade919bfa89 | | Olmo-3-7B-Instruct | 0.082 | Not recorded | 6a279e5d90966ade919bfa89 | | MICE Forest | 0.085 | Not recorded | 6a279e5d90966ade919bfa89 | | MICE Forest | 0.085 | Not recorded | 6a279e5d90966ade919bfa89 | ### Full Data Median Absolute Error: 0.026. Result ID: 6a27eec9fbc373592c257e40. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Full Data Median Absolute Error: 0.026. Result ID: 6a27eec9fbc373592c257e7d. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### gpt-oss-120b Median Absolute Error: 0.048. Result ID: 6a27eec9fbc373592c257e47. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of in-context examples":"100"}. This record does not assert independent reproduction. ### gpt-oss-120b Median Absolute Error: 0.048. Result ID: 6a27eec9fbc373592c257e8f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"in-context examples":"100"}. This record does not assert independent reproduction. ### gpt-oss-120b Median Absolute Error: 0.049. Result ID: 6a27eec9fbc373592c257e43. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of in-context examples":"0"}. This record does not assert independent reproduction. ### gpt-oss-120b Median Absolute Error: 0.049. Result ID: 6a27eec9fbc373592c257e45. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of in-context examples":"10"}. This record does not assert independent reproduction. ### gpt-oss-120b Median Absolute Error: 0.049. Result ID: 6a27eec9fbc373592c257e83. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"Zero-Shot"}. This record does not assert independent reproduction. ### gpt-oss-120b Median Absolute Error: 0.049. Result ID: 6a27eec9fbc373592c257e89. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"in-context examples":"10"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B-Inst. Median Absolute Error: 0.05. Result ID: 6a27eec9fbc373592c257e46. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of in-context examples":"100"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B-Inst. Median Absolute Error: 0.05. Result ID: 6a27eec9fbc373592c257e8b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"in-context examples":"100"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B-Think. Median Absolute Error: 0.051. Result ID: 6a27eec9fbc373592c257e88. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"in-context examples":"10"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B-Inst. Median Absolute Error: 0.052. Result ID: 6a27eec9fbc373592c257e44. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of in-context examples":"10"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B-Inst. Median Absolute Error: 0.052. Result ID: 6a27eec9fbc373592c257e85. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"in-context examples":"10"}. This record does not assert independent reproduction. ### Qwen3-8B Median Absolute Error: 0.053. Result ID: 6a27eec9fbc373592c257e90. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"in-context examples":"100"}. This record does not assert independent reproduction. ### Most Similar Embed. Median Absolute Error: 0.055. Result ID: 6a27eec9fbc373592c257e48. [Reporting paper]() Recorded evaluation configuration: {"n":"10"}. This record does not assert independent reproduction. ### GLM-4.7-Flash Median Absolute Error: 0.055. Result ID: 6a27eec9fbc373592c257e87. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"in-context examples":"10"}. This record does not assert independent reproduction. ### Most Similar Embed. Median Absolute Error: 0.055. Result ID: 6a27eec9fbc373592c257e91. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-8B Median Absolute Error: 0.056. Result ID: 6a27eec9fbc373592c257e8a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"in-context examples":"10"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B-Think. Median Absolute Error: 0.056. Result ID: 6a27eec9fbc373592c257e8e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"in-context examples":"100"}. This record does not assert independent reproduction. ### Mode Imputation Median Absolute Error: 0.058. Result ID: 6a27eec9fbc373592c257e94. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GLM-4.7-Flash Median Absolute Error: 0.06. Result ID: 6a27eec9fbc373592c257e8d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"in-context examples":"100"}. This record does not assert independent reproduction. ### Complete Case Median Absolute Error: 0.062. Result ID: 6a27eec9fbc373592c257e41. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Complete Case Median Absolute Error: 0.062. Result ID: 6a27eec9fbc373592c257e7e. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Olmo-3-7B-Instruct Median Absolute Error: 0.064. Result ID: 6a27eec9fbc373592c257e86. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"in-context examples":"10"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B-Inst. Median Absolute Error: 0.065. Result ID: 6a27eec9fbc373592c257e42. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Number of in-context examples":"0"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B-Inst. Median Absolute Error: 0.065. Result ID: 6a27eec9fbc373592c257e7f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"Zero-Shot"}. This record does not assert independent reproduction. ### Olmo-3-7B-Instruct Median Absolute Error: 0.066. Result ID: 6a27eec9fbc373592c257e8c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"in-context examples":"100"}. This record does not assert independent reproduction. ### MICE PMM Median Absolute Error: 0.068. Result ID: 6a27eec9fbc373592c257e49. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MICE PMM Median Absolute Error: 0.068. Result ID: 6a27eec9fbc373592c257e92. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Qwen3-8B Median Absolute Error: 0.069. Result ID: 6a27eec9fbc373592c257e84. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"Zero-Shot"}. This record does not assert independent reproduction. ### GLM-4.7-Flash Median Absolute Error: 0.074. Result ID: 6a27eec9fbc373592c257e81. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"Zero-Shot"}. This record does not assert independent reproduction. ### Qwen3-30B-A3B-Think. Median Absolute Error: 0.075. Result ID: 6a27eec9fbc373592c257e82. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"Zero-Shot"}. This record does not assert independent reproduction. ### Random Sample Median Absolute Error: 0.075. Result ID: 6a27eec9fbc373592c257e95. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Olmo-3-7B-Instruct Median Absolute Error: 0.082. Result ID: 6a27eec9fbc373592c257e80. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"mode":"Zero-Shot"}. This record does not assert independent reproduction. ### MICE Forest Median Absolute Error: 0.085. Result ID: 6a27eec9fbc373592c257e4a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MICE Forest Median Absolute Error: 0.085. Result ID: 6a27eec9fbc373592c257e93. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.