Evaluating the Performances of Missing Data Handling Methods in Ability Estimation From Sparse Data
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Large amounts of missing data could distort item parameter estimation and lead to biased ability estimates in educational assessments. Therefore, missing responses should be handled properly before estimating any parameters. In this study, two Monte Carlo simulation studies were conducted to compare the performance of four methods in handling missing data when estimating ability parameters. The methods were full-information maximum likelihood (FIML), zero replacement, and multiple imputation with chain equations utilizing classification and regression trees (MICE-CART) and random forest imputation (MICE-RFI). For the two imputation methods, missing responses were considered as a valid response category to enhance the accuracy of imputations. Bias, root mean square error, and the correlation between true ability parameters and estimated ability parameters were used to evaluate the accuracy of ability estimates for each method. Results indicated that FIML outperformed the other methods under most conditions. Zero replacement yielded accurate ability estimates when missing proportions were very high. The performances of MICE-CART and MICE-RFI were quite similar but these two methods appeared to be affected differently by the missing data mechanism. As the number of items increased and missing proportions decreased, all the methods performed better. In addition, the information on missing data could improve the performance of MICE-RFI and MICE-CART when the data set is sparse and the missing data mechanism is missing at random.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.034 | 0.193 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it