Predicting the Past: Imputation of Historical Data
Bibliographic record
Abstract
Research using historical data is becoming more common across the social sciences. However, approaches using historical data suffer from a more acute missing data problem than approaches using contemporary data. Complete datasets are required to use many common statistical and machine learning techniques, the majority of which cannot handle missing data. One approach to handling missing data is to impute the missing values. Using the Database of Religious History (DRH), a large historical database, comprised of both quantitative and qualitative data, this research compares the accuracy and bias of 10 imputation methods. k-nearest neighbors (k-NN), missForest, Generalized low rank models (GLRM), Factorial analysis for mixed data (FAMD), DataWig, and five methods implemented in the R package mice (multiple imputation by chained equations). On average, a missForest approach had higher imputation accuracy and among the lowest bias compared to the other methods. The accuracy and bias of different methods implemented in mice were highly variable, highlighting the importance of researchers stating the precise method used for imputation, rather than general phrases such as ‘data were imputed using mice’.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.029 | 0.129 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.003 | 0.006 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.005 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".