Bibliographic record
Abstract
How do you do a distributional analysis? Cross-tabs? This chapter will cover how to conduct a factor by factor analysis. It will also demonstrate how preliminary distributional analyses can pinpoint difficulties in research design and/or data anomalies. It will focus on techniques for resolving data, computational and linguistic problems. Now that you have some basic understanding of how the variable rule program works, let us now turn to the step-by-step procedures involved in performing an analysis. I will begin with distributional analysis. FUNDAMENTALS All too often when students first set out to do a distributional analysis, they do it the wrong way round. In order to do it right, distinguish between the roles of the dependent variable and the independent (explanatory) factors. Recall that in every variation analysis the focus is the tendency for the dependent variable to occur in a series of cross-cutting independent factors: ‘The essence of the analysis is an assessment of how the choice process is influenced by the different factors whose specific combinations define these contexts’ (Sankoff 1988c: 985). THE WRONG WAY TO DO DISTRIBUTIONAL ANALYSIS Many students make the mistake of reporting how the variants are distributed across the explanatory factors. Consider the results file for variable (t,d) in (1).
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 | 0.009 | 0.048 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.007 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.008 | 0.008 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.072 | 0.027 |
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".