Comparing corrosion control treatments using a robust Bayesian generalized additive model
Bibliographic record
Abstract
Pipe loop studies are used routinely to evaluate corrosion control treatment, and updated regulatory guidance will ensure that they remain an important tool for water quality management. But they are inherently complex and the data they generate are difficult to analyze: non-linear time-trends, non-detects, extreme values, and autocorrelation are common features, the latter due to repeatedly measuring the effluent from test pipes. Popular statistical tests, such as the Student t or rank-sum tests, are often inadequate descriptions of the data. Here, we propose an approach to statistical analysis of pipe loop data that accommodates many of these difficult-to-model characteristics: a robust Bayesian generalized additive model with continuous-time autoregressive errors. Our model facilitates corrosion control treatment comparisons without the need for imputing non-detects or special handling of outliers. It is well-suited to describing nonlinear trends without overfitting, and it accounts for reduced information content due to autocorrelation. We demonstrate the model using an example pipe loop study comprising four years of data, multiple pipe configurations, and multiple orthophosphate dosing protocols. We compare the experimental treatments, finding that an initially high dose of orthophosphate (2 mg P L-1) that is subsequently lowered (0.75 mg P L-1) can yield lower lead release than an intermediate dose (1 mg P L-1) in the long term. We also find that—consistent with previous work—galvanic corrosion yields relatively high particulate lead release, especially at higher orthophosphate doses. An advantage of the Bayesian approach we adopt here is that it yields the full posterior distribution of all parameters and all quantities derived from those parameters, including the model predictions. This means that analysts can construct any comparison that is relevant to the study goals, without the need to rely on a particular statistical test.
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 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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".