Extract statistical results out of textual resources with JATSdecoder's function get.stats() and the table2stats() function from the tableParser package.

Both functions output a data table with the detected standard test statistics (t, Z, F, Χ², U, G², H, Q, BF) and effect sizes (r, R², β, d, ƞ², ω², OR, RR) to enable a check on the recomputability and the consistency of reported p-values.

Note: JATSdecoder and tableParser were designed to analyze reporting practices and summarize specific statistical results within large literature collections. The consistency check is just a side functionality that may result in falsely flagged results for different reasons (e.g., false/non-extractions, corrected p-values).

---

Upload textual resource:

Select a document in docx, pdf, html, xml, cermxml, or htm format and get.stats() will extract all standard results within the full text and captions/footnotes, and table2stats() from within the tabulated content.

---

---

Plain textual input

To gain experience on how the extraction of statistical results works and when it fails, you can paste plain textual reports of results or create a result matrix manually here. The text input will be processed with JATSdecoder's function get.stats() to extract the sticked results within the floating text and transform the detected statistical standard results into a data frame object. If possible, a p-value is computed and compared to the reported p-value, since the option 'checkP' is activated. Enter a plain text snipped here: The extracted sticked results:

The extracted standard results:

---

To reproduce the result on the initial example text, run the follwing code locally:

---

Plain matrix input

The input will be processed with tableParser's function matrix2text() to collapse the tabulated content and detect statistical standard results. First, define the matrix size. Enter tabled content cell-wise (pasting a full table is not possible, sorry!). The collapsed and preprocessed matrix content:

The detected standard results:

---

To reproduce the processing of the initial example table, run the follwing code locally:

---

About get-stats.app

This service is built with RStudio and the shiny package.

---

Get the JATSdecoder and the tableParser package

Both packages are available via CRAN. An installation and usage guide is stored at their github repositories:
https://github.com/ingmarboeschen/JATSdecoder, https://github.com/ingmarboeschen/tableParser

---

How to cite get-stats.app

Böschen, I. (2026). get-stats.app [webapplication]. www.get-stats.app

---

Resources and evaluation papers

Böschen, I. (2026). JATSdecoder: A Metadata and Text Extraction and Manipulation Tool Set. R package.

Böschen, I. (2026). tableParser: Parse Tabled Content to Text Vector and Extract Statistical Standard Results. R package.

Böschen, I. (2026). Extraction of tabulated statistical results with tableParser. arXiv preprint https://doi.org/10.48550/arXiv.2603.19756

Böschen, I. (2024). statcheck is flawed by design and no valid spell checker for statistical results. arXiv preprint https://doi.org/10.48550/arXiv.2408.07948

Böschen, I. (2023). Evaluation of the extraction of methodological study characteristics with JATSdecoder. Scientific Reports 13, 139. https://doi.org/10.1038/s41598-021-98782-3

Böschen, I. (2021). Evaluation of JATSdecoder as an automated text extraction tool for statistical results in scientific reports. Scientific Reports 11, 19525. https://doi.org/10.1038/s41598-021-98782-3

Böschen, I. (2021). Software review: The JATSdecoder package - extract metadata, abstract and sectioned text from NISO-JATS coded XML documents; Insights to PubMed Central’s open access database. Scientometrics. https://doi.org/10.1007/s11192-021-04162-z

---

PDF compilation

By default, CERMINE is used to convert PDF to cermxml files.

Optionally, pdftools can be used to extract plain text from PDF documents.

For the extraction of tables from PDF documents the R package tabulapdf is used.

---

Contact and responsability

If you have any questions or recommendations feel free to contact me:

Dr. Ingmar Böschen
University Hamburg
Institute of Psychology
Research Methods and Statistics
Von-Melle-Park 5
20146 Hamburg
Germany
ingmar.boeschen@uni-hamburg.de

---

Data‑Handling Policy

get-stats.app is a free web service. To process a document, it must be temporarily uploaded to our server. Uploaded files and any data generated from them are used solely for the purpose of providing the requested service to you. We do not store, retain, or reuse your documents or the resulting data tables after processing is complete.

Cookies and Usage Data

get-stats.app does not use cookies or any other form of user‑tracking technology. However, our servers automatically generate logs that record basic technical information. These logs are analyzed in order to help us maintain and improve the performance, security, and reliability of this service.

External links

This website contains links to external sites. Please be aware that we are not responsible for the content, privacy practices, or data‑handling policies of these third‑party websites.

Copyright Responsibility

We do not assume any legal responsibility for the processing of media that is protected by copyright. You are solely responsible for ensuring that any content you upload is used in compliance with applicable copyright laws.