The Theil–Sen Slope for High-Stakes Decisions from Progress Monitoring

Abstract

ABSTRACT: More and more, schools are considering the use of progress monitoring data for high-stakes decisions such as special education eligibility, program changes to more restrictive environments, and major changes in educational goals. Those high-stakes types of data-based decisions will need methodological defensibility. Current practice for summarizing progress monitoring data is to use a hand-fit trend lines (for practitioner use) or linear regression (for research). This study critically examines both approaches and compares them to a new nonparametric slope called the Theil–Sen. A field test with 372 published data series compared hand-fit, linear regression, and Theil–Sen slopes against evaluative criteria of power and precision, meeting data assumptions, and agreement with visual judgments. Results indicate promise for Theil–Sen slope in defensible high-stakes decision making.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 39 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.