Assessment & Research

Machine learning-based brief version of the Caregiver-Teacher Report Form for preschoolers.

Lin et al. (2023) · Research in developmental disabilities 2023
★ The Verdict

A 36-item machine-learning C-TRF gives the same scores as the 100-item version and frees up two-thirds of your paperwork time.

✓ Read this if BCBAs who screen or re-evaluate preschoolers in daycare, Head Start, or public pre-K.
✗ Skip if Clinicians working only with school-age kids or adults.

01Research in Context

01

What this study did

The team fed 100-item Caregiver-Teacher Report Forms into a machine-learning model.

They asked the computer to pick the smallest set of items that still gave the same scores.

The model spit out a 36-item version using records from the preschoolers.

02

What they found

The short form matched the full form almost perfectly.

R-squared values ran from 0.86 to 0.96 across all problem scales.

In plain words, the 36-item quiz gives you the same numbers in a large share less time.

03

How this fits with other research

Nikolov et al. (2009) did the same trick with the QABF. They squeezed 80 items down to 15 and kept the five behavior functions intact.

Chen et al. (2001) built a 24-item short form of the Adaptive Behavior Scale that also tracked the full scale with near-perfect correlation.

Suhrheinrich et al. (2020) took a different road: they swapped trial-by-trial fidelity coding for a 3-point checklist and still hit a large share agreement. All four studies show the same theme—smart trimming saves time without losing accuracy.

04

Why it matters

You now have a 10-minute C-TRF that yields the same clinical picture. Use it during hectic preschool screenings, re-evaluations, or when teachers simply won’t fill out 100 questions. Less paperwork, same data—no trade-off.

Free CEUs

Want CEUs on This Topic?

The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.

Join Free →
→ Action — try this Monday

Print the 36-item C-TRF-ML and swap it in for your next teacher packet—then clock the time you save.

02At a glance

Intervention
not applicable
Design
other
Sample size
363
Population
not specified
Finding
strongly positive
Magnitude
large

03Original abstract

BACKGROUND: The Caregiver-Teacher Report Form of the Child Behavior Checklist for Ages 1½-5 (C-TRF) is a widely used checklist to identify emotional and behavioral problems in preschoolers. However, the 100-item C-TRF restricts its utility. AIMS: This study aimed to develop a machine learning-based short-form of the C-TRF (C-TRF-ML). METHODS AND PROCEDURES: Three steps were executed. First, we split the data into three datasets in a ratio of 3:1:1 for training, validation, and cross-validation, respectively. Second, we selected a shortened item set and trained a scoring algorithm using joint learning for classification and regression using the training dataset. Then, we evaluated the similarity of scores between the C-TRF-ML and the C-TRF by r-squared and weighted kappa values using the validation dataset. Third, we cross-validated the C-TRF-ML by calculating the r-squared and weighted kappa values using the cross-validation dataset. OUTCOMES AND RESULTS: Data of 363 children were analyzed. Thirty-six items of the C-TRF were retained. The r-squared values of C-TRF-ML scores were 0.86-0.96 in the cross-validation dataset. Weighted kappa values of the syndrome/problem grading were 0.72-0.94 in the cross-validation dataset. CONCLUSIONS AND IMPLICATIONS: The C-TRF-ML had about 60 % fewer items than the C-TRF but yielded comparable scores with the C-TRF.

Research in developmental disabilities, 2023 · doi:10.1016/j.ridd.2023.104437