Interpreting functional analysis outcomes using automated nonparametric statistical analysis
A free web app gives an 83% accurate, bias-free statistical call on functional-analysis graphs in seconds.
01Research in Context
What this study did
Hall et al. (2020) tested a free web tool called ANSA. It reads FA graphs and gives a stats-based answer in seconds.
The team fed 65 published FA graphs into ANSA. They checked if its call matched the proven function.
What they found
ANSA got it right 83% of the time. That beat experts who only eyeballed the same graphs.
The tool never gets tired or biased. It just runs the numbers and spits out a clear call.
How this fits with other research
Kranak et al. (2021) ran the same check on real clinic charts. They hit the same 83% mark, so the finding holds outside the lab.
Ohan et al. (2015) looked at a different shortcut: trial-based FA in regular classrooms. Both studies want faster, cleaner answers for busy staff.
Virues-Ortega et al. (2011) tested caregiver reports instead of live FA. Their 74% match is lower than ANSA’s 83%, so stats beat surveys here.
Why it matters
You can paste any FA graph into ANSA and get a bias-free call before the team meeting ends. Use it when you need a second set of eyes or when staff disagree on the trend. It’s free, takes seconds, and now has two studies showing 83% accuracy.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Upload your last FA graph to ANSA and compare its call with your visual check
02At a glance
03Original abstract
Current methods employed to interpret functional analysis data include visual analysis and post-hoc visual inspection (PHVI). However, these methods may be biased by dataset complexity, hand calculations, and rater experience. We examined whether an automated approach using nonparametric rank-based statistics could increase the accuracy and efficiency of functional analysis data interpretation. We applied Automated Nonparametric Statistical Analysis (ANSA) to a sample of 65 published functional analyses for which additional experimental evidence was available to verify behavior function. Results showed that exact behavior function agreement between ANSA and the publications authors was 83.1%, exact agreement between ANSA and PHVI was 75.4%, and exact agreement across all 3 methods was 64.6%. These preliminary findings suggest that ANSA has the potential to support the data interpretation process. A web application that incorporates the calculations and rules utilized by ANSA is accessible at https://ansa.shinyapps.io/ansa/.
Journal of Applied Behavior Analysis, 2020 · doi:10.1002/jaba.689