Simulations indicate PSW cognitive assessment would improve classification of response by only about 5-10 students per 1,000 in the best case¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2016 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Data simulation showed adding the strongest PSW predictor (r2 .828 to .838) reduced expected misclassifications among 1,000 observations only modestly; the median eta squared improvement across 33 contrasts was .001. → Miciak Jeremy 2016

Evidence¶

Miciak Jeremy 2016¶

Miciak Jeremy, Williams Jacob L., Taylor W. Pat, Cirino Paul T., Fletcher Jack M., Vaughn Sharon. (2016). Do Processing Patterns of Strengths and Weaknesses Predict Differential Treatment Response? Journal of Educational Psychology, 108(6), 898-909. https://doi.org/10.1037/edu0000096

q2 · i? · associational · r2

Simulation of two correlated datasets of 1,000 observations comparing misclassification at mean and 25th-percentile cut points with and without the PSW dimension; the best case improved classification for roughly 5-10 of 1,000 students.

"Data simulations indicated that the most optimistic scenario would result in only a small improvement in predictive accuracy (approximately 5–10 students for every 1,000 students assessed). Most comparisons resulted in no statistically significant or educationally meaningful improvement in prediction."

Discussion¶

Related Claims¶

• Simulation evidence cited in the article indicates PSW methods have consistently low positive predictive values despite high negative predictive values — related
• The XBA and C/DM PSW methods show chance-level agreement (kappa = -.10) in identifying LD among fourth graders with reading comprehension deficits — related
• XBA LD status does not predict posttest reading outcomes beyond pretest performance in decoding, fluency, or comprehension — related