EIR® had a positive, substantively important but statistically non-significant effect on first-grade reading comprehension¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r2 · q3 · i2 medium
Currency · newest study 2008 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i2 On the Gates-MacGinitie reading test, the EIR® effect size was 0.47 (improvement index +18 percentile points), not statistically significant but meeting the WWC substantively-important threshold of 0.25. → Early Intervention in Reading® 2008 q3 i2 The WWC-calculated Gates-MacGinitie effect size was 0.47, favoring EIR® but not statistically significant. → Early Intervention in Reading® 2008 (2)

Evidence¶

Early Intervention in Reading® 2008¶

Early Intervention in Reading®. (2008). WWC Intervention Report, What Works Clearinghouse, U.S. Department of Education. http://www.earlyinterventioninreading.com

q3 · i2 · causal · r2

In the Taylor et al. (1991) randomized controlled trial, comprehension was measured with the Gates-MacGinitie reading test. The report notes the effect was "not statistically significant" but met the WWC substantively-important criterion of an effect size of at least 0.25.

"The study authors did not find statistically significant effects of EIR®, but the effect was positive and large enough to be considered substantively important according to WWC criteria (that is, an effect size greater than or equal to 0.25)."

Early Intervention in Reading® 2008 (2)¶

Early Intervention in Reading®. (2008). WWC Intervention Report, What Works Clearinghouse, U.S. Department of Education. http://www.earlyinterventioninreading.com

q3 · i2 · causal · r2

WWC calculations for the Taylor et al. (1991) randomized controlled trial (Appendix A3.2) report a Gates-MacGinitie mean difference of 3.62 favoring EIR®, an "effect size" of 0.47, marked ns (not statistically significant), with an improvement index of +18.

"Gates-MacGinitie Reading Test Grade 1 12/57 20.76 (8.03) 17.14 (6.97) 3.62 0.47 ns +18"

Discussion¶

Related Claims¶

• Greenwood et al. (1993) reported a statistically significant CWPT effect on CTBS-Reading, but the WWC-corrected analysis was not statistically significant — related
• Failure Free Reading shows potentially positive effects on reading comprehension — related
• VIP shows potentially positive effects on reading achievement for fifth-grade English language learners (effect size 0.50, not statistically significant) — related
• EIR® produced statistically significant positive effects on first-grade alphabetics outcomes (segmentation and blending, vowel sounds) — related
• The evidence base for EIR® is small: only one of seven reviewed studies met WWC evidence standards — related
• The effect on SAT math scores was positive but not statistically significant, though large enough to be substantively important (effect size at least 0.25) — related
• Reading Go! showed positive but not statistically significant effects on reading comprehension — related
• The guide treats an effect size of +0.25 or higher as substantively important, equivalent to raising performance at least 10 percentile points — a broader claim this one bears on