Effectiveness of Cognitive Tutor Algebra I at Scale
Pane, John F.; Griffin, Beth Ann; McCaffrey, Daniel F.; Karam, Rita (2014). Educational Evaluation and Policy Analysis, v36 n2 p127-144 Jun 2014. Retrieved from: https://eric.ed.gov/?id=EJ1024233
-
, grades8-12
Cognitive Tutor Algebra I Intervention Report - Secondary Mathematics
Review Details
Reviewed: May 2026
- Randomized Controlled Trial
- Meets WWC standards without reservations
This review may not reflect the full body of research evidence for this intervention.
Evidence Tier rating based solely on this study. This intervention may achieve a higher tier when combined with the full body of evidence.
Please see the WWC summary of evidence for Cognitive Tutor Algebra I.
Findings
|
Outcome measure |
Comparison | Period | Sample |
Intervention mean |
Comparison mean |
Significant? |
Improvement index |
Evidence tier |
|---|---|---|---|---|---|---|---|---|
|
CTB/McGraw-Hill Algebra Proficiency Exam |
Cognitive Tutor Algebra I vs. Business as usual |
1 Year |
Grades 8–12;
|
-0.02 |
0.03 |
No |
-- | |
|
CTB/McGraw-Hill Algebra Proficiency Exam |
Cognitive Tutor Algebra I vs. Business as usual |
2 Years |
Grades 8–12;
|
0.08 |
-0.08 |
No |
-- |
Evidence Tier rating based solely on this study. This intervention may achieve a higher tier when combined with the full body of evidence.
Sample Characteristics
Characteristics of study sample as reported by study author.
-
10% English language learners -
Rural, Suburban, Urban
-
- B
- A
- C
- D
- E
- F
- G
- I
- H
- J
- K
- L
- P
- M
- N
- O
- Q
- R
- S
- V
- U
- T
- W
- X
- Z
- Y
- a
- h
- i
- b
- d
- e
- f
- c
- g
- j
- k
- l
- m
- n
- o
- p
- q
- r
- s
- t
- u
- v
- x
- w
- y
Alabama, Connecticut, Kentucky, Louisiana, Michigan, New Jersey, Texas
-
Race Black 36% White 46%
Study Details
Setting
The study took place in 51 school districts across seven states, including urban districts in Alabama, Connecticut, New Jersey, and Texas; suburban districts in Michigan; and rural districts in Kentucky and Louisiana.
Study sample
On average, White non-Hispanic students comprised 41 - 52% of the sample in each condition, while Black students, the next largest group, comprised 30-41%. Free- or reduced-price lunch status was 38 - 69% of the sample in each condition. Finally, English Language Learner (ELL) status was around 10% in each sample condition.
Intervention Group
Cognitive Tutor® Algebra I was implemented for 2 consecutive school years. The curriculum involved teacher-directed classroom instruction 3 days a week and computer-guided instruction 2 days a week. The software was available for students to use during class and other times during the day. It was self-paced, and students’ progress was based on mastery of the material. During the classroom lessons, students were exposed to topics such as solving linear equations, mathematical modeling with linear and quadratic expressions, problem solving using proportion reasoning, and analyzing data and making predictions. To apply these concepts, students completed worksheets and other activities and engaged in a variety of problem solving strategies. An implementation study indicated that teachers generally implemented all components of Cognitive Tutor® Algebra I, but sometimes emphasized the components differently from the publisher recommendations.
Comparison Group
Students in the comparison condition received each school’s existing Algebra I curriculum, which included curricula published by Glencoe, McDougal Littell, and Prentice Hall.
Support for implementation
Teachers received 4 days of training throughout the study. During a 3-day session prior to the school year, teachers were introduced to the curriculum, software, and tools, and provided instruction on connections between the curriculum and software and how to use the data to inform instruction. Teachers received a fourth day of training during the school year, at which time professional development staff observed classrooms, offered recommendations, and helped with any problems the teachers had. In addition, teachers received training materials, an implementation guide, and a book of resources and assessments.
Additional Sources
In the case of multiple manuscripts that report on one study, the WWC selects one manuscript as the primary citation and lists other manuscripts that describe the study as additional sources.
-
Pane, J. F., Griffin, B. A., McCaffrey, D. F., & Karam, R. (2014). Addendum to effectiveness of Cognitive Tutor Algebra I at scale (Working Paper WR-1050-DEIES) (high school experiment). Santa Monica, CA: RAND Corporation.
-
Pane, J. F., Griffin, B. A., McCaffrey, D. F., Karam, R., Daugherty, L., & Phillips, A. (2013). Does an algebra course with tutoring software improve student learning? (high school experiment). Santa Monica, CA: RAND Corporation.
-
Sales, A. C., & Pane, J. F. (2015, June). Exploring causal mechanisms in a randomized effectiveness trial of the Cognitive Tutor (high school experiment). Paper presented at the 8th International Conference on Educational Data Mining, Madrid, Spain.
Grant Competition
Review Details
Reviewed: May 2026
- Grant Competition (findings for Cognitive Tutor Algebra I)
- Randomized Controlled Trial
- Meets WWC standards without reservations
This review may not reflect the full body of research evidence for this intervention.
Evidence Tier rating based solely on this study. This intervention may achieve a higher tier when combined with the full body of evidence.
Findings
|
Outcome measure |
Comparison | Period | Sample |
Intervention mean |
Comparison mean |
Significant? |
Improvement index |
Evidence tier |
|---|---|---|---|---|---|---|---|---|
|
CTB/McGraw-Hill Algebra Proficiency Exam |
Cognitive Tutor Algebra I vs. Business as usual |
Cohort 1 only ;
|
N/A |
N/A |
No |
-- | ||
|
CTB/McGraw-Hill Algebra Proficiency Exam |
Cognitive Tutor Algebra I vs. Business as usual |
Cohort 2 only;
|
N/A |
N/A |
No |
-- |
Evidence Tier rating based solely on this study. This intervention may achieve a higher tier when combined with the full body of evidence.
Sample Characteristics
Characteristics of study sample as reported by study author.
-
10% English language learners -
Rural, Suburban, Urban
-
- B
- A
- C
- D
- E
- F
- G
- I
- H
- J
- K
- L
- P
- M
- N
- O
- Q
- R
- S
- V
- U
- T
- W
- X
- Z
- Y
- a
- h
- i
- b
- d
- e
- f
- c
- g
- j
- k
- l
- m
- n
- o
- p
- q
- r
- s
- t
- u
- v
- x
- w
- y
Alabama, Connecticut, Kentucky, Louisiana, Michigan, New Jersey, Texas
-
Race Black 30%
Study Details
Setting
The setting of the study was 74 middle schools in 51 school districts in seven states, which varied by urban, suburban, and rural contexts. Both public and parochial schools were included in the study from city districts in Texas, Connecticut, New Jersey, and Alabama; suburban districts near Detroit, Michigan, primarily rural districts in Kentucky, and districts throughout Louisiana.
Study sample
99 percent of study participants were in 8th grade. The intervention and comparison groups did not show differences in racial/ethnic composition according to Table 1, p. 133. 41% of the middle school intervention group were Caucasian and 44% of the middle school comparison group were Caucasian. 30% of both groups were African-American. 27% of the intervention group were Latino and 24% of the comparison group were Latino. The groups did not vary by the proportion eligible for free and reduced price lunch (69% of the intervention group and 63% of the comparison group). 10% of both groups were classified as English Learners. The proficiency rates on state assessments in Reading 2004, Reading 2005, and Mathematics 2005 were different between the middle school intervention and comparison groups, according to Table 1, p. 133. The proficiency rates between middle school intervention and comparison groups did not vary on Reading 2006, Mathematics 2004, and Mathematics 2006.
Intervention Group
The Cognitive Tutor Algebra I intervention combines the use of algebra textbook materials with an automated computer-based Cognitive Tutor program designed to develop students' algebraic problem-solving skills (p. 128). The software individualizes the instruction that students receive based on students' thinking demonstrated in the problems. The guideline is that students spend 2 days per week of their class time using the tutorial software and 3 days participating in student-centered classroom activities that involve group work and problem solving. The software was designed to provide students with real-world problem-solving situations and are aligned with standards established by the National Council of Teachers of Mathematics. Students' use of the software is self-paced and the student experience is shaped by their mastery of the material (p. 129).
Comparison Group
Schools in the comparison condition utilized their existing algebra curriculum, generally published by Prentice Hall, Glencoe, and McDougal Littell, during the two-year study period.
Support for implementation
Teachers received 4 days of training on the Cognitive Tutor Algebra I curriculum and instructional process, embedded in the software. Teachers attended a 3-day session prior to the start of the school year, and a 1-day training session during the school year. During the 3-day training, teachers received an introduction to the curriculum materials, tutoring software, and teacher instructional tools. Teachers are provided with guidance on how to implement the curriculum and suggestions of strategies for effective questioning techniques, as well as instruction on how to use data from the software to better tailor their instruction. During the follow-up training day in the school year, professional development staff observe classrooms and offer recommendations to improve implementation. Teachers received a set of training materials, an implementation guide, and various resources and assessments as part of the intervention group.
Single Study Review
Review Details
Reviewed: December 2025
- Single Study Review (findings for Cognitive Tutor Algebra I)
- Randomized Controlled Trial
- The study does not meet WWC group design standards because the equivalence of the clusters in the analytic intervention and comparison groups is necessary but the requirement was not satisfied.
This review may not reflect the full body of research evidence for this intervention.
Evidence Tier rating based solely on this study. This intervention may achieve a higher tier when combined with the full body of evidence.
Findings
Evidence Tier rating based solely on this study. This intervention may achieve a higher tier when combined with the full body of evidence.
Sample Characteristics
Study sample characteristics were not reported.Cognitive Tutor Algebra I Intervention Report - Secondary Mathematics
Review Details
Reviewed: June 2016
- Randomized Controlled Trial
- Does not meet WWC standards because equivalence of the analytic intervention and comparison groups is necessary and not demonstrated.
This review may not reflect the full body of research evidence for this intervention.
Evidence Tier rating based solely on this study. This intervention may achieve a higher tier when combined with the full body of evidence.
Please see the WWC summary of evidence for Cognitive Tutor Algebra I.
Findings
Evidence Tier rating based solely on this study. This intervention may achieve a higher tier when combined with the full body of evidence.
Sample Characteristics
Study sample characteristics were not reported.Additional Sources
In the case of multiple manuscripts that report on one study, the WWC selects one manuscript as the primary citation and lists other manuscripts that describe the study as additional sources.
-
Pane, J. F., Griffin, B. A., McCaffrey, D. F., & Karam, R. (2014). Addendum to effectiveness of Cognitive Tutor Algebra I at scale (Working Paper WR-1050-DEIES) (middle school experiment). Santa Monica, CA: RAND Corporation.
-
Pane, J. F., Griffin, B. A., McCaffrey, D. F., Karam, R., Daugherty, L., & Phillips, A. (2013). Does an algebra course with tutoring software improve student learning? (middle school experiment). Santa Monica, CA: RAND Corporation.
-
Sales, A. C., & J. F. Pane (2015, June). Exploring causal mechanisms in a randomized effectiveness trial of the Cognitive Tutor (middle school experiment). Paper presented at the 8th International Conference on Educational Data Mining, Madrid, Spain.
An indicator of the effect of the intervention, the improvement index can be interpreted as the expected change in percentile rank for an average comparison group student if that student had received the intervention.
For more, please see the WWC Glossary entry for improvement index.
An outcome is the knowledge, skills, and attitudes that are attained as a result of an activity. An outcome measures is an instrument, device, or method that provides data on the outcome.
A finding that is included in the effectiveness rating. Excluded findings may include subgroups and subscales.
The sample on which the analysis was conducted.
The group to which the intervention group is compared, which may include a different intervention, business as usual, or no services.
The timing of the post-intervention outcome measure.
The number of students included in the analysis.
The mean score of students in the intervention group.
The mean score of students in the comparison group.
The WWC considers a finding to be statistically significant if the likelihood that the finding is due to chance alone, rather than a real difference, is less than five percent.
The WWC reviews studies for WWC products, Department of Education grant competitions, and IES performance measures.
The name and version of the document used to guide the review of the study.
The version of the WWC design standards used to guide the review of the study.
The result of the WWC assessment of the study. The rating is based on the strength of evidence of the effectiveness of the intervention. Studies are given a rating of Meets WWC Design Standards without Reservations, Meets WWC Design Standards with Reservations, or >Does Not Meet WWC Design Standards.
A related publication that was reviewed alongside the main study of interest.
Study findings for this report.
Based on the direction, magnitude, and statistical significance of the findings within a domain, the WWC characterizes the findings from a study as one of the following: statistically significant positive effects, substantively important positive effects, indeterminate effects, substantively important negative effects, and statistically significant negative effects. For more, please see the WWC Handbook.
The WWC may review studies for multiple purposes, including different reports and re-reviews using updated standards. Each WWC review of this study is listed in the dropdown. Details on any review may be accessed by making a selection from the drop down list.
Tier 1 Strong indicates strong evidence of effectiveness,
Tier 2 Moderate indicates moderate evidence of effectiveness, and
Tier 3 Promising indicates promising evidence of effectiveness,
as defined in the
non-regulatory guidance for ESSA
and the regulations for ED discretionary grants (EDGAR Part 77).