In: Statistics and Probability
An educational psychologist studies the effect of frequent testing on retention of class material. In one of the professor's sections, students are given quizzes each week. The second section receives only two tests during the semester. At the end of the semester, both sections receive the same final exam, and the scores are summarized below.
a. Do the data indicate that testing frequency has a significant effect on performance? Use a two-tailed test with α = .01. (7 points)
b. Compute r2 and state the size of the effect (e.g. small, medium, large). (2 points)
Frequent Quizzes n=15,m=72,SS=112
two exams n=15,M=68,SS=98
The (R-squared) , (additionally called the coefficient of assurance), which is the extent of change (%) in the reliant variable that can be clarified by the autonomous variable. Consequently, as a general guideline for deciphering the quality of a relationship dependent on its R-squared worth (utilize the outright estimation of the R-squared an incentive to make all qualities positive):
- if R-squared worth < 0.3 this worth is commonly viewed as a None or Very feeble impact size,
- if R-squared worth 0.3 < r < 0.5 this worth is commonly viewed as a powerless or low impact size,
- if R-squared worth 0.5 < r < 0.7 this worth is commonly viewed as a Moderate impact size,
- if R-squared worth r > 0.7 this worth is commonly viewed as solid impact size,
here the value of R2 is 0.3636 then it effect is small