Academic Integrity: tutoring, explanations, and feedback — we don’t complete graded work or submit on a student’s behalf.

Five hundred students completed the “Census at School” survey. Each was asked ho

ID: 3257855 • Letter: F

Question

Five hundred students completed the “Census at School” survey. Each was asked how many hours per week they spent doing homework. A researcher uses a quasi-experimental design to compare the average time spent doing homework per week to high school students in different grades. The research question is, “Do students in different grades of high school spent significantly different amounts of time doing homework per week?” Five students were randomly selected from each grade; the data is presented below.

What is the effect size?

Use G*Power to estimate the power of the study?

Grade

9

10

11

12

Hours Spent Doing Homework

3

2

1

5

5

2

1

5

2

4

10

4

3

10

2

19

10

12

5

7

Grade

9

10

11

12

Hours Spent Doing Homework

3

2

1

5

5

2

1

5

2

4

10

4

3

10

2

19

10

12

5

7

Explanation / Answer

Answer:

ANOVA

Tests of Between-Subjects Effects

Dependent Variable:   time

Source

Type III Sum of Squares

df

Mean Square

F

Sig.

Partial Eta Squared

Noncent. Parameter

Observed Powerb

Corrected Model

193.200a

3

64.400

5.111

.011

.489

15.333

.839

Intercept

627.200

1

627.200

49.778

.000

.757

49.778

1.000

grade

193.200

3

64.400

5.111

.011

.489

15.333

.839

Error

201.600

16

12.600

Total

1022.000

20

Corrected Total

394.800

19

a. R Squared = .489 (Adjusted R Squared = .394)

b. Computed using alpha = .05

Effect size=0.489

F tests - ANOVA: Fixed effects, omnibus, one-way

Analysis:              Post hoc: Compute achieved power

Input:    Effect size f         =             0.489

               err prob            =             0.05

               Total sample size              =             20

               Number of groups            =             4

Output:               Noncentrality parameter             =             4.7824200

               Critical F              =             3.2388715

               Numerator df     =             3

               Denominator df =             16

               Power (1- err prob)        =             0.3392984

power= 0.339

Tests of Between-Subjects Effects

Dependent Variable:   time

Source

Type III Sum of Squares

df

Mean Square

F

Sig.

Partial Eta Squared

Noncent. Parameter

Observed Powerb

Corrected Model

193.200a

3

64.400

5.111

.011

.489

15.333

.839

Intercept

627.200

1

627.200

49.778

.000

.757

49.778

1.000

grade

193.200

3

64.400

5.111

.011

.489

15.333

.839

Error

201.600

16

12.600

Total

1022.000

20

Corrected Total

394.800

19

a. R Squared = .489 (Adjusted R Squared = .394)

b. Computed using alpha = .05