In: Statistics and Probability
A researcher wants to see if there are any differences between three types of studying: Studying in a quiet room, studying in a room with classical music playing, and studying in a room with loud lawn equipment going on outside the window. She recruits 9 college students and puts three in each group. She has them read an excerpt from a physics textbook and then gives them a 5-question quiz. Below are their scores. Does study condition have an effect on academic performance?
Quiet Room Classical Music Loud Lawn Equipment
122
243
524
13. Calculate F and make your decision (accept or reject the null?) and report your results in APA format (see the “In The Literature” section on page 349 in your textbook to help you with this).
The following questions assess your understanding of correlational data.
Let μ1, μ2, μ3 denote the mean quiz score of the students who prepared for the quiz studying in a quiet room, studying in a room with classical music playing, and studying in a room with loud lawn respectively.
We have to test:
H0: μ1= μ2 = μ3 Vs Ha: Not all means are equal
In words,
H0: Study condition has no effect on academic performance Vs Ha: Study condition has a significant effect on academic performance
The appropriate statistical test to test the above hypothesis would be a One way ANOVA.
Constructing an ANOVA table of the format:
Source of Variation | SS | df | MS | F |
Between Groups | SSB | k-1 | MSB = SSB / (k-1) | F = MSB / MSW |
Within Groups | SSW | N-k | MSW = SSW / (N-k) | |
Total | SST | N-1 |
where, K = No. of groups copared and N = No .of observations in the sample.
2.
dfbetween = k - 1 = 3 - 1 = 2
dfwithin = n - k = 9 = 3 = 6
dftotal = n - 1 = 9 - 1 = 8
and F critical is obtained from the F table for (k-1,n-k) = ( 2,6) degrees of freedom for alpha = 0.05:
F2,6 = 5.14
3. Computing the means M1, M2 and M3:
M1 = (1 + 2 + 5) / 3 = 2.67
M2 = (2 + 4 + 2) / 3 = 2.67
M1 = (2 + 3 + 4) / 3 = 3
SS(within) = SSW = Sum [Individual observations in a group - Group mean ]2 for the three groups
= [(1-2.67)^2+(2-2.67)^2+(5-2.67)^2] + [(2-2.67)^2+(4-2.67)^2+(2-2.67)^2] + [(2-3)^2+ (3-3)^2+(4-3)^2]
= 13.34
4. The grand mean is computed using the formula:
G = Sum of all sample observations / Total No. of observations
= (1+2+5+2+4+2+2+3+4) / 9..............(Since, N = 9)
= 2.78
SS(Between) = SSB = Group size * (Group mean - Grand Mean) for the three groups
= 3 [((2.67-2.78)^2)+((2.67-2.78)^2)+((3-2.78)^2 )]
= 0.222
SSTotal = SSW + SSB
= 13.34 + 0.22
= 13.56
5. MSW = SSW / (N-k)
= 13.34 / (9-3)
= 2.22
MSB = SSB / (k-1)
= 0.22 / (3-1)
= 0.11
13. F = MSB / MSW
= 0.11 / 2.22
= 0.05
Comparing the F value obtained with the critical value,
Since F = 0.05 < 5.14 does not lie in the rejection region, we fail to reject the null hypothesis. We may conclude that the data does not provide sufficient evidence to support the claim that Study condition affects academic performance.
Also, to obtain the p-value, we may use the excel function: FDIST
We get p-value = 0.952 > 0.05, which brings us the same conclusion as above.
In APA style,
A one-way between subjects ANOVA was conducted to compare the effect of Study condition on academic performance.There no significant effect of Study condition on DV academic performance at the p<.05 level for the three conditions [F(2,6) = 0.05, p = 0.952)]