In: Math
The authors of a paper concerned about racial stereotypes in television counted the number of times that characters of different ethnicities appeared in commercials aired on a certain city's television stations, resulting in the data in the accompanying table.
Ethnicity |
African- American |
Asian | Caucasian | Hispanic |
---|---|---|---|---|
Observed Frequency | 56 | 12 | 320 | 6 |
Based on the 2000 Census, the proportion of the U.S. population
falling into each of these four ethnic groups are 0.177 for
African-American, 0.032 for Asian, 0.734 for Caucasian, and 0.057
for Hispanic. Do the data provide sufficient evidence to conclude
that the proportions appearing in commercials are not the same as
the census proportions? Test the relevant hypotheses using a
significance level of 0.01.
Let p1, p2,
p3, and p4 be the
proportions of appearances of the four ethnicities across all
commercials.
State the null and alternative hypotheses.
H0: p1 =
p2 = p3 =
p4 = 0.177
Ha: H0 is not
true.
H0: p1 =
p2 = p3 =
p4 = 69.738
Ha: H0 is not
true.
H0: p1 = 0.177,
p2 = 0.032, p3 = 0.734,
p4 = 0.057
Ha: H0 is not
true.
H0: p1 =
p2 = p3 =
p4 = 56
Ha: H0 is not
true.
H0: p1 = 69.738,
p2 = 12.608, p3 = 289.196,
p4 = 22.458
Ha: H0 is not
true.
Calculate the test statistic. (Round your answer to two decimal
places.)
χ2 =
What is the P-value for the test? (Round your answer to
four decimal places.)
P-value =
What can you conclude?
Do not reject H0. There is convincing evidence to conclude that the proportions of appearances in commercials are not the same as the census proportions.
Reject H0. There is not enough evidence to conclude that the proportions of appearances in commercials are not the same as the census proportions.
Reject H0. There is convincing evidence to conclude that the proportions of appearances in commercials are not the same as the census proportions.
Do not reject H0. There is not enough evidence to conclude that the proportions of appearances in commercials are not the same as the census proportions.
State the null and alternative hypotheses.
H0: p1 = 0.177,
p2 = 0.032, p3 = 0.734,
p4 = 0.057
Ha: H0 is not
true.
Test Statistic
O : Observed Frequency
E : Expected Frequency
Ethnicity | O: Observed Frequency | Proportion | E: Expected Frequency = Total * Proportion |
African-American | 56 | 0.177 | 394*0.177=69.738 |
Asian | 12 | 0.032 | 394*0032=12.608 |
Caucasian | 320 | 0.734 | 394*0.734=289.196 |
Hispanic | 6 | 0.057 | 394*0.057=22.458 |
Total | 394 |
O: Observed Frequency | E: Expected Frequency | O-E | (O-E)2 | (O-E)2/E |
56 | 69.738 | -13.738 | 188.7326 | 2.7063 |
12 | 12.608 | -0.608 | 0.3697 | 0.0293 |
320 | 289.196 | 30.804 | 948.8864 | 3.2811 |
6 | 22.458 | -16.458 | 270.8658 | 12.0610 |
Total | 18.0777 |
Test Statistic
Degrees of freedom = number of ethnicities -1 = 4-1 =3
For 3 degrees of freedom,
p-value = 0.0004
As p-value : 0.0004 < significance level : 0.01 ; Reject the null hypothesis.
Conclusion:
Reject H0. There is convincing evidence to conclude that the proportions of appearances in commercials are not the same as the census proportions.