Paired t-tests
Table 1: Means of the brand index scores for the three brands under consideration
Brand |
Mean |
Standard deviation |
Advil |
36.4 |
4.4 |
Bayer |
33.6 |
3.9 |
Tylenol |
35.7 |
4.3 |
Sample size: 126 |
||
Table 1 shows the means of the brand index scores for the three brands under consideration. The brand index scores are the totals of ten judgments about each brand on a Likert scale.
Table 2: Paired t-tests of the mean brand index scores for the three brands under consideration
Brand pairing |
t |
Advil and Bayer |
6.19* |
Bayer and Tylenol |
4.48* |
Advil and Tylenol |
1.36* |
|
* p ≤ 0.15 |
The paired t-tests displayed in Table 2 aim to determine if the differences in the means between each brand and each other brand are statistically significant. In 85 or more samples out of 100 samples drawn from the same population as this sample, it would be expected that the differences in the mean brand index scores between Advil and Bayer, Bayer and Tylenol and Advil and Tylenol would be about what they are here. The results of this sample can be projected to the population for this test.
Independent t-tests
Table 3: Means of the advertising and brand index scores for Advil for respondents whose purchase intention went up or down after viewing the advertisements
Advil purchase intention after exposure to the advertisements... |
Number |
Brand index score |
Advertising index score |
||
Mean |
Standard deviation |
Mean |
Standard Deviation |
||
...went up |
19 |
36.8 |
4.3 |
3.6 |
2.6 |
...went down |
45 |
37.1 |
4.1 |
2.6 |
2.5 |
Respondents were asked to rate their likelihood of purchasing each of the three brands on a constant-sum scale both before and after viewing advertisements for each of the brands. Table 3 shows that the Advil constant-sum score of 19 respondents went up after exposure to the ads, and it went down for 45 respondents. For respondents whose Advil scores increased after exposure (“up movers”), mean brand index scores were lower and mean advertising index scores were higher than for respondents whose Advil scores decreased after exposure (“down movers”). Advertising index scores represent the number of positive attributes out of 14 selected by the respondent as applying to each ad.
Table 4: Independent t-tests for the means of the advertising and brand index scores for Advil for respondents whose purchase intention went up or down after viewing the advertisements
|
t |
Advil brand index score |
0.26 |
Advil advertising index score |
1.52* |
|
* p ≤ 0.15 |
As shown in Table 4, independent t-tests were conducted to determine if the differences in the mean brand index scores and mean advertising index scores between “up movers” and “down movers” were statistically significant. The difference between the brand index scores was not found to be significant and cannot be projected to the population from which the samples were drawn. However, in 85 samples out of 100 samples drawn from the same population as this sample, it would be expected that the difference between the mean advertising index scores of the “up movers” and the “down movers” would be about what it is here. The results for this sample can be projected to the population for this test.
Chi-squared test
Table 5: Relationship between Advil purchase intent and Advil's brand index score
Likelihood of purchasing Advil after exposure to ads |
Advil brand index score above the median |
Advil brand index score below the median |
Went up |
9 |
8 |
Stayed the same |
21 |
33 |
Went down |
22 |
20 |
Chi-squared: 2.12 |
|
* p ≤ 0.15 |
In Table 5, a chi-squared test is used to determine if there is a statistically-significant relationship between whether a respondent’s intention to purchase Advil went up, went down or stayed the same and whether a respondent’s brand index score for Advil was above or below the median Advil brand index score of 37. No statistically-significant relationship was found.
Frequency count
Table 6: Number of respondents for each brand whose purchase intentions went up, went down or stayed the same after exposure to the ads
Likelihood of purchasing brand after exposure to ads |
Advil |
Bayer |
Tylenol |
Went up |
19 |
50 |
26 |
Stayed the same |
62 |
73 |
58 |
Went down |
45 |
3 |
42 |
Brand preference comparison
Table 7: Number of respondents who had a higher perception of the Advil brand than the Tylenol brand, and vice versa
|
Number |
Advil brand index score is higher than Tylenol brand index score |
68 |
Advil brand index score is lower than Tylenol brand index score |
58 |
Correlation
Correlation between Advil brand index score and Tylenol brand index score |
0.3* |
|
* p ≤ 0.15 |
As shown in Table 8, there is a weak correlation between the brand index scores of Advil and Tylenol. In 85 samples out of 100 samples taken from the same population as this sample, it would be expected that the correlation between the brand index scores of Advil and Tylenol would be about what it is here. The results of this sample can be projected to the population.
Paired t-tests for heavy users
Table 9: Means of the brand index scores for the three brands under consideration, among respondents whose frequency of use is four or more times over the past 30 days
Brand |
Mean |
Standard deviation |
Advil |
37.2 |
4.1 |
Bayer |
32.7 |
2.9 |
Tylenol |
36.1 |
3.9 |
Sample size: 46 |
||
Table 9 shows the means of the brand index scores for the three brands under consideration, taking into account only those respondents whose use of over-the-counter pain relief medication in the last 30 days was over the median (four times or more). The brand index scores are the totals of ten judgments about each brand on a Likert scale.
Table 10: Paired t-tests of the mean brand index scores for the three brands under consideration, among respondents whose frequency of use is four or more times over the past 30 days
Brand pairing |
t |
Advil and Bayer |
6.67* |
Bayer and Tylenol |
5.04* |
Advil and Tylenol |
1.29* |
|
* p ≤ 0.15 |
The paired t-tests displayed in Table 10 aim to determine if the differences in the means between each brand and each other brand are statistically significant. In 85 or more samples out of 100 samples drawn from the same population as this sample, it would be expected that the differences in the mean brand index scores for heavy users between Advil and Bayer, Bayer and Tylenol and Advil and Tylenol would be about what they are here. The results of this sample can be projected to the population for this test.