Conclusions
Basic Statistics: Paired t-test
The respondents preferred Nature Valley than Quaker or Soyjoy because of it's higher mean Brand Index Score (BIS). However, paired t-test showed that only one pair, Soyjoy and Nature Valley, was statistically significant. Thus, this result could be projected to the population. In 85 or more samples drawn from the same population as this sample, the mean scores for the compared brands would be similar to what they are in this sample.
Basic Statistics: Between Groups t-test
Thirty-three respondents exhibited a more positive opinion over Soyjoy after viewing the ad, while 11 exhibited a more negative opinion. The simple and colorful ad may have attracted viewers. Since Brand Index Score (BIS) and Ad Index Score (AIS) were all significant, the answers provided in the sample could be projected to the population. In 85 or more samples drawn from the same population as this sample, the mean Brand Index Score (BIS) and Ad Index Score (AIS) for Soyjoy would be similar to what they are in this sample.
Basic Statistics: Chi-Squared Significance Test
Twenty-nine respondents had above-median BIS's while 34 had below median scores. There were more respondents who originally less favored Soyjoy but thought higher of the brand in the post-viewing of the ad. In 85 or more samples drawn from the same population as this sample, the scores for Soyjoy would be similar to what they are in this sample. Since the results are statistically significant, the answers provided in the sample can be projected onto the population.
Basic Statistics: Change Frequency
This frequency test was conducted in order to determine whether the ads used in the survey increased positive feelings towards any of the three brands. The two most positively increasing ads were Quaker and Soyjoy, whereas Nature Valley ad had a majority of down-movers and those who stayed the same.
Basic Statistics: Simple Correlation
There was a weakly positive correlation between respondents who like Quaker and Soyjoy. In 85 or more samples out of 100 samples drawn from the same population of this sample, it would be expected that there to be a weak direct relationship between two brands as there are in this sample. In terms of Brand Index Scores, when the Quaker brand’s score increases or decreases in a certain direction, Soyjoy’s brand index score tends to follow the same pattern. When it comes to correalation with gender, a weak correlation of 0.2 was found to exist between the Quaker and Soyjoy brands of cereal bars, which suggested that males who like the Quaker brand slightly tend to like the Soyjoy brand too and vice versa.
Regression Analysis
The multiple regression analysis for Nature Valley showed that there was a moderate relationship between how respondents rated the Nature Valley brand on the ten Likert items and their liking toward the Nature Valley ad by the result of their pre-post ad exposure change score. Since F-ratio was statistically significant, in 85 or more samples drawn from the same population as this sample, it would be expected that the coefficient of multiple determinations would be about the same as this sample. For Quaker, there was a moderate relationship with coefficient of .6., and it was also found to be significant with an F-ratio of 3.32. Lastly, There was a weak relationship between how respondents rated the Soyjoy brand on the ten Likert questions and their liking toward the Soyjoy ad by their pre-post ad exposure change score. It was revealed that only 27.3% of the variance of the pre-post ad exposure change scores could be explained by Likert items. Since the F-ratio for Soyjoy was significant, in 85 or more samples out of every 100 drawn from the same population as this sample, it would be expected that the coefficient of multiple determination would be about the same as it is in the sample.
Discriminant Analysis for Nature Valley
Between the up-movers and down-movers of those favoring Nature Valley, up-movers had slightly higher Likert item scores. In the classification matrix of predicted versus actual move scores, 85.4% of the originally grouped cases were classified correctly. The observed t-ratio proved to be significant, meaning in 85 or more samples out of 100 samples the statistics can be accurately projected to the population. Discriminant analysis was a quite successful because Wilks’ Lambda result showed that group centroids were statistically significant as indicated by chi-squared value of 20.77 and 85.4% of the original grouped cases were correctly classified as either an up-movers group or a down-movers group. Moreover, t-ratio to test this classification accuracy was significant.
ANOVA/MANOVA for Nature Valley
The F-ratio between the interaction of gender and Nature Valley was significant. The difference between male and female respondents was the largest for up-movers and the smallest for down-movers. Male up-movers had a higher Likert item mean score, while female up-movers had lower mean scores. The interaction between gender and Nature Valley was not significant when processed in the MANOVA, meaning the data for interaction between gender and Nature Valley could not be applied to the greater population from which the sample was drawn.
Factor Analysis
For Nature Valley, the two factors account for 49.1% of the variance. Seven brand attributes loaded to Factor 1: " good brand", "makes me feel energized", "better health benefits than other bars", "substitute for a meal", "take care of my appetite", "feel good about purchasing", "packaging is attractive."
For Quaker, the three factors account for 69.1% of the variance. Seven brand attributes loaded to Factor 1: " good brand", "makes me feel energized", "better health benefits than other bars", "substitute for a meal", "take care of my appetite", "feel good about purchasing", "packaging is attractive."
For Quaker, the three factors account for 69.6% of the variance. Seven brand attributes loaded to Factor 1: " good brand", "makes me feel energized", "better health benefits than other bars", "substitute for a meal", "take care of my appetite", "feel good about purchasing", "packaging is attractive."
It is revealed that Nature Valley had the highest mean attitude score of 3.4 while the other two brands came in tied with a score of 3.3. The t-ratios were only significant in the paired test between Soyjoy and Nature Valley. Therefore, in 85 or more samples out of every 100 drawn from the same population as this sample, it would be expect that the results would remain the same.
Cluster Analysis for Nature Valley
A 2-mean and 3-mean cluster analysis was run to determine how likely respondents would fall in certain set clusters. These clusters would group respondents into best-fit categories based on how they matched with the brand attribute scores. Eight Likert items in 2-mean analysis and 10 Likert items in 3-mean analysis were found to be statistically significant. After comparing the cluster means between 3 found clusters within the group, it was revealed that the respondents in cluster 1 had the highest mean scores, followed by cluster 2 then cluster 3. A chi-squared significance test was also conducted to determine the relationship between cluster membership and gender for the Nature Valley brand. The results showed that the number of males and females in Cluster 1 and Cluster 2 were almost same, while cluster 3 was slightly female oriented. However, since these results were not statistically significant, they could not be used to describe a larger population. In 85 (or more) of 100 samples drawn from the same population as this sample, we would not expect to find the same results.