conclusion

Basic Statistics

Correlated t-tests: Brand Index Scores

The Brand Index Score for the three brands of vodka ranged from 31.4 for Stolichnaya, to 33.5 for Belvedere and Ketel One in the middle with a mean score of 32.0. The Brand Index Score was calculated by the the summing the results of the 10 Likert questions for each brand, the highest possible score being 50. The three means are all in the middle range indicating that, on average, the respondents had a fairly neutral attitude towards the brands. Two of the three t-tests revealed a significant result, meaning that the differences in scores between Stolichnaya and Belvedere and between Belvedere and Ketel One can be predicted to the population with an 85% confidence level.

Between Group t-tests: pre and post-exposure to the ad

For Stolichnaya only 28% of respondents reported an increased purchase intention after viewing the ad while 38% reported a decrease in purchase intention. Both the mean Advertising Index Score and Brand Index score for those respondents who reported an increased purchase intention was higher than that of those who reported a decreased purchase intention. The between groups t-test resulted in a significant relationship and the differences in the means between up-movers and down-movers can be predicted to the population.

Chi Squared Test: up vs. down movers and the median Brand Index Score

Although there appears to be a slight difference in the location of the Brand Index Scores of up and down-movers in relation to the median Brand Index Score of 31. 52% of up-movers were above the median compared with 44% of down-movers, however the chi-square test revealed that the difference was not significant and therefore could not be predicted to the population.

Frequencies: Change in Purchase Intention

Belvedere had the highest number of up-movers with 34, and therefore the most positive post-exposure purchase intention. Stolichnaya and Ketel One both had only 19 up-movers, they also had the highest numbers of down movers with 27 and 28 respectively. Belvedere also had a lower number of respondents who maintained the same level of purchase intention pre to post-ad with 16 compared to 21 and 22 for Ketel One and Stolichnaya.

Brand Preference Comparision

26 out of the 68 total respondents, or 38.2%, gave Stolichnaya a higher Brand Index Score than they gave to Belvedere. This result is in line with the information which showed that more respondents' purchase intentions increased for Belvedere than for Stolichnaya post-ad exposure, giving them a generally more positive attitude toward the brand.

Pearson Correlation Test

The scores of the correlation run between the Brand Index Scores of Belvedere and Stolichnaya revealed a significant low inverse correlation, therefore as the Stolichnaya Brand Index Score rises the Belvedere score falls, though not dramatically.

Brand Preference Comparision among Female Respondents

11 respondents out of a total of 43, or 25.6%, gave Stolichnaya a higher Brand Index Score than they gave to Belvedere. These results make it appear that fewer females in this sample prefer Stolichnaya to Belvedere than the total sample which 38% gave Stolichnaya a higher score. This would also imply that male respondents score Stolichnaya more positively on the Brand Index Score than both females and the total sample.

next

Multiple Regression Analysis

The brand attributes of Stolichnaya account for only 12.5% of the variance in the pre and post-ad viewing scores, this finding is not significant and cannot be predicted to the population. Only one attribute, "Stolichnaya has a nice bottle," was found to be significant and in 85 out of 100 samples taken from the same population as this sample the coefficient is expected to be about what they are here.

The brand attributes of Belvedere Vodka account for only slightly more variance that those of Stolichnaya, 15.0%, which is not significant and cannot be predicted to the population. The two brand attributes, "Belvedere has and nice bottle" and" Belvedere is sophisticated", are statistically significant therefore, in 85 out of 100 samples taken from the same population as this sample it would be expected that the results for these two variables would be approximately what they were in this sample.

A significantly higher 33% of the variance for Ketel One is explained by the 10 Likert items in the questionaire, this result can be predicted to the population. Four of the brand attributes for Ketel One: "has a nice bottle", "is preferred over other vodkas", "makes good mixed drinks", and "is not a brand that I would buy," also have coefficients which are statistically significant.

next

Discriminant Analysis

The analysis found that 70.6% of the time the classification of respondents into up or down-movers can be predicted accurately. The Likert items which determine the most of the classification of a respondent are Belvedere’s “bottle” and its perceived “high quality.” These two variables had the strongest coefficients at 1.0. Belvedere “fits my lifestyle”, ‘is prefered”, and “is recommended” are also influential with slightly lower coefficients. 70.6% is a statistically significant amount and therefore it is predicted that the grouping of the population can be correctly predicted at approximately the same rate of 70.6%.

next

ANOVA

The Likert item "Belvedere has an attractive bottle" has a higher mean score for men then women in the up-mover group, in the groups who stayed the same or were down-movers women had a more positive score than men. Among those up-movers, males had an average Brand Index Score of 4.4 compared with the female score of 4.1 implying that exposure to the ad had a more extreme effect on men's opinions of the Belvedere bottle than on women. The f-ratio revealed that the results were significant for all variables and can therefore be predicted to the population, when gender and change score are applied to the variable independently or in conjunction with one another.

MANOVA

Females in the same and down-mover group gave higher mean scores for all ten Likert items than the corresponding value given by males, however in the up-mover group then males gave higher mean scores for all variables than the females. This suggests that males gave more definate opinions regarding the Likert variables while women stayed closer to the central "Neither Agree nor Disagree." The f-ratio for gender and change score where significant while the f-ratio for the combination of the two was not, meaning that the effect of gender on the Likert score and that of change (up, same, down) grouping have a significant effect on the resulting score and this effect can be predicted to the population. However when gender and change group occur in conjunction the resulting effect is no longer significant and cannot be predicted to the population.

next

Factor Analysis

The three brands of vodka all loaded on two factors; for Stolichnaya they explained 57% of the variance, for Belvedere 56% and for Ketel One 64%. The paired t-test showed that the mean attitude scores for Stolichnaya and Belvedere and for Stolichnaya and Ketel One were statistically significant and could therefore be predeicted to the population. The mean attitude scores were 3.1, 3.5 and 3.6 which is in the middle zone, on a ten point scale, and appear to be fairly neutral with the most positive attitude towards Ketel One and the least positive towards Stolichnaya.

next

Cluster Analysis

The respondents for Stolichanaya are spilt between two clusters, 39 fell in cluster one and 29 on cluster two. The mean Likert item scores are statisticallly lower for cluster two than for cluster one for every item except "Stolichnaya is like any other vodka."

The crosstab performed on the respondents drinking habits and the cluster in which they fell based on their Likert item scores revealed that more fell into cluster two independent of whether they drank never/ rarely or they drank sometimes/often. The clusters identified cannot predict the drinking habits of a respondent in the sample.

back to top