Data Analysis in Marketing - Assignment Example

• a. Quantitative: Results are conclusive and generalizable

b. Qualitative: Results are tentative and less generalizable

Question 2

Part 2

The best design is the quantitative research design. Quantitative research is highly recommended because the researcher has a clear picture of what is to be expected in the research. The other reason is that it makes use of measurable data to formulate facts as well as uncover patterns in research. The data collected in quantitative research is also much more structured compared to the qualitative data collection techniques (Saunders, Saunders, & Thornhill, 2011). Quantitative research is objective in nature because it only seeks accurate measurements along with analysis of the target concepts to respond to the questions. Considering that a large sample size increases data reliability, quantitative research gathers a huge amount of data that can be easily organized and put into reports for analysis. Therefore, quantitative research is more logical and offers a measure of what people think from a numerical as well as statistical view point.

Question 3

1. C-Bias

2. B-Quality and quantity

3. D-Reliability and validity

4. E-Competence

5. A-Congruence

Question 4

Using secondary data sources is very crucial since it always saves time. In the era of information technology, one can easily access the secondary data sources via the Internet. Also, most of the libraries have been digitized. Next, there are also easily accessible compared to primary data sources. The Internet has revolutionized secondary data collection and one can access the sources anywhere. It is also less costly to use secondary data sources. They are also feasible for both longitudinal as well as international comparative studies. Continuous surveys, for example, government censuses are particularly good for such research purposes. The researchers can evaluate the evolution if the surveys are carried out on a regular basis.

Question 5

Sample size (n) = 200

When we say that we are 99% confident that the true value of the parameter is in our CI, it means that we express that 99% of the hypothetically observed CI intervals will hold the parameter’s true value.

When a hypothesis test is carried out while calculating confidence interval, it is correct to point out that the significance level is 5% if the confidence level is 95%.

p ± [z x Sp]

Calculation

Question 6

Independent t test: The population means from the two unrelated groups are equal:

H0: u1 = u2

Correlation: that correlation coefficient (r) = 0 -- that there is no relationship between the variables.

Question 7

Open-ended response Q8-5

Close-ended Q 7

Scaled response Q11_5

Question 8

Nominal: Q12

Ordinal: Q15

Interval: Q13

Ratio: N/A

Part 3

Question 1

CI Formula: p ± [z x Sp]

It can be concluded that 318 respondents out of the 569 participants agreed that they had purchased prescription medicines in the past 12 months. The best estimate of the percentage of people who indicated that they that they had purchased prescription medicines in the past 12 months is 55.9%. And, we are 99% confident that the true population value falls between………….and ……………%.

Question 2

Interpretation: We are fairly certain (95%) the hypothesis that mean level of controversy with the product category “Alcohol” is equal to 3.0 is supported. It is because the calculated t-value of -0.647 falls inside the +/- 1.96 acceptance region. In addition, we are 95% confident that the true population value falls between -0.1993 and 0.1005.

Question 3

Calculate a z-score.

Z = p-πH/sx

p = sample percentage

πH = hypothesized percentage

Sx = standard error of that percentage or √(p x q)/n

Calculate a z-score.

z = p-πH/sx

p = 27.8

πH = 30

Sx = √(27.8x 72.2)/569

z = 27.8-30/1.88

z = -1.17

Interpretation: Because our calculated z-score of -1.17 is not greater than the critical z-score of +1.64, we can say that our hypothesis is NOT SUPPORTED. Hence, we can conclude, with 95% confidence, that the percentage of consumers who believed that for underwear, how the product is advertised is controversial is less than 30%.

Question 4

Formula

Alcohol

Since the calculated p-value is > .05, we ACCEPT the null hypothesis. That is, there is no statistically significant difference between males and females when it comes their perceptions how controversial alcohol is as a controversial product category (Mm = 3.2, Mf=2.8). Both groups believe it is controversial.

It is equally important to note that the t value is -2.62 with associated degrees of freedom of 558. This is not significant (sig. = .396) since > 0.05. The mean difference between groups is – 0.41. This is followed by the standard error for the sampling distribution of mean differences and the 95% confidence interval for the difference in means. We conclude that that there is no significant difference that exists between males and females when it comes to their perceptions how controversial alcohol is as product categories.

Tobacco

Since the calculated p-value is > .05, we ACCEPT the null hypothesis. That is, there is no statistically significant difference between males and females when it comes their perceptions how controversial tobacco is as a controversial product category (Mm = 4.1, Mf=4.2). Both groups believe it is controversial.

Furthermore, the t value is -3.89 with associated degrees of freedom of 559. This is not significant (sig. = .216) since > 0.05. The mean difference between groups is – 0.069. This is followed by the standard error for the sampling distribution of mean differences and the 95% confidence interval for the difference in means. We conclude that that there is no significant difference that exists between males and females when it comes to their perceptions how controversial tobacco is as product categories.

Question 5

The first table represents the descriptive statistics due to the fact that option was selected in the Options window. An average of 24.52 was for the different age groups relative to their mean overall attitude towards business.

We accept the null since the p-value is 0.53. We conclude that there are no statistically significant differences between age range groups relative to their mean overall attitude towards business.

We must look at the Duncan post-hoc results to determine which groups are different. However, because the p-value is >0.05, the Duncan test results are meaningless (Welman, Kruger, & Mitchell, 2005).

Question 6

Since the P value is <.05, we have a SIGNIFICANT association. This means there is little support for the null hypothesis (no association). Therefore, we have a significant association between different age ranges and whether or not the consumer had bought contraceptives in the last 12 months. We have the PRESENCE of a systematic relationship between the two variables.

Considering that our Chi-square statistic was significant (< or .05). This means the pattern we observe between different age ranges and whether or not the consumer had bought contraceptives in the last 12 months is a systematic relationship. That is, we could expect to see this same relationship if we ran our study over many, many times.

A significant chi-square result means the researcher should look at the cross-tabulation row and column counts to “see” the association pattern. The majority (139/154) who were aged between 18 to 34 years purchased contraceptives in the last 12 months compared to other age ranges.

Question 7

7 (a) Interpretation: Since the p-value = .000, we reject the null in favor of the alternative. We can conclude that there is a statistically significant relationship present in the perceived levels of agreement among the two statements “Higher taxes should be placed on the sales of controversial products” and “it should be more difficult for consumers to obtain controversial products.” In addition, we can conclude that the relationship is increasing, such that the more someone agrees that higher taxes should be placed on the sales of controversial products, the more someone will be of the view that it should be more difficult for consumers to obtain controversial products. However, this relationship is weak (r = 0.42). The direction of association is positive.

7 (b) Interpretation: Since the p-value = .000, we reject the null in favor of the alternative. We can conclude that there is a statistically significant relationship present between whether or not someone purchased alcohol in the past 12 months and how controversial they think the product category “Alcohol” is. Besides, we can conclude that the relationship is reducing, such that the more someone agrees to have bought alcohol in the past 12 months, the lesser someone will view how controversial they think the product category “Alcohol” is. However, this relationship is very weak (r = 0.17).

The direction of association is negative.