指导澳洲assignment-澳大利亚银行商务统计与市场营销

澳洲指导assignment-澳大利亚作业银行商务统计与市场营销STATISTICS FOR BUSINESS AND MARKETING
Assignment 2
15 marks
Due in Week 9
Part A
Bank of Australia, one of the four leading banks, wishes to assess the effectiveness of one of its recent advertising campaigns that they undertook in promoting the Income Protection and Life Insurance Policies among their customers. The bank has recently introduced a new line of Income Protection and Life Insurance products with an attractive and easy payment scheme in order to boost risk management strategy of customers. 200 of its current customers, who were over the age of 18 and in full-time or part-time employment, were randomly selected for the study.  Each respondent was interviewed before and after being exposed to the advertisement. The file Data2A_Assignment 2.xls, contains the 200 observations from a hypothetical random sample of respondents.  The sample is drawn from a population of 1,200 male and 1,300 female respondents. In this population of male and female customers, there are 2,500 workers.  The variables for each respondent in the file are:

GENDER  1 = Male,  2 = Female
JOB  1 = Full-time employment, 0 = Part-time employment
AGE  Age in years
INCOME  Household income ($’00s)
BEFORE  Purchase of insurance policy ($) in the month before the advertising exposure
AFTER  Purchase of insurance policy ($) in the month after the advertising exposure
CITY   1 = Melbourne, 2 = Sydney, 3 = Adelaide and 4 = Brisbane
PROMOTION 1 = TV, 2 = Radio, 3 = Newspaper  and   4 = Internet

The people in the sample were asked for their responses to the statement - “The new line of Income Protection and Life Insurance products has enhanced my level of purchase”. The responses are the variable ATTITUDE and coded as follows:

1 = strongly disagree,
2 = disagree,
3 = no view either way
4 = agree
5 = strongly agree.

Use SPSS to perform the following tasks. Report your results in an MS Word document.

(1) Find the mean and standard deviation of the age of respondents in the sample. Use these to place a 95 percent confidence interval on the mean age of the population of bank’s customers. (You will need to use the finite population correction factor).

(2) Find the means and standard deviations of the income of (a) Male and (b) Female respondents in the sample, regardless of employment hours. Treat the male and female groups as strata for the purposes of a Stratified Random Sample. Based on this supposition, use the means and standard deviations to place a 95 percent confidence interval on the mean income of all customers in the population. (The finite population correction factor is already contained in the stratified sample standard error formula – do not use it again!)#p#分页标题#e#

(3) Create a new variable called POSITIVE where POSITIVE = 1 if the response to ATTITUDE was 4 or 5, OTHERWISE = 0. Attach value labels and variable labels to POSITIVE. Find the proportion of Female respondents in the sample that had a positive response to the attitudinal question and construct a 95 percent confidence interval on the proportion of Female customers in the population with a positive response. (Remember that, given the way POSITIVE is coded, the mean is the same as the proportion that had a positive response to ATTITUDE. You will also need to use the finite population correction factor).

(4) If the household purchase data is not normally distributed, perform a Wilcoxon Rank Sum test of the null hypothesis that the distributions of purchase in the month before being exposed to the advertising campaign are the same for Male workers and Female workers in the population of customers. Perform the hypothesis test at .05 level of significance.

(5) If the data is not normally distributed, perform a Wilcoxon Signed Rank Test of the null hypothesis that purchase in the month before the advertising exposure is the same as in the month after for the population of customers.

(6) Re-code ATTITUDE into a new variable called NEWATT with Agree and Strongly Agree = 1 (Positive). No View Either Way = 2 (Neutral) and Disagree and Strongly Disagree = 3 (Negative). Perform a chi-square goodness of fit test of the null hypothesis that positive, neutral and negative responses are equally likely amongst the population of Part-time workers.

(7) Use a chi-square test of the null hypothesis that attitudes (use NEWATT) are independent of the promotion methods that the customers in the population are exposed to.

澳洲指导assignment-澳大利亚作业Part B
An Australian owned clothing manufacturer is operating in 3 major cities around the world: New York, London and Tokyo. In a recently held meeting, the board of director decided to analyze sales in these 3 locations. In particular, they are interested to find out whether the business location has any effect on their sales of clothing within the same price range.  The file Data2B_Assignment 2.xls contains 100 observations from a hypothetical random sample of one week sales of clothing in three capital cities. For each showroom, the variables in the file are:

SALES  One-week average sales ($’00s) of clothing
LOCATION  Location of business operation:
1 = New York     2 = London    3 = Tokyo
PRODUCT   Clothing products are categorized:
1 = Men’s clothing 2 = Women’s clothing 
3 = Sports clothing    4 = Children’s clothing
 PROMOTION 1 = Leaflet Distributions   2 = Internet Websites   #p#分页标题#e#
                                      3 = International Clothing Magazines   4 = Newspapers

(8) Conduct a 1-way ANOVA to test the null hypothesis that means sales are the same in all three business locations.

(9) Find Tukey confidence intervals for the mean difference between pair of business locations. Is there any statistically significant mean difference between pair of business location?  (Report on these only where the differences are statistically significant.)

(10) Conduct a 2-way ANOVA to test the null hypothesis that means sales are the same for all products and cities. Allow for the possibility of an interaction effect between the products and the location.

(11) Produce Tukey confidence intervals for row and column differences. (Report on these only where the differences are statistically significant.)

(12) Use a Kruskall-Wallis test of the null hypothesis that the distributions of sales are the same for all three-business locations.

(13) Is the sales data sufficiently non-normal to warrant the non-parametric test instead of one-way ANOVA?  (Hint: In your answer to this question, you are expected to revisit the result obtained from Q8).

澳洲指导assignment-澳大利亚作业Notes:

(a) http://www.ukassignment.org/daixieAssignment/aozhoudaixieassignment/For assignment formatting, refer to and follow the guidelines set out in the document “Guidelines for writing assignments” document in Blackboard/WebCT under Tutorial Material.

(b) The assignment must be professionally presented.

(c) Marks will not be awarded for any table presented without an analysis.

(d) This is a group assignment of a maximum of three students per group; however, your tutor can grant you permission of two students per group. The assignment group must be from the same tutorial group.
 
(e)  An assignment Cover Sheet must accompany every assignment (see “cover sheet” in Blackboard/WebCT - Tutorial Material) which must be signed by all group members’ prior to submission. Any assignment submitted without an Assignment Cover Sheet will not be marked.