Is any particular length of advert significantly better or worse than the others? If so, which length; and is it better or worse?
For this coursework you are required to perform an Analysis of Variance using SPSS. Your solution should be word-processed and submitted electronically. Your solution should include any output produced from the analysis, and a detailed account of the methods you have used, the reasons you have chosen those particular methods, and the conclusions you have drawn.
The problem:
An experiment is carried out to determine the effectiveness of advertising a particular product with new local TV stations. In different parts of the country, advertisements are placed with either the local TV or a local radio station. The length of the advertisements is characterised as short, medium or long. Each combination of media and length is tested in four localities. The observed result is the level of sales in that locality in the fortnight following the appearance of the first advertisement.
The data are in the SPSS datafile LocalTV.
Load the data into SPSS and investigate the meaning of the values of the variables.
Perform a suitable two-way Analysis of Variance to investigate the results. If appropriate, include a suitable multiple comparisons analysis and/or a profile plot. Explain why it is appropriate to include (or exclude) such analyses.
You should address the following questions, explaining your answers in detail:
1.Are the main effects significant, and is there any significant interaction?
2.What percentage of the variation in the sales figures is accounted for by the model?
3.Is any particular length of advert significantly better or worse than the others? If so, which length; and is it better or worse?
4.Do the radio or TV adverts produce better sales?
5.If your requirement is to maximize sales figures, which combination of media and length would you select?
6.What form of advertising would you definitely not use?
7.If your requirement is to maximize profit, what other factors would you take into consideration, and what would you advise a firm to do?
