Assignment 1                   Due 20 Mar 2016
 
 
Q1   The general manager of a nationwide chain of fine jewellery stores is interested in investigating customer satisfaction. She decides to run a nationwide survey of customers.
(a)  Suggest two categorical questions that could be asked in the survey, one nominal and one ordinal.

(b)  Suggest two numerical questions that could be asked in the survey, one discrete and one continuous.

(c)   The Manager plans to distribute the survey by including on the receipt the web-address to an online survey. The sales assistants will be told to point out the web-address on the receipt to customers.
Discuss briefly any disadvantages of this method.                                                               

 
Q2    The data file Diamonds.xls contains data from a random sample of round cut diamonds from a Singapore based retailer of diamond jewellery (including the sales prices (in US dollars)). The worksheet called “Info” gives a list of the variables, their meanings and a brief background on this dataset.
(a) Construct a % frequency distribution for the sale prices and use this to complete the table below:      [3]

Frequency Table for Sale Prices of Diamonds

Sales (in 1000s)	Midpoint	Frequency	% Frequency
0 < x ≤ 1.5
1.5 < x ≤ 3
3 < x ≤ 4.5
4.5 < x ≤ 6
6 < x ≤ 7.5
7.5 < x ≤ 9
9 < x ≤ 10.5
10.5 < x ≤ 12

                                                                                                                       
(b). In Excel, construct a histogram illustrating the frequency distribution, and insert this in the space below. Comment on what this graph shows. ........................................................................... [4]

(c). Calculate summary statistics for the sales prices and use them to complete the table below, rounding your answers to 3 decimal places:

Statistic	Sales (1000s)
Mean
Median
1st quartile
3rd quartile
Interquartile range
Range
Standard deviation

                                                                                                                                [3]
 
(d) Using the appropriate variables in Diamonds.xls, draw side-by-side boxplots to compare the distribution of the diamonds sales prices for each of the three certification laboratories. Comment on what these plots show.


Q3    Refer back to the file Diamonds.xls used in Question 2. This dataset also contains data on the colour and clarity classifications of each diamond. The “Info” worksheet gives information on these variables.
 
(a). Construct a pivot table with Clarity as the row variable and Colour as the column variable ....       [2]

Insert your table here

 
 
 
 
 
 
 

(b). Use your pivot table to construct a contingency table showing percentages in each clarity category by colour.  (This means that each column of your table should add up to 100%.) Pay attention to rounding in your display....................................................................................................................................... [3]

Insert your table here

 
 
 
 
 
 
 
 
 
 
 

(c) Construct a suitable chart to illustrate the above contingency table, and comment on what it suggests.       [4]

	Insert your chart here
			Type your comments here

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Q4    Extension Question – this is not compulsory, but is an opportunity to earn some bonus marks if you want to attempt this more challenging question. You can get up to 5 extra marks by doing so.
 
Refer back to the data in the file Diamonds.xls. Use Excel’s PivotTable facility to create a table showing how the mean sales price and weight (in Carats) vary according to Clarity.  You will have to explore the options in the PivotTable Field List in order to change the value field setting from “Sum” (the default) to more appropriate settings. Comment on what your table shows.

Insert your table here                     Insert your comments here               [5]

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

+ + + + + +