In: Statistics and Probability
a) Use the Histogram tool to develop a frequency distribution for the number of days and the browser used as a customer of this online store. Use your judgement for determining the number of bins to use.
b) Construct complete histogram graphs and numerical descriptions (that is, histograms and measures of location and dispersion) for the length of time the shopper spends on the website and the amount spent per transaction.
c) The company would like to investigate the effect that the day of the week have on sales. Summarize the total dollars spent and the mean amount spent per transaction for each day of the week. Briefly discuss your findings.
Customer | Day | Browser | Time (min) | Pages Viewed | Amount Spent ($) |
8 | Fri | Firefox | 4.3 | 6 | 55.96 |
40 | Wed | Chrome | 5.0 | 5 | 36.48 |
19 | Fri | Other | 5.6 | 4 | 68.45 |
28 | Sat | Firefox | 6.0 | 4 | 27.91 |
37 | Thu | Firefox | 6.2 | 4 | 84.17 |
31 | Thu | Chrome | 7.1 | 2 | 41.20 |
49 | Mon | Other | 7.3 | 6 | 52.15 |
35 | Tue | Chrome | 7.8 | 5 | 71.81 |
24 | Tue | Firefox | 8.0 | 2 | 48.66 |
23 | Sun | Chrome | 8.0 | 3 | 32.73 |
47 | Thu | Chrome | 8.1 | 2 | 17.84 |
15 | Fri | Chrome | 8.4 | 3 | 84.12 |
3 | Mon | Chrome | 8.5 | 4 | 26.68 |
34 | Fri | Chrome | 9.1 | 3 | 52.09 |
25 | Fri | Firefox | 9.6 | 3 | 54.66 |
16 | Thu | Chrome | 9.6 | 4 | 59.20 |
48 | Fri | Chrome | 9.7 | 7 | 103.15 |
22 | Tue | Chrome | 10.2 | 6 | 74.43 |
6 | Sat | Firefox | 10.5 | 6 | 67.80 |
39 | Tue | Chrome | 10.6 | 2 | 39.06 |
43 | Fri | Firefox | 10.8 | 4 | 70.38 |
26 | Wed | Chrome | 11.0 | 2 | 40.54 |
5 | Wed | Chrome | 11.3 | 4 | 66.27 |
38 | Sat | Chrome | 11.3 | 4 | 55.58 |
4 | Tue | Firefox | 11.4 | 2 | 44.73 |
7 | Sun | Chrome | 11.4 | 2 | 36.04 |
13 | Sun | Other | 11.7 | 7 | 64.16 |
33 | Sun | Chrome | 11.8 | 4 | 37.17 |
30 | Mon | Other | 11.8 | 9 | 120.25 |
1 | Mon | Chrome | 12.0 | 4 | 54.52 |
9 | Wed | Firefox | 12.7 | 3 | 70.94 |
11 | Sat | Other | 13.3 | 6 | 54.04 |
44 | Mon | Chrome | 13.3 | 7 | 110.65 |
50 | Fri | Chrome | 13.4 | 3 | 98.75 |
46 | Fri | Firefox | 13.7 | 4 | 68.17 |
18 | Mon | Chrome | 14.0 | 7 | 126.40 |
12 | Sun | Firefox | 14.3 | 5 | 48.05 |
20 | Wed | Chrome | 15.1 | 5 | 32.69 |
41 | Tue | Other | 15.9 | 4 | 67.44 |
21 | Sat | Firefox | 16.3 | 5 | 78.58 |
36 | Mon | Firefox | 16.5 | 5 | 59.99 |
27 | Sat | Chrome | 16.9 | 5 | 34.69 |
32 | Fri | Firefox | 18.0 | 8 | 134.40 |
42 | Sat | Chrome | 18.1 | 7 | 60.14 |
2 | Wed | Other | 19.5 | 6 | 94.90 |
17 | Thu | Chrome | 23.3 | 7 | 91.62 |
14 | Mon | Firefox | 24.4 | 10 | 168.91 |
10 | Tue | Chrome | 24.7 | 7 | 68.73 |
45 | Mon | Chrome | 30.1 | 6 | 104.23 |
29 | Fri | Firefox | 32.9 | 10 | 155.30 |
a)
The histograms for Day is obtained in excel by using following steps,
Step 1: Write the Data Values for Day in excel. The screenshot is shown below,
Step 2: make a column "Bin" for days mon, tue, .... The screenshot is shown below,
Step 3: Since the data values are categorical, we will count the frequency using the excel function =COUNTIF(B2:B51,"Mon") . The screesnhot is shown below,
Step 4: select the column "Bin" and "Frequency" then
INSERT > Recommended Charts > All Charts > Clustered Column > OK. The screenshot is shown below,
The histogram is obtained. the screenshot is shown below,
Similarly, the histogram for Browser can be obtained by making bin Firefox, Chrome and Other then count for each bin in data values. The histogram is shown below,
b)
The histogram for time spent is obtained in excel using follwoing steps,
Step 1: Write the data values for Time(min) in excel.
Step 2: Make a column Bin with range 5, 10, 15, 20, ....40. The screenshot is shown below,
Step 3: DATA Data Analysis > Histogram > OK. The screenshot is shown below,
Step 4: Select input range: Time column, Bin range: bin column. The screenshot is shown below,
Step 5: Select column bin and frequncy then INSERT > recommended Charts > All Charts > Clustered Column. The screenshot of histogram is shown below,
Similarly, the histogram for Amount Spent can be obtained by making bin size of your choice, e. g. Bin: 0, 25, 50...175. The screenshot of histogram is shown below,
c)
The total dollars spent and the mean amount spent per transaction for each day of the week can be obtained by folowing theses steps,
Step 1: Sort the data by day.
DATA > Sort > Expand the Selection > OK. then input Sort by: Daya, Sort On: Values and Order > Custome List
The screenshot is shown below,
Step 2: Take sum for each day of week using the excel function =SUM(F2:F10). The screenshot is shown below,
Step 3: Take average for each day of week using the excel function =AVERAGE(F2:F10). The screenshot is shown below,
The Sum and average for each day of week is shown below,
Sum | Average | |
Mon | 823.78 | 91.53111 |
Tue | 414.86 | 59.26571 |
Wed | 341.82 | 56.97 |
Thu | 294.03 | 58.806 |
Fri | 945.43 | 85.94818 |
Sat | 378.74 | 54.10571 |
Sun | 218.15 | 43.63 |
Step 4: Select column Day, Sum and Average then
INSERT > Recommended Charts > All Charts > Line > Ok. The screenshot is shown below,