Background
A recent study of social media use in early 2019 was undertaken to examine if there were any patterns in the gender, living arrangements, parents’ education and age of spent online per weekend in three social media types, namely Facebook, Instagram and Others (Youtube, Twitter etc). The purpose of the study is to understand the habits of the younger population in relation to different forms of media use. An example of the first 10 observations is seen below.
Instagram Facebook Other Gender Age Lives at Home Year 10 Year 12 Bachelor
| 35 | 38 | 17 | 0 | 19 | 1 | 1 | 0 | 0 |
| 65 | 26 | 21 | 1 | 19 | 0 | 1 | 0 | 0 |
| 55 | 44 | 23 | 0 | 18 | 0 | 0 | 0 | 1 |
| 40 | 29 | 24 | 1 | 18 | 0 | 1 | 0 | 0 |
| 65 | 40 | 24 | 1 | 19 | 1 | 0 | 1 | 0 |
| 50 | 64 | 25 | 1 | 17 | 1 | 0 | 1 | 0 |
| 65 | 41 | 25 | 1 | 18 | 0 | 0 | 1 | 0 |
| 60 | 24 | 26 | 0 | 19 | 0 | 0 | 0 | 0 |
| 60 | 54 | 27 | 1 | 18 | 0 | 0 | 0 | 1 |
| 65 | 73 | 27 | 1 | 19 | 1 | 0 | 0 | 0 |
A key to understanding the data is as follows:
- Instagram: time spent in minutes per weekend on Instagram
- Facebook: time spent in minutes per weekend on Facebook
- Other: time spent in minutes per weekend on other social media platforms
- Gender: a dummy variable where Female=l and Male=0
- Age: is the age of the person who agreed to participate in the study
- Lives at Home: whether the person lives at home where Yes=l and 0=No
- Year 10: highest level of education of parents is Year 10
- Year 12: highest level of education of parents is Year 12
- University: parents had completed a bachelor’s degree
- Postgraduate: This is the reference variable for Year 10, Year 12 and Bachelor so all comparisons are against this variable
Task 1 (Boxplots and t-tests: Investigating the Data)
- Construct separateboxplots for gender and time spent online for Facebook, Instagram and other social media platforms. What can you say about the distributional features shown in the graphical representations (central location, spread and skewness) of each of the boxplots?
(4 marks)
- (a) Considering Facebook, Instagram and Social Media, test whether there is a significant difference in the usage time between males and females at a 5% level of significance.
(2 marks)
(b) Considering Facebook, Instagram and Social Media, test whether there is a significant difference in the usage time for those who live at home versus thus who do not live at home at a 5% level of significance.
(2 marks)
- Write a short summary of the results of Questions 1 & 2 outlining the results that you have found and how these results better help to explain the purpose of the study. What happens if you were willing to decrease the significance levels?
(4 marks)
Note: In all two sample tests, you should discuss briefly whether it is a one or two tail test, the test
statistics, any assumption made and draw a conclusion based on Excel output.