This is worth 50% of the module mark. Work must be submitted via Moodle.
Information about Submission
The word count is 2,000. You will need to produce your work in a single Word
document. This means that any data and charts you produce in SPSS must be copied
into Word. I recommend you to save your word file as pdf document and upload the
pdf version of your report onto Turnitin. This will ensure that all graphs and tables in
your document are correctly displayed. Furthermore, Turnitin only accepts pdf or
word (.doc/.docx) documents. Any other formats that cannot be opened will receive a
mark of 0.
2
TASK: Data analysis
Use the dataset (see Moodle) “wage.sav” and try to answer the following research question:
which underlying variable affects the people’s wage?
The variables used in the dataset as defined as follows:
Variable name Variable definition
Wage The wage of the interviewee
Age Age at the time of the interview
Msp Dummy variable, if married=1 and 0 otherwise
Collgrad Dummy variable, if college graduate=1 and 0 otherwise
Union Dummy variable, if union member=1 and 0 otherwise
Experience Total years of experience
Tenure Number of years in the current company
Hours Weekly working hours
Your coursework should cover the following topics:
1. A cover which includes the module code, assignment title, name and ID.
2. Introduction (5%)
Do some background research on the factors that may affect people’s wage. This
section should be no more than 500 words.
3. Descriptive statistics, graphs and correlation test (20%)
• Descriptive statistics: provide numeral descriptive statistics of the variables
wage, age, experience, tenure, hours used in the dataset (Mean, Median,
Maximum, Minimum, variance, Standard deviation, Skewness etc). Describe
the statistics for each variable briefly. (10%)
• Graphs: create a scatter plot to show the relationship between wage and marriage,
explain the results. (5%)
• Create a new variable ln(wage), explain the use of the function logarithm. (5%)
4. Regression analysis and discussion of the results (50%)
Dependent variable: lnwage; all other variables as used as independent variables
• Write out the regression model (5%)
• Explain the model summary table (5%)
• Set up, conduct hypothesis tests and interpret the results for the ANOVA table (10%)
• Set up, conduct hypothesis tests and interpret the results for the coefficients table
(15%)
• Discuss the results: which of the factors can explain people’s wage level? You should
provide appropriate references of theories and evidence for your analysis (15%)
5. Diagnostic tests (10%)
• Check for the existence of the multicollinearity issue, explain the methodology and
discuss the results (10%)
6. Conclusion (5%)
7. The format, English grammar and syntax (5%)
3
8. References, using the Harvard Referencing style (5%)
Please note the following:
• You must use SPSS for your analysis and report the SPSS results in your assignment.
• Your assignment should demonstrate a good understanding of the relevant concepts,
analytical methods and their interpretation.
• The assignment should demonstrate a good ability to interpret the statistical method,
relevant data and facts in an analytical manner.