Assignment Overview
For this assignment you will utilise SPSS to conduct data analysis of Australian public service employee data in four specified areas, and then write a
ief report on each area. You will also respond to two short answer questions.
Related learning outcomes
This assignment assesses the following unit learning outcomes:
1. specify the objectives of an investigation in statistical terms
3. produce appropriate descriptions and visualisations of data distributions
4. estimate population parameters (proportions, means) using appropriate statistics and confidence intervals
5. select and conduct appropriate hypothesis tests for different population parameters (proportions, single sample means, difference of means for matched and independent samples)
6. describe the relationships between variables (co
elations, crosstabs, relative risk and odds ratios) and test the significance of these relationships
7. interpret the outcomes of data analysis to write a concise report on findings.
Assignment 2: Analysis of data - Part 1
Teaching period 3, 2018
STA10003: Foundations of Statistics
Assignment 2: Analysis of data - Part 1
Word limit: Maximum of five (5) pages (one page for each question)
Weighting: 20%
Due date: 5pm AEDT Friday 4 January 2019 (Week 7)
After you have read this information, head over to the Assignment 2 - part 1 Q&A discussion board to ask any questions and see what your peers are saying about this assignment.
Assignment overview
Assignment details
Scenario
You are a new graduate researcher at a social science and psychological sciences research institute. You have been given a dataset based on the most recent Australian Public Service Commission Census 2016, which is a survey of Australian Public Service Sector Employees and asked to analyse the data to answer several questions of interest that are presented on the following pages.
You will use the data set provided for you in the Supporting resources section.
Data preparation
For the purpose of your report, you must use SPSS to draw a random sample of 1500 of the 4352 observations. You will conduct your analysis on this sample of 1500. Instructions on how to generate your random sample are on pages four (4) to seven (7) of this document. Once you have drawn your random sample, you may need to modify your data for the binomial test. The instructions of which are provided on page eight (8). Note, however, that some variables contain missing values. Therefore, each of your analyses might not contain the entire 1500 cases.
Data analysis
For your assignment, you are required to complete the first four questions by producing the appropriate analyses and writing the relevant report for each question. You are also required to complete Question 5, which contains two short answer questions. The reports should follow the format of the model reports provided in the Additional resources section. For each of the first four questions requiring SPSS, you should include the relevant output (e.g. tables, confidence interval calculations and graphs) with your report.
You are required to produce the following sets of analyses. Each analysis should be accompanied by a
ief report (each report should be no more than one page).
Page
Description
Instructions
1
The variable ‘WorkEnjoyment’ indicates the extent to which each employee agrees with the statement 'I enjoy my work'.
Produce the relevant graph and table to summarise the ‘WorkEnjoyment’ variable and write a paragraph explaining the key features of the data observed in the output in the style presented in the course materials.
2
The variable ‘JobEngagement’ is a scale measurement that indicates how engaged an employee is with the job they work in. This variable was measured on a scale that can take values from 0 to 20, with higher values representing greater employee engagement with their job.
Produce the relevant graph and tables to summarise the ‘JobEngagement’ variable and write a paragraph explaining the key features of the data observed in the output in the style presented in the course materials.
3
The variable ‘Bullied’ indicates whether or not an employee has reported being bullied at work. An occupational health and safety researcher at the institute hypothesised that more than 13.7% of Australian public service staff have reported being bullied at work.
Conduct a binomial test using the ‘Bullied’variable to test the researcher's claim. Produce the relevant output and write a binomial test report based on your output in the style presented in the course materials.
4
The variable ‘TeamEngagement’ is a scale score (0 to 20) of how engaged an employee is with the team of colleagues they regularly work with, with higher values representing greater employee engagement with their team. Previous research indicates that Australian public service employees have an average 'team engagement' score of 14.5. However, an organisational psychologist at the institute has claimed that this has decreased due to changes made by the cu
ent government.
Conduct a One-sample t-test using the ‘TeamEngagement’ variable to test this claim. Produce the relevant output and write a One-sample t-test report based on your output in the style presented in the course materials. Include the relevant output with your answer.
Short answer questions
5 (a)
A researcher wants to investigate the percentage of public service employees who are cu
ently working more than 40 hours per week. The researcher hypothesised that more than 21% of public service employees are cu
ently working more than 40 hours per week. A random sample of public service employees is obtained and each person is asked if they are cu
ently working more than 40 hours per week ('yes' or 'no').
What type of hypothesis test would be appropriate to investigate the researcher's hypothesis?
5 (b)
The researcher hypothesised that more than 21% of public service employees cu
ently work more than 40 hours per week. He conducted the appropriate hypothesis test and obtained a p-value of XXXXXXXXXXBased on this result, he concludes that exactly 21% of public service employees cu
ently work more than 40 hours per week.
Comment on the validity of his conclusion. Provide justification for your conclusion.
Checklist
Question 1 should include [as appropriate]:
· A graph and frequency output appropriate for a categorical variable.
· A paragraph that includes mention of largest group, smallest group, spread of percentages and proportions (as appropriate), and any other relevant patterns based on the model reports from the learning materials.
Question 2 should include [as appropriate]:
· A graph and explore output appropriate for a metric variable.
· A paragraph that includes a description of the centre, spread, outliers if present, and shape of distribution based on the model reports from the learning materials.
Question 3 should include [as appropriate]:
· The binomial test output and all other output produced to answer the question.
· A paragraph that reports the results of the binomial test following the format of the model reports from the learning materials.
Question 4 should include [as appropriate]:
· The One-sample t-test output and all other output produced to answer the question.
· A paragraph that reports the results of the One-sample t-test following the format of the model reports from the learning materials.
Question 5:
The answers should be presented with sections (a) and (b) clearly identified.
Overall check:
· The co
ect variable is used to produce output.
· The co
ect procedure is performed.
· Graphs appropriately edited and labelled (e.g. edited variable names; 'Figure 1. The distribution of …').
· Co
ect test values used.
· All figures quoted in the report are co
ect according to your own output.
· Includes 95% confidence interval interpretations where appropriate.
· Significance interpreted co
ectly (i.e. check that you are not saying the finding is significant when it is not or vice versa).
· Co
ectly refe
ing to the sample or population where appropriate.
· Proofreading of reports for e
ors.
Assignment Criteria
1. Summary of categorical variable.
2. Summary of metric variable.
3. Binomial test.
4. One-sample t-test.
5. Short answer question #1
6. Short answer question #2.
Please note that the following guide may look different to the ones you have encountered in the rest of your course or in this unit. You will be awarded marks for each of the elements present. Your total grade for this assignment will still be expressed as a percentage.
Your work will be assessed using the following marking guide:
Criteria
0 marks
1 mark
2 marks
3 marks
4 marks
Summary of categorical variable
(4 marks)
Inappropriate graphs or tables used.
Appropriate graphs and tables for categorical data.
No report.
Appropriate graphs and tables for categorical data.
Reasonable attempt to summarise the information shown in the output.
Appropriate graphs and tables for categorical data.
Graphs suitably edited for presentation (e.g. figure title).
Written summary covers all relevant features of output.
Appropriate graphs and tables for categorical data.
Graphs suitably edited for presentation (e.g. figure title).
Written summary covers all relevant features of output and is clearly and concisely written.
Summary of metric variable
(4 marks)
Inappropriate graphs or tables used.
Appropriate graphs and tables for metric data.
No report.
Appropriate graphs and tables for metric data.
Reasonable attempt to summarise the information shown in the output.
Appropriate graphs and tables for metric data.
Graphs suitably edited for presentation (e.g. figure title).
Written summary covers all relevant features of output.
Appropriate graphs and tables for metric data.
Graphs suitably edited for presentation (e.g. figure title).
Written summary covers all relevant features of output and is clearly and concisely written.
Binomial test
(4 marks)
Inco
ect procedure and/or no report.
Co
ect procedure, however with an inco
ect variable or comparison and/or major e
ors in report.
Co
ect output.
Report presented following format used in course materials.
Report has no major e
ors, but more than one or two minor e
ors.
Co
ect output.
Report presented following format used in course materials.
Report has only one or two minor e
ors.
Co
ect output.
Report presented following format used in course materials.
Report has no e
ors or minimal minor e
ors only and is clearly and concisely written.
One-sample t- test
(4 marks)
Inco
ect procedure and/or no report.
Co
ect procedure, however with an inco
ect variable or comparison, and/or major e
ors in report.
Co
ect output.
Report presented following format used in course materials.
Report has no major e
ors, but more than one to two minor e
ors.
Co
ect output.
Report presented following format used in course materials.
Report has only one to two minor e
ors.
Co
ect output.
Report presented following format used in course materials.
Report has no e
ors or minimal minor e
ors only and is clearly and concisely written.
Short answer question #1
(1 mark)
No attempt or is inco
ect.
Co
ect.
Not applicable.
Not applicable.
Not applicable.
Short answer question #2
(3 marks)
No attempt or is inco
ect.
Co
ect conclusion.
Co
ect conclusion, partial justification.
Co
ect conclusion, full justification.
Not applicabl