Reference no: EM132240250 , Length: word count:3000
Assignment -
Introduction: The project will be based on a real-world problem using real data from a selected application.
Task: You are required to identify and contextualise a problem by using a large dataset and use SAS programming to solve this problem. You need to use a collection of real-world "raw" datasets and write multiple SAS programs that perform the steps involved in pre-processing, statistical analysis, reporting and comparison.
You need to choose a dataset where the dataset
- should have at least 2000 instances,
- should be related to Health or Environment domain,
- should include multivariate data,
The full functionality of the application is up to you but a brief project proposal (maximum two-pages) should be submitted to the Unit Leader for approval before you start your project. The proposal should be included as an Appendix in the final report and is not included in the word count. Submissions without a pre-approved proposal will not be accepted.
You are required to design, build, test and document a SAS application which will have the following steps:
- Data Collection and Preparation (download the data sets, clean and prepare the data).
- Pre-processing (write a SAS program to pre-process the raw data and create new files).
- Statistical Analysis (write a SAS program that calculates the results to solve the problem that you identified in your proposal and produces statistical reports for at least two comparable files.).
- Comparison (write a SAS program that compares the statistics such as by showing the similarities and differences).
Deliverables:
Project report - A report that explains the design and development of the project must be submitted by the deadline. The report should contain the problem definition, objectives, system design rationale, results, conclusions, etc. Please see the marking criteria for more details. You should briefly describe your code as well and it should be clear what each data/procedure step does and why it is necessary.
The report should not exceed 3000 words. You can use figures, diagrams, tables and screenshots to explain your system and these are not included in the word count. References and appendices are not included in the word count either.
SAS code - Your SAS code that implements the project requirements code should be attached as an appendix in your report. You should test your code with the SAS software before you submit to make sure it works. Correct use of SAS language constructs, code quality and professionalism will be marked. Please see the marking criteria for more details. A ZIP file containing the full running code should be submitted separately.
Presentation - Students will make a presentation to demonstrate their work and show the outcome. Student presentations have 15 minutes. There will be a 3-5 minute questions and answers part as well.
Attachment:- Assignment Files.rar