Assessment Instructions
Key Information:
| Assessment title: | Software Use / Statistical Analysis |
| Module Name: | Information Technology |
| Module Code: | |
| Tutor’s Name: | |
| Assessment will be set in: | |
| Assessment is due in: | |
| Assessment weighting: | 25% |
Assessment Task Instructions:
| Core Task: Assume that you have been asked by an organisation to collect and analyse data. You are required to submit a report detailing the statistical analysis of a dataset. To avoid you having to collect real data the dataset for analysis should come from those built into R. It must have a minimum of 4 columns and you should discuss your chosen dataset with your tutor to ensure its suitability for the assignment. In your report you should describe a (possibly hypothetical) scenario under which the data has been collected and throughout the report you should assume the reader has no technical knowledge of the topic, datatypes or R. To illustrate your understanding of computational data you should explain the dataset in terms of size, the datatypes used (e.g. real, integer) and the units of measurement. You should calculate the memory requirements for storing the dataset. State any assumptions you make. The plot(datasetName) function of R will yield a chart of the dataset. Include a screenshot of the chart(s) in your report. To show your understanding of interpreting statistical results you should explain the chart and the results it shows. The reader should not have to make any assumptions regarding the diagrams. You should write about any further statistical analysis of the data you have carried out. To show your understanding of R and how you have applied analysis techniques you should include any R script used in an appendix and also as a separate text file. Document the code assuming the reader has no technical knowledge. Having analysed the data you should state what business decisions could be made based on the results and what further data should be collected (and why). |
| Structure: Your report must include : Title page, contents page, page numbers Section 1: Introduction – 200 words maximum, introducing the company/organisation that the report is written for and why the data has been collected. State the name of the dataset you have chosen. Section 2: The dataset – 200 words maximum, describing the size of the dataset, the datatypes within it, the units of measurement (where applicable) and an estimate of the memory required to store the data (include calculations). Section 3: Plot description – 300 words maximum, describing the diagram produced by the default plot(datasetName) function in R for your chosen dataset; Section 4: Additional analysis – 500 words maximum, describing any further analysis of the data using inbuilt or custom written R code/script. Include a copy of the script as an appendix. You should aim to use multiple methods and extracts of the full R script to illustrate your understanding of the script and the results. Section 5: Summary – max 300 words, describing what business decisions could be made, if any, based on the results from sections 2, 3 and 4. Also state what further data should be collected and why. Section 6: Reference list (not included in the word count) Section 7: Appendix (R script) |
| Theory and/or task resources required for the assessment: You will need to use the R programming environment to access and analyse the data. Installation of R Open https://mran.microsoft.com/documents/rro/installation Integrate with Visual Studio 2015 (see notes here) https://docs.microsoft.com/en-us/visualstudio/rtvs/installing-r-tools-for-visual-studio#supported-versions-of-visual-studio Intro Tutorial https://docs.microsoft.com/en-us/visualstudio/rtvs/getting-started-with-r The datasets in R can be listed using the data command: >data() To view the data, type the name of the dataset, e.g. >ChickWeight To plot the data use the plot command e.g. >plot(ChickWeight) You will have to research the topic for your chosen dataset to provide general background information. The datasets are based on real research that can be found on the internet. Take care to reference this research material in the proper manner should you choose to use it. You are expected to calculate the memory requirements to store the dataset; you will need to understand the fundamental datatypes to do this. |
| Assessment reference style: As well as any literary references you should include references to any R script code used that is not sourced from the taught material (e.g. labs/lectures). References should be in the Harvard style. You do not need to include a bibliography. |
| Expected word count: Although there is no minimum wordcount you are expected to write no more than 1500 words. Note that this is a limit; not a target. Be succinct in your writing and avoid repetition. The Reference and Appendix sections are not included in the word count. You may write additional appendices as needed. Use diagrams, lists, tables to keep the word count to a minimum. |
Learning Outcomes Assessed:
| The following learning outcomes are assessed in this task: Identify the following accurately: integer, real/float, Boolean, character, string, date/time, records (or equivalent), arrays (or equivalent) Demonstrate a theoretical understanding of conditions and iteration structures Apply the fundamentals of number systems to computational data Use of programming software for statistical analysis of computational data |
Submission Requirements:
| You must type your assessment in Arial font 11, with single spacing. You must submit the assessment electronically (in docx/pdf format) via the VLE module page. Please ensure you submit it via Turnitin. Ensure you submit any R script files alongside the docx/pdf report. Please submit the report no later than the submission date stated in the Key Information section. As part of the submission you may be expected to explain sections of your report or R script in a short non-assessed viva. Assessments submitted after the submission deadline may incur penalties or may not be accepted. |
Assessment Mark:
| The assessment will be marked using the following weighted marking criteria: Introduction (15%) – how well you have framed the circumstances under which the dataset has been collected.The Dataset (15%) – how well you have described the dataset, the datatypes and calculated the memory requirements for the dataset and how clear you are in describing any assumptions you have made.The Plot (15%) – how well you describe (to a non-technical reader) what the plot function is showing and any assumptions you have madeAdditional Analysis (40%) – the relevance of the analyses you have made, why you have made them, the clarity of the expressed results and the clarity of any R Script descriptions.Conclusion (15%) – how well you link your conclusions and suggested business decisions to the results of the analysis. You will receive a % mark in each of these categories and your overall mark will be calculated as the sum. The overall mark will also be a percentage mark (0-100%). You should examine the marking criteria grid for further details of the marking. |
Assessment Feedback:
| Your tutor will mark the assessment and provide you with a written feedback sheet. You can use this feedback to guide your further learning on the module. |
