TECH3100 Data Visualisation in R | Case Study Analysis – Solved Study Guide
This guide walks you through every section of TECH3100 Data Visualisation in R Assessment - Case Study Analysis. You'll see exactly how a strong submission approaches dataset selection, data import, exploration, descriptive statistics, R code documentation, and the all-important interpretation and recommendations section. Whether you're stuck on where to start or just want to see what a high-scoring response looks like, you're in the right place.
Inside you'll find the full solved analysis using the diamonds dataset from ggplot2, annotated R code walkthroughs, scoring tips drawn directly from the rubric, common mistakes to avoid, and a quick revision checklist. By the end, you'll know not just what to submit - but why every part of it earns marks.
ASSESSMENT OVERVIEW
This assessment requires you to develop a case study demonstrating your ability to evaluate and apply standard statistical techniques using R within a marketing context.
- Dataset selection (~200 words)
- Data import and preparation (~250 words)
- Data exploration (~300 words)
- Descriptive statistics (~300 words)
- R code documentation (~200 words)
- Interpretation and recommendations (~450-500 words)
- Submission: Word/PDF report + .R file
Case Study:
You have been hired as a data analyst for a marketing research company. Your task is to analyse a dataset to derive insights and make data-driven recommendations for a marketing campaign. The dataset provided contains information about customers, their demographics, purchasing behaviour, and campaign response.
Step 1: Dataset Selection: Choose a suitable dataset from publicly available datasets commonly used with R. Some popular options include:
- "mtcars": This dataset contains information about various car models, including variables such as horsepower, miles per gallon (MPG), and number of cylinders.
- "iris": This dataset includes measurements of different iris flower species, including variables like petal length, petal width, and sepal length.
- "diamonds": This dataset contains information about diamonds, including variables such as carat weight, cut quality, and price.
- Or you may use a dataset specific to your chosen industry or field of interest. Ensure that the dataset has sufficient variables and diversity to allow for the application of a range of statistical techniques.
Tip: Markers award HD (2/2) for 'creativity and innovation in dataset selection.' Simply using diamonds is fine, but if you can briefly explain why it mirrors real luxury consumer behaviour, you signal insight - that's the difference between a Credit and a Distinction.
Step 2: Data Import: Import the chosen dataset into R using appropriate functions or libraries.
Include the necessary code for dataset importation in your submission.
Tip: Don't just paste the import code without comment. The rubric explicitly rewards 'optimised importation code' at Distinction and 'additional enhancements' at HD. Add a comment line explaining what the data contains after import - one sentence is enough.
Step 3: Data Exploration: Perform exploratory data analysis by examining the structure, summary statistics, and visualisations of the dataset. Utilise appropriate techniques covered in the subject (Weeks 1, 2, and 3) to gain insights into the dataset.
Tip: The rubric distinguishes between 'basic' (Pass) and 'thorough' (Distinction) exploration. Basic is just str() and summary(). Thorough means adding visualisations - at minimum a histogram of price and a boxplot by cut quality - and actually commenting on what they reveal about the distribution.
Step 4: Descriptive Statistics: Calculate and present descriptive statistics, including measures of central tendency, measures of dispersion, and relevant statistical summaries for key variables in the dataset. Utilise appropriate R functions and techniques to perform these calculations.
Tip: This criterion carries 5 marks - the joint highest in the rubric. Most students lose marks here by presenting statistics without interpretation. Don't just report numbers. Explain what they mean for the marketing campaign. Markers want to see you connecting the data to decisions.
Step 5: R Code Documentation: Document your R code using comments to explain the purpose and functionality of each step in the analysis. Ensure that your code is well-structured, readable, and easily understandable.
Tip: Remember: you must submit your R code as a separate .r file (not .R, not inside the Word doc). Zipped files are not accepted. Get the file extension right - minor admin errors like this cost easy marks.
Step 6: Interpret the results obtained from the statistical analysis in the context of the marketing campaign. Clearly explain the insights or conclusions drawn from the analysis and provide data-driven recommendations for the marketing strategy based on your findings. You will present this in the case study report.
Tip: Interpretation and Recommendations also carries 5 marks - the joint highest criterion. Weak students list statistics again. Strong students translate every key finding into a concrete marketing action. Use the rubric language: markers want 'comprehensive, strategic recommendations that demonstrate exceptional understanding of the marketing problem.'
Want the Full Solved Solution for TECH3100 Data Visualisation in R assessment?
This guide covers the complete solved case study - all six steps, full R code with inline comments, APA 7 reference list, and descriptive statistics tables ready for submission. Everything is structured exactly as required by the Kaplan marking guide. Get the complete assignment package including all tasks, detailed analysis, and formatted content ready to submit.
How to Score High on TECH3100 Data Visualisation in R Assessment?
- Justify dataset selection with both statistical and marketing relevance
- Use multiple visualisations and explain each insight clearly
- Apply appropriate statistical techniques (not just basic summaries)
- Interpret results in direct relation to the marketing scenario
- Provide recommendations that are clearly supported by data
- Ensure R code is clean, structured, and well-commented
- Demonstrate depth in analysis rather than surface-level observations
- Use professional report structure with clear headings
- Maintain logical flow from analysis → insight → recommendation
Why Students Struggle with This Assessment
- Descriptive statistics without context: Students run summary() and copy-paste the output. Markers aren't impressed by raw R output - they want you to interpret what the numbers mean for the marketing scenario. Always translate statistics into business language.
- Weak or generic recommendations: Listing 'target high-value customers' without specifying which variables identify them (carat > 1.5, cut = Ideal) earns basic marks at best. Your recommendations must be directly traceable to your analysis.
- Undocumented R code: Submitting code without comments is an automatic hit on the 3-mark R Code Documentation criterion. Even simple lines deserve a comment explaining why they're there.
- Confusing exploration and descriptive statistics: The assessment has separate marks for Data Exploration (Step 3) and Descriptive Statistics (Step 4). Don't conflate them - exploration is about understanding the data structure; descriptive stats are about quantifying it precisely.
- Missing the .r file submission: The report and the R code are two separate deliverables. Many students submit only the report. The R code must be a standalone .r file submitted alongside the report.
Related Units
Frequently Asked Questions
Q: What exactly does this assessment require me to submit?
A: Two files: (1) a case study report in Word or PDF format, and (2) your complete R code in a .r file extension. Both are mandatory. The report should include your introduction, dataset details, step-by-step explanation of the analysis, visualisations, interpretation of results, and data-driven marketing recommendations. The .r file is submitted separately and must be well-commented. Zipped files are not accepted.
Q: Which dataset should I use for the best marks?
A: Any dataset from the approved list (mtcars, iris, diamonds) or a field-specific one can work. The rubric awards HD for datasets that 'demonstrate creativity and innovation.' The diamonds dataset is recommended because it includes both continuous (price, carat) and categorical (cut, color, clarity) variables, enabling a broader range of statistical techniques including correlation, distribution analysis, and category-level comparisons - all of which are expected in a strong submission.
Q: Can I use Generative AI (like ChatGPT or Claude) for this assessment?
A: Yes - this assessment is Level 2 GenAI, meaning use is optional but permitted for research and content generation. However, you must reference any GenAI tool used exactly as you would any other source, and you must include an appendix documenting all prompts and responses used. Undisclosed use of GenAI may result in academic misconduct penalties including a mark of zero.
Q: How detailed does my R code documentation need to be?
A: At a minimum, you need comments explaining the purpose of each major section (Credit level). For Distinction, every step should be commented with its purpose and functionality. For HD, your comments should provide 'exceptional clarity and detailed explanations' - essentially, someone unfamiliar with your analysis should be able to read just your comments and understand exactly what you did and why. Think of it as annotated code, not just labelled code.