BUSINFO700 Chap.1 Business Problems, Big Data and the R Workflow
Business Problems, Big Data and the R Workflow
This chapter sets up the habit the whole course rewards: begin with the business decision, identify the evidence that could change it, and only then choose an analysis. It summarises the course description and its six learning outcomes, then introduces the R environment that every lab uses.
You will see why the labs value R for business work, including reproducible scripts that rerun on new data, and where its main risk lies, which is the silent error that produces output without a warning. A worked example builds numeric vectors and a factor, shows that R sorts factor levels alphabetically, and handles a missing value without hiding a smaller denominator.
The chapter closes with the course's argument for describing data before modelling it.
What this chapter covers
- 01
A managerial view of small and big data
- 02
The six course learning outcomes
- 03
Why the labs use R and RStudio
- 04
Vectors, factors, data frames and lists
- 05
Missing values and silent errors
- 06
Describing data before modelling it
Worked example · free
Clean a coded value before explaining the result to managers
- 1Import and summarise first: the raw mean is (32 + 28 − 1 + 35 + 30) / 5 = 124 / 5 = 24.8 minutes, and the minimum of −1 is impossible for a duration.
- 1Inspect the code book: −1 marks a failed scan, so it is a missing value, not a fast delivery. Recode it as NA.
- 1Recompute with na.rm = TRUE: (32 + 28 + 35 + 30) / 4 = 125 / 4 = 31.25 minutes over four deliveries.
- 1Explain to managers that the typical time is about 31 minutes, based on four of five deliveries, and that one record needs follow-up.
Key terms
- Reproducible analysis
- An analysis saved as code so that anyone can rerun every step and obtain the same output.
- Factor
- R's data type for categorical variables, storing each value as one of a fixed set of levels.
- Data frame
- A table of equal-length columns, possibly of different types, holding one row per observation.
- Silent error
- A coding mistake that R executes without a warning, so wrong output looks legitimate.
- Missing value
- An absent observation, recorded in R as NA, which by default makes summary functions return NA.
Business Problems, Big Data and the R Workflow FAQ
Do I need prior programming experience for the R labs?
The first lab starts from installing R and RStudio and builds up from the console, the four RStudio panes and the working directory to vectors and data frames. Code is scaffolded step by step, and the notes point to the free online book R for Data Science and to each function's help page.
Why does R list my factor levels in an odd order?
R sorts factor levels alphabetically unless you specify them, so a three-level variable such as low, medium and high comes out as high, low, medium. Set the order with the levels argument whenever the categories have a natural sequence, as the Week 3 lecture does for age bands.
What is a silent error in R?
It is a mistake that runs without any warning, such as summarising the wrong column or forgetting how missing values were handled. The lab notes list it as one of R's main risks, and the remedy is to validate every output against what you expect before reporting it.
Why does the course start with simple statistics instead of machine learning?
The labs argue that descriptive and bivariate statistics show what is happening in the data, expose coding errors and outliers, and provide the checks needed to judge a complex model's output. A model is only as trustworthy as the data and assumptions behind it.
Which naming style should I use in my scripts?
The lab notes recommend snake_case, with words joined by underscores, for example monthly_sales or customer_age. Names must not start with a digit, contain spaces or special characters, or reuse reserved words such as TRUE or NULL. Descriptive names make a script easier for a marker or colleague to follow.
Assessment move
Install R and RStudio early and keep one tidy folder for the course, with the working directory set to it, so that every lab script finds its data without editing paths. Retype the Lab 1 commands yourself rather than pasting them; typing forces you to notice the assignment arrow, case sensitivity and the difference between a vector and a data frame.
For each new dataset, run a short checking routine before any analysis: the structure of the data frame, the summary of each column, the minimum and maximum of every numeric variable, and the levels of every factor. Write one comment line above each block of code saying what question it answers.
Finally, practise explaining one output in two sentences for a manager who will never see the code, because that translation is what the assessments reward.
Working through Business Problems, Big Data and the R Workflow in BUSINFO700? Sia is AskSia’s AI Statistics tutor — ask any BUSINFO700 Business Problems, Big Data and the R Workflow question and get a clear, step-by-step explanation grounded in how BUSINFO700 is taught and assessed. Read this chapter free, then take your hardest questions to Sia.
