W1 L2 Data, Variables & Types of Quantitative Data

“Data” = recorded pieces of information collected to answer a question, describe a phenomenon, or test a hypothesis.
Two major categorical groupings
- Qualitative data: descriptive, non-numeric, language-based representations (e.g., asking “What are your barriers to exercising today?” in an interview).
- Quantitative data: numeric representations (e.g., grade-point average, minutes of moderate activity captured by Fitbit).
Both approaches typically collect responses from multiple people, then look for “average” patterns:
- Qualitative → thematic average (shared themes such as environmental barriers).
- Quantitative → numerical average (e.g., mean 19 minutes of moderate exercise across 200 people).

Modern life is “bathed” in numbers: social media metrics, newspaper statistics, everyday conversations.
Numerical summaries (especially aggregated statistics) communicate complex reality succinctly.
Real-world media examples referenced (single day of Australian news):
- Australia’s unemployment rate falls to 4\% (lowest since 02/2008) → description + historical comparison.
- Great Barrier Reef suffers the 6^{th} mass bleaching event → numeric count indicates severity/progression.
- Sports pages saturated with player and match statistics.
- COVID-19 dashboards: vaccination counts relative to eligible population.
Course emphasis: mainly quantitative methods but will also introduce qualitative analysis.

Only two possible values (e.g., Yes/No, 0/1, 1/2).
Always discrete—no decimal points.
Also called dichotomous variables/factors.
Example questions used in class illustration:
- “Do you have a pet dog?” (Yes=1, No=0)
- “Have you ever seen a Bermasco dog?”
- “Are you a veterinarian?”
Sample dataset (7 participants) demonstrated: participant ID + three binary columns.

Whole-number counts; more than two levels (can be few or thousands).
Still discrete (no decimals).
Example classroom survey:
- “How many children are in your class?” (values like 24,25,30)
- “What year level are you in?” (2,5,6)
- “How many year levels have you attended this school?”
Sample dataset of 7 students showed variability and logical patterns (older students could still have fewer years at the school due to changing schools).

Values can take any point along a scale, including decimals.
Synonym: continuous data.
Café example (Glenelg) measured across seven different dates:
- Maximum daily temperature (\approx 14.7^{\circ}C – 34.2^{\circ}C).
- Kilos of ice-cream sold (0.7–5.1 kg).
- Kilos of hot-chocolate mix used (0.3–4.2 kg).
Patterns discovered:
- Warmer days → more ice-cream, less hot-chocolate.
- Colder days → opposite trend.

Variable (a.k.a. factor): a measurable characteristic that varies (≥2 possible values).
- Examples in one-school study @ 2 p.m.: height, country of birth, sleep quality, academic performance.
- Each stored as a column in a data set.
Constant: characteristic that does not vary within the study context.
- School (single girls’ school), gender (all girls), time of measurement (always 2 p.m.).
Key principle: If there is no variability, statistical analysis is impossible; thus, constants are excluded from variable lists.

Discrete: finite or countably infinite set of separate values (integers). Examples: binary and integer data.
Continuous: uncountably infinite values within an interval (real numbers with decimals).

Quantitative summaries aid public understanding but can oversimplify; critical thinking needed (the course will teach how to “understand, think about, and question” numbers).
Multiple terminology synonyms exist (binary = dichotomous, variable = factor). Awareness prevents confusion.

Distinguish qualitative vs. quantitative data.
Recognize ubiquitous presence of quantitative information in media & everyday life.
Classify quantitative data into binary, integer, or real-number types.
Identify whether a study element is a variable or a constant.
Remember discrete ↔ continuous distinction.
Be comfortable reading raw data tables and relating each column to its variable type.

Subsequent course material: deeper statistical thinking, data organization, variable scaling, and both quantitative & limited qualitative analytical techniques.