Introduction to Statistics and Data

Comprehensive vocabulary flashcards covering fundamental statistical concepts, data classification, study design, and software tools from Week 1: Introduction to Statistics and Data.

Statistics

The discipline of learning from data through collection, organisation, analysis, interpretation, and communication while recognising uncertainty; the term also refers to numerical summaries calculated from data.

Data

Recorded observations about people, objects, or events.

Observational Unit

A single entity or individual (such as one student) being observed or studied.

Variable

A recorded characteristic or attribute of an observational unit.

Observation

A recorded value of a variable for a particular observational unit.

Population

The complete set of units about which researchers want to draw conclusions.

Sample

The subset of units selected from a population for study.

Parameter

A numerical characteristic that describes an entire population.

Statistic

A numerical summary calculated from a sample, often used to estimate an unknown population parameter.

Descriptive Statistics

Statistical procedures used to organise and summarise observed data using tables, graphs, and numerical summaries.

Inferential Statistics

Statistical procedures that use sample data to draw conclusions about a broader population while accounting for uncertainty.

Census

A study or investigation that collects information from every single unit in the target population.

Sample Study

A study that collects information from a selected subset of the target population.

Selection Bias

A systematic error that occurs when the selection process systematically favours certain units over others in a way relevant to the research question.

Variation

The differences observed between values, which can occur between different units, within a single unit over time, or between different samples.

Confounding Variable

A variable related to both the explanatory variable and the outcome that can complicate the interpretation of their relationship.

Categorical Data

Data that represent groups, labels, or ordered categories, answering the question 'Which category?'.

Quantitative Data

Data that represent numerical counts or measurements, answering the question 'How many or how much?'.

Nominal Data

A subcategory of categorical data where the categories have no natural or meaningful order (e.g., transport mode, faculty, blood group).

Ordinal Data

A subcategory of categorical data where categories possess a meaningful order, though the gaps between categories are not necessarily equal (e.g., low, moderate, and high satisfaction).

Discrete Data

Quantitative data whose possible values form a countable set of distinct numbers (e.g., number of classes or purchases).

Continuous Data

Quantitative data where a variable can theoretically take any numerical value within an interval (e.g., travel duration, height, rainfall amount).

Interval Scale

A measurement scale with equal differences between values where zero is an arbitrary reference point rather than an absolute absence (e.g., temperature in Celsius).

Ratio Scale

A measurement scale featuring equal differences between values and a meaningful, absolute zero (e.g., travel duration).

Cross-sectional Data

Data collected from different units observed at or for the same point in time or reference period.

Time-series Data

Data where a variable is recorded for the same unit or location over successive points in time.

Primary Data

Data collected directly by the investigators specifically for the study at hand.

Secondary Data

Pre-existing data originally gathered for another purpose and reused for the current study (e.g., administrative records, published datasets).

Observational Study

A study in which researchers record existing characteristics or conditions without assigning treatments or manipulating conditions.

Experiment

A study design where researchers deliberately assign a treatment or condition to participants to evaluate outcomes and support causal conclusions.

Random Assignment

The process of allocating participants to different experimental treatments or conditions by chance, helping balance other characteristics on average.

Random Sampling

The process of selecting individuals from the population by chance to decide who enters the study.

Open-source Software

Software whose source code is released under licences that permit its use, modification, and redistribution by anyone.

R

An open-source programming language and software environment designed for statistical computing and graphics.

jamovi

An open-source statistical software package featuring an accessible graphical user interface.