Why this chapter matters
Inference is only as credible as the data process. Good sampling and clear variable definitions prevent misleading conclusions.
What you will learn
- Distinguish population parameters from sample statistics.
- Classify variables as categorical or quantitative and identify their measurement context.
- Recognize common sources of bias and describe better sampling plans.
Lessons in this chapter
- Population, sample, and variablesSet up a statistical study using precise language for who and what is measured.
- Sampling methods and biasCompare random, stratified, cluster, and convenience samples and their risks. Read the full guide →
- Observational studies versus experimentsIdentify when a design supports association only or supports causal claims.
- Data quality checksScreen for missing values, outliers, and wording effects before analysis.
Study task
Draft a sampling plan for a campus survey on study time, including target population, method, and one likely bias with a mitigation step.
Chapter checkpoint
Why does a convenience sample weaken inference about a full population?
Because participants are chosen by ease of access, not random selection, so the sample can systematically differ from the population.