Data Production Notes #1

Population

The entire collection of individuals you want to learn about.

Sample

Part of the population that is selected for the study.

Parameter

The numerical value that describes a characteristic of a population.

Statistic

The numerical value that describes a characteristic of a sample.

Experiment

A study where the person conducting the study considers how a response behaves under experimental conditions.

Observational Study

A study where the person conducting observes characteristics of a sample selected from a population.

Hawthorne Effect

Noticing that employees work harder simply because management installed a camera.

Anecdotal Evidence

A personal account that is not scientifically proven.

Confounding Variables

Variables that may affect the outcome without being noticed, like age influencing both glasses and school performance.

Lack of Realism

Testing conditions that do not represent real-world scenarios.

Paired Sample

A sample where measurements are taken from the same subjects before and after an intervention.

Two Sample

Comparing averages between two independent groups.

Type 1 Error

A false positive result, such as a COVID-19 test indicating infection when the patient is healthy.

Type 2 Error

A false negative result, such as a cancer screening indicating no cancer when the patient actually has it.

Simple Random Sample (SRS)

Individuals are selected at random and without replacement.

Stratified Sample

Separate random samples are taken from groups of similar individuals within a population.

Cluster Sample

Randomly selects small groups (clusters) and samples all units within those clusters.

Systematic Sample

Selects from an ordered arrangement, starting randomly and then choosing every kth person.

Convenience/Haphazard Sample

A non-random sample based on ease of access.

Volunteer Sample

Participants volunteer to be part of a sample.