Statistics Chapter 1 - Unit 1.3 Vocabulary

Vocabulary flashcards covering sampling methods, study designs, experimental terms, errors, and ethics in statistics.

Observational study

A study in which researchers observe and measure characteristics without attempting to modify the individuals being studied.

Experiment

A study in which researchers apply or assign a treatment and then observe its effect on the subjects.

Cross-sectional study

An observational study in which data are observed, measured, and collected at one point in time.

Retrospective study

An observational study in which data are collected from the past by examining records, interviews, or recollections.

Prospective study

An observational study in which subjects or groups are followed forward in time and data are collected as events occur.

Random sampling

A sampling process where individuals are selected by a random process; in a simple random sample of size $n$, every possible sample of size $n$ has the same chance of being selected.

Systematic sampling

A sampling method where a starting point is selected and then every $k\text{th}$ member of the population is chosen.

Convenience sampling

A sampling method that uses individuals who are easiest or most readily available to reach.

Stratified sampling

A sampling method where the population is divided into strata and individuals are randomly selected from every stratum (some from all groups).

Cluster sampling

A sampling method where the population is divided into clusters, entire clusters are randomly chosen, and all members in the selected clusters are included (all from some groups).

Treatment

A condition or intervention applied to subjects in an experiment.

Experimental unit / subject

The individual, object, or entity to which a treatment is applied; human experimental units are commonly called subjects.

Control group

A comparison group that does not receive the active treatment or receives a standard or placebo treatment.

Placebo

An inactive treatment designed to resemble the real treatment.

Placebo effect

A response caused by a subject's belief that they received an effective treatment rather than by the treatment itself.

Randomization

The process of using a random process to assign subjects to treatment groups.

Replication

Using enough subjects or repeating an experiment so treatment effects can be detected more reliably.

Blinding

A procedure where the subject does not know which treatment they received.

Double-blind

A study design where neither the subjects nor the people evaluating or administering the treatments know who received which treatment.

Completely randomized design

An experimental design in which subjects are randomly assigned directly to treatment groups.

Randomized block design

An experimental design in which subjects are first divided into blocks of similar subjects, then randomly assigned to treatments within each block.

Matched pairs design

An experimental design in which subjects are paired by similarity, or the same subjects are measured under two conditions.

Lurking variable

A variable not included in the study that may affect the relationship between the variables being studied.

Confounding

A condition that occurs when the effects of two or more variables cannot be separated, making it unclear which variable produced the observed effect.

Sampling error

The difference between a sample result and the true population result that occurs solely because only a sample was observed.

Nonsampling error

An error not caused by random sampling, such as incorrect data, recording errors, biased questions, false responses, inappropriate analysis, or biased conclusions.

Voluntary response bias

Bias occurring when people who choose to participate differ from people who do not.

Nonresponse bias

Bias occurring when people selected for the sample fail to respond, and their characteristics differ from responders.

Interviewer bias

Bias that occurs when an interviewer's wording, tone, behavior, or expectations influence responses.

Loaded question

Question wording or assumptions that push respondents toward a particular answer.

Cherry picking

Selecting only data or results that support a desired conclusion while ignoring contradictory evidence.

Falsified data

Data that are fabricated or deliberately altered.

Inappropriate statistical methods

Statistical methods that do not fit the data or study design and can create misleading results.

Conflict of interest

A financial or personal interest that may influence the study or its interpretation.

Ghostwriting

A practice where a substantial contributor to a research paper is not properly acknowledged as an author.

Financial support disclosure

The reporting of relevant funding and financial support for a research study.

Informed consent

The process where human subjects voluntarily agree to participate after being informed of relevant risks and procedures.