Introductory Statistics: Missing Data, Sampling Methods, and Study Designs

Vocabulary practice flashcards covering missing data, experimental design, sampling methods, and types of observational studies based on the lecture material.

Data values missing completely at random

A condition where the likelihood of a data value missing is independent of its value or any other value in the dataset.

Data values missing not at random

A condition where a missing value is directly related to the reason that it is missing.

Delete cases

A method of handling missing data by deleting entire subjects or participants with missing values from the dataset.

Imputing missing values

A method of handling missing data by substituting values, such as the mean of other values, a randomly selected similar value, or a regression estimate.

Subject

A human participant in a study or experiment.

Observational study

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

Experiment

A study in which researchers apply a treatment or influence to participants and proceed to observe its effects on them.

Experimental units

The individuals or items upon which an experiment is performed, referred to as subjects when they are human.

Placebo

A harmless and ineffective pill, medicine, or procedure used by researchers for comparison with active treatments.

Lurking variable

A hidden factor not included in a statistical analysis that affects the relationship between the variables being studied.

Replication

The repetition of an experiment on more than one individual to ensure the sample size is large enough.

Blinding

An experimental technique where the subject does not know whether they are receiving the treatment or a placebo.

Double blinding

An experimental setup where both the subject and the researcher do not know who received the treatment or the placebo.

Simple random sample

A sample of $n$ subjects selected in such a way that every possible sample of the same size $n$ has the exact same chance of being chosen.

Random sampling

A selection method where all members of the population have the same chance of being selected.

Systematic sampling

A sampling method where a starting point is selected, and then every $k^{\text{th}}$ element in the population is chosen.

Convenience sampling

A sampling method that simply uses data and results that are very easy to obtain.

Stratified sampling

A sampling method where the population is subdivided into at least two subgroups (strata) based on shared characteristics, and a sample is drawn from each subgroup.

Cluster sampling

A sampling method where the population area is divided into sections (clusters), some clusters are randomly selected, and all members from the selected clusters are chosen.

Multistage sampling

A study design that uses a combination of different sampling methods conducted across sequential stages.

Retrospective study

An observational study where data are collected from a past period of time, such as from historical records (also known as a case-control study).

Cross-sectional study

An observational study in which data are measured or observed at one specific point in time.

Prospective study

An observational study where data are collected forward in time by tracking groups sharing common factors (also known as a longitudinal or cohort study).