Study Types & Questions
A study that records information from every single item or individual in an entire population.
What is a CENSUS?
A sampling method where units are chosen according to a random starting point and a fixed, periodic interval between selections.
What is systematic random sampling?
A nonrandom sampling method composed of individuals who are easiest for the researcher to reach.
What is a convenience sample?
An inactive treatment designed to look and feel identical to the real treatment being tested.
What is a placebo?
The practice of assigning more than one experimental unit to each treatment group to ensure consistent results.
What is replication?
A study where researchers actively assign conditions or treatments to experimental units to observe outcomes.
What is an EXPERIMENT?
A sample of size n selected in such a way that every possible sample of size n has the exact same chance of being chosen.
What is a simple random sample (SRS)?
A systematic error in sampling that results in a statistic consistently overestimating or underestimating a population parameter.
What is bias?
The variable whose categories or levels are deliberately imposed on experimental units in an experiment.
What is an explanatory variable (or factor)?
Keeping potential extraneous variables at the exact same settings across all experimental units.
What is direct control?
An observational study in which units are selected at a point in time, and data from the past is gathered about them.
What is a RETROSPECTIVE STUDY?
A sampling method where the population is divided into non-overlapping homogeneous groups based on shared characteristics, followed by an SRS within each group.
What is a stratified random sample?
A bias that occurs when a sample is composed entirely of self-selected individuals, usually favoring those with strong, negative opinions.
What is voluntary response bias?
The outcome variable measured on each experimental unit after a treatment has been administered.
What is a response variable?
The key design step required in an experiment to justify a cause-and-effect conclusion.
What is random assignment?
The component of an investigative question that identifies the parameter and direction for a hypothesis test or the goal of estimation for a confidence interval.
What is Component 2 (Parameter and direction)?
A sampling method where the population is divided into mini-versions of the whole, an SRS of entire groups is chosen, and data is gathered from every unit in those selected groups.
What is a cluster random sample?
A bias that occurs when the sampling process systematically excludes or underrepresents a specific portion of the population.
What is undercoverage bias?
An experimental design feature where neither the subjects nor the research staff interacting with them know who is receiving which treatment.
What is a double-blind (or double-masked) experiment?
An experimental design in which subjects are first grouped by an extraneous variable before treatments are randomly assigned within each group.
What is a randomized block design?
The critical process in data collection required if a researcher wants to generalize study conclusions to an entire population.
What is random selection?
A sampling strategy where a chosen unit is returned to the population prior to the next selection, allowing it to potentially be selected again.
What is sampling with replacement?
A bias that occurs when chosen individuals fail or refuse to respond, and their missing data differs systematically from respondents.
What is nonresponse bias?
A variable in an observational study that is associated with both the explanatory and response variables, offering an alternative explanation for their relationship.
What is a confounding variable?
A randomized block design with blocks of size two, where subjects are matched on a variable or each unit receives both treatments in random order.
What is a matched pairs design?