Week 1 : Health Research: Definitions, Study Designs, Variables, Validity, and Bias

What is health research?

Systematic inquiry used to generate or apply knowledge that improves health.

What are the 5 purposes of health research?

Description, association, prediction, causation, and evaluation.

What is quantitative research?

Research that uses numbers/statistics to study relationships among variables.

What is qualitative research?

Research that uses words, stories, or experiences to describe, explain, or understand a phenomenon.

What is the easiest way to remember quantitative vs. qualitative?

Quantitative = numbers; Qualitative = experiences/words.

What is the target population?

The larger population the researcher ultimately wants the findings to apply to.

What is the accessible population?

The portion of the target population the researcher can actually access.

What is a sample?

The people who actually participate in the study.

What does external validity mean?

Generalizability — who the study results can be generalized to.

What question should I associate with external validity?

"Who can we generalize the results to?"

What are the three observational study designs listed in the Week 1 slides?

Cross-sectional, case-control, and cohort.

What experimental study design is listed in the slides?

Randomized Controlled Trial (RCT).

What study design is associated with measuring prevalence at one point in time?

Cross-sectional.

What are the evidence-synthesis designs listed in the slides?

Scoping/systematic reviews and meta-analyses.

What is a nominal variable?

A variable consisting of names/categories with no ranking.

What is an example of a nominal variable?

Blood type.

What is an ordinal variable?

Categories that have a meaningful order/rank.

What is an example of an ordinal variable?

Pain severity (mild, moderate, severe).

What is a discrete variable?

A numerical variable that can be counted.

What is an example of a discrete variable?

Number of hospital visits.

What is a continuous variable?

A numerical variable that is measured.

What is an example of a continuous variable?

Blood pressure.

What shortcut can I use for the four variable types?

Nominal = Name; Ordinal = Order; Discrete = Count; Continuous = Measure.

What is validity?

Whether something measures what it is supposed to measure.

What is reliability?

Consistency of a measurement.

What is the easiest way to remember validity vs. reliability?

Validity = right thing; Reliability = repeatable/consistent.

A scale gives the same incorrect weight every time. Is it reliable?

Yes. It consistently produces the same result.

A scale gives the same incorrect weight every time. Is it valid?

No. It isn't accurately measuring what it is supposed to measure.

What does bias mean in research?

A systematic error that can affect the study's results.

What are the three selection biases listed in the slides?

Sampling bias, volunteer bias, and attrition bias.

What is recall bias?

Error caused when participants cannot accurately remember past information.

What is observer bias?

Bias caused by the researcher's observations influencing how information is recorded or interpreted.

What is interviewer bias?

Bias that occurs when the interviewer influences participants' responses.

What is attrition bias?

Bias related to participants dropping out of a study.

What is confounding?

An outside factor associated with both the exposure and outcome that distorts their true relationship.

What two words should immediately come to mind when I see "confounding"?

Exposure + outcome.

Coffee drinking is associated with stress, but coffee drinkers also work longer hours and long work hours are associated with stress. What is the possible confounder?

Long work hours.