Research Methods in Health Science Exam 2

generalizability

External validity is really all about ensuring…

target (theoretical)

Type of population that we are interested in studying

accessible (sampling frame)

Type of population who we could potentially sample

selected sample

Type of population who we sample

actual sample

Type of population who participates in our study

population validity

Are the people in our study similar to the people we want to generalize to?

ecological validity

Do the conditions of the study resemble the real-world environments in which the findings are meant to apply?

simple random, systematic random, stratified random, cluster

Probabilistic sampling techniques (4)

convenience, quota, purposeful, snowball

Non-probabilistic sampling techniques (4)

simple random

Technique whereby everyone in the population has an equal chance of being selected for the sample

systematic random

Draws a random sample from the target population by selecting units at regular intervals starting from a random point

stratified random with equal proportions

Randomly selecting a sample from within certain strata, or subgroups within the population. Each subgroup is separated from the others based on a common characteristic. We end up with a different number of people in each group

stratified random with unequal proportions

Randomly selecting a sample from within certain strata, or subgroups within the population. Each subgroup is separated from the others based on a common characteristic. We end up with the same number of people in each group

cluster

Dividing the target population into groups, called clusters, then randomly selecting a subsection of these groups to form your sample

convenience

Simply recruiting anyone you have access to

quota

Separating people into groups and then enrolling anyone willing to participate in the study

purposeful

People who are considered “experts” on the topic of interest are identified and recruited for the study

snowball

Iterative process whereby the researcher establishes trust and rapport with person/persons who have knowledge about the topic but are otherwise distrustful or hard to contact

homogenous sample (restricted)

When samples lack diversity in age, socioeconomic status, education, culture, or lived experience, they fail to capture the natural variability in the broader population

context specificity

Context influences how people interpret questions, respond to interventions, and interact with researchers

self-selection

Volunteers often differ systematically from nonparticipants in ways directly related to the research topic

underrepresented subgroups

Although exclusion criteria can reduce heterogeneity and strengthen internal validity, they also narrow the population to which findings apply

periodicity

The fixed interval or repeating pattern in how units are selected from an ordered list

oversampling

Selecting more participants from a specific subgroup than would occur through random sampling

internal

Validity measuring whether a study accurately shows a cause-and-effect relationship

external

Validity measuring whether the results can be generalized beyond the study

pre-test (baseline)

A measurement taken before starting an experiment or intervention

matched pairs

Participants are paired based on shared characteristics to control variability and reduce the influence of confounding variables

blinding

A research technique where participants do not know if they are in the treatment group or the control group

double blind

A research technique where neither the participants nor the researchers know which participants are in the treatment group or the control group

between-subjects

An experimental design comparing one group of participants to another, completely different group of participants

within-subjects

An experimental design involving using one group of participants and comparing them to themselves

crossover

A type of experimental design where participants experience multiple experimental conditions in a particular sequence

washout period

A deliberately scheduled gap between stopping one treatment and starting another, allowing the first intervention to clear from the body so its effects do not interfere with the assessment of the next one

dependent

Researchers should prioritize matching on characteristics related to the ____ variable

regression to the mean

The natural tendency for subjects who happen to score extremely low or extremely high on an initial test because of luck or chance to score closer to the group average on subsequent tests regardless of the intervention

attrition bias

When there are systematic differences between the groups because subjects from one group have disproportionately dropped out or have been excluded during follow-up

allocation bias

When there are systematic differences in how subjects are assigned to the treatment and comparison/control groups

testing

When fatigue or possible carryover effects occur between the pre-test and post-test

maturation

When subjects naturally change as a function of time rather than due to the independent variable

history

When something external happens right before the story or between the pre-test and post-test that alters how a subject responds to the assessment

performance bias

When subjects change their behavior after realizing they are or are not getting the intervention, or when researchers provide different care to the groups because they know which group they belong to

detection bias

When researchers inconsistently assess the outcome because they expect a certain outcome from the subject

true

True or false: for there to be attrition bias, there must be a significant difference between the dropout rates across groups

exposure variable (risk variable)

Any biological, behavioral, environmental, social, or medical factor that may influence a person’s likelihood of developing a health-related condition

outcome variable (disease variable)

The health-related state or event we are interested in measuring or explaining

prospective cohort

Identifies people who are or are not exposed to something in the present, then follows those people over time to determine disease rates for each group in the future

retrospective cohort

Identifies people who were or were not exposed to something in the past, then follows up in the present to determine disease rates for each group

case-control

Identifies people who presently either have or don’t have a disease, then determines the incidence of exposure to something in the past

cross-sectional

Exposures and outcomes are collected at a single point in time (or over a very short time window) in a defined population

relative risk

The ratio of the probability of a disease or outcome occurring in an exposed group compared to the probability of the disease or outcome occurring in a non-exposed group. Time element

odds ratio

The ratio of the odds of exposure for people with the disease compared to the odds of exposure for people without the disease

prevalence ratio

Measure of association that compares the prevalence of an outcome in an exposed group to the prevalence of the same outcome in an unexposed group. No time element

risk/exposure, disease/outcome

In the 2×2 table for the different odds ratio, etc. calculations, this factor is on the left while this factor is on the top

cohort

Relative risk is typically used for this kind of study

case-control, cross-sectional (sometimes cohort but it is misleading)

Odds ratio is typically used for these kinds of studies

cross-sectional

Prevalence ratio is typically used for this kind of study

nominal

Simplest form of data whereby options are only categorized and therefore have no intrinsic numerical value

ordinal

Options can be ranked in some order but the interval from one option to the next varies and therefore mathematical principles cannot be applied

interval

Options are not only rank ordered but also have equal intervals between each category

ratio

Options are rank ordered, equidistant, and utilize a true zero (zero actually means none or nothing)

interval and ratio

We can use parametric statistics for these two types of data

ratio

The only type of data that can be multiplied and divided

nominal/ordinal, interval/ratio

These two types of data are discrete, while these two are continuous

reliability

Refers to the consistency of the test or measure

validity

Refers to the accuracy of the test or measure

inter-rater reliability

How consistently raters evaluate or judge an independent variable

test stability

Whether the measure is stable over time

internal consistency

How well the items on the measure work together to produce similar scores

inter-rater reliability

Ensure raters do not influence each other, determine how many raters you want

pearson’s correlation, cohen’s kappa, intraclass correlation coefficients

Three ways to measure inter-rater reliability

test stability

Consider that some constructs naturally change anyway and how long to wait between tests

pearson’s correlation, intraclass correlation coefficients

Two ways to measure test stability

internal consistency

How to split the test (odd/even, split-half)

cronbach’s alpha, McDonald’s omega

Two ways to measure internal consistency

face validity

You look at the items and see whether “on its face” it seems like a good translation of the construct

content validity

Addresses how well test questions match the content or subject area they are intended to assess

predictive validity

Tells you how well a certain measure can predict future behavior or performance

convergent validity

The degree to which a construct measure converges with other measures that should be measuring the same thing

discriminant validity

The degree to which a construct measure diverges from other measures that purport to be measuring something different

face and content

Types of foundational validity (2)

predictive, convergent, and discriminant

Types of prognostic validity (3)