Research Methods in Health Science Exam 3

statistical significance testing

Communicates probability by telling us how likely the current result would be if the study’s null hypothesis were true. Do we think something happened?

random sampling error

The natural deviations that occur when randomly sampling from the population

bias

Flawed sampling procedures whereby the researcher does not use a representative sample

central limit theorem

For a sufficiently large sample size, the distribution of the sample mean becomes approximately normal with mean and variance regardless of the population’s original distribution.

mean of the population

In the central limit theorem, the mean of the sampling distribution becomes equal to the…

statistical significance testing

This helps quantify whether a result is due to chance or due to some factor of interest

type 1 error

When the researcher concludes the intervention worked, but it didn’t (false positive)

type 2 error

When the researcher concludes the intervention did not work, but it actually did (false negative)

power

The ability of the test to correctly reject a null hypothesis when it is false

p-value

A ____ less than or equal to alpha is statistically significant you reject the null hypothesis, or if it is greater you fail to reject the null hypothesis

sample size manipulation

Statistical significance testing is vulnerable to…

power analysis

A tool that helps researchers design studies that are large enough to detect meaningful effects, but not so large that small changes seem significant

effect sizes

Communicates strength by telling us the magnitude of the experimental effect, or the relationship/odds between variables. How big or small was the effect or relationship?

confidence intervals

Communicates precision by providing a range of plausible values for the population parameter being estimated. How sure are we about our finding?

cohen’s d or hedges’ g

These two estimate the magnitude of standardized differences between two groups means.

hedge’s g

This is more appropriate for small sample sizes than Cohen’s d because it provides a bias correction.

pearson’s r or point-biserial

Used to measure the effect size of a correlation or association (2)

pearson’s r

This measures the strength of a linear relationship between continuous variables

point-biserial

This correlation measures the strength between one dichotomous and one continuous variable

relative risk and odds ratio

Used to measure the effect size of a proportion (2)

-1, 1, 0

For pearson’s r and point-biserial, scores range from ___ to ___. A ___ indicates no effect

-2, 2, 0

For Cohen’s d and Hedges’ g, scores typically range from to with _ indicating no effect

0, infinity, 1

For relative risk and odds ratio, scores range from ___ to ___ and a score of __ indicates no effect

confidence interval

Refers to the range of expected values of your estimate (usually your effect size) if you re-ran your experiment with a different sample

true

True or false: if a confidence interval includes the no effect value, we can’t confidently conclude that the effect in our sample is that same as in the population

ethnography

Anthropologic approach whereby the researcher immerses themselves in the environment of their subjects to observe and interact with them to understand their culture, behaviors, and social interactions

grounded-theory

A systematic approach where the researcher constructs theories through methodical gathering and analysis of data

case-study

Involves an in-depth exploration of a single case or a small number of cases within their real-life context

phenomology

Seeks to understand the essence and meaning of lived experiences from the perspective of those who experienced them

narrative

Focuses on understanding how people make sense of their experiences and construct their identities through storytelling

action-oriented

Participatory and collaborative approach whereby the researcher works with participants to identify issues and implement solutions to bring about change through the research process

credibility

Confidence in the truth of the findings

transferability

Showing that the findings have applicability in other contexts

dependability

Showing that the findings are consistent and could be repeated

confirmability

A degree of neutrality or the extent to which the findings of a study are shaped by the respondents and not researcher bias, motivation, or interest

construct vadility

Dependability is analogous to

external validity

Transferability is analogous to

internal validity

Credibility is analogous to

triangulation

Using multiple sources, methods, or researchers to cross-check findings and reduce bias

member checking

Allows participants to review preliminary findings to confirm they accurately reflect their experience

thick description

Involves providing rich, detailed contextual information so readers can assess whether findings apply to other settings

audit trail

Keeping detailed records of research decisions, data collection, coding, and analysis for transparency

reflexivity

The process of acknowledging and reflecting on the researcher’s biases, experiences, and potential influence on the study

prolonged engagement

Spending enough time int he research setting to build trust and gain deeper insights

peer debriefing

Sharing findings with colleagues or external experts for critical feedback

negative case

Involves actively searching for data that contradicts emerging themes to refine interpretations

focus group

A guided discussion among 5-8 participants that explores shared experiences or opinions on a topic whereby the social dynamic among the participants can surface new perspectives

moderator

Encourages quiet participants and manages dominate ones, speaks less than 5% of the time, and uses open-ended prompts

Nuremberg Code of 1947

Ten protections for participants of research studies established after World War II (no one was actually legally required to follow them at the time)

The Tuskegee experiment

Conducted by the US Public Health Service. Sharecroppers were not told that they had syphilis and were not given treatment even when it became available

National Research Act

Established a commission to identify basic ethical principles necessary for human subject research. Established IRBs

The Belmont Report

Respect for persons, beneficence, justice

respect for persons

People are autonomous and can decide what happens to them. If they aren’t fully capable, they need extra protection

beneficence

Maximize benefits, minimize harm

justice

Be fair in how you select research subjects. Don’t exploit certain groups just because it’s easier or cheaper

exempt

If the study is lowest risk and anonymous, then it is this type of IRB review

expedited

If the study is minimal risk and not anonymous, then it is this type of IRB review

full board (committee)

If the study is more than minimal risk and not anonymous, then it is this type of IRB review

informed consent

Process by which a participant voluntarily agrees to take part in a study after being fully informed about all aspects of the research that are relevant to their decision

minimizing harm

Requires researchers to reduce, prevent, and manage any potential physical, psychological, social, legal, or economic risks to participants as much as possible

anonymity and confidentiality

Protecting participants’ privacy

anonymity

Identities are completely unknown and untraceable

confidentiality

Identities are known to the researcher but kept private and secure

avoiding deception

Being honest with participants by not misleading them about the purpose, procedures, or nature of the study, unless absolutely necessary and ethically justified

right to withdraw

Participants can leave a study at any time, without penalty or negative consequences, and can request that their data be removed

ordinal

When interval/ratio data violate assumptions, they are generally treated as _____ data for non-parametric testing