CC, CI, p-values
A correlation coefficient of r = 0.85 indicates this type of relationship
A strong, positive relationship
(example of strong negative relationship = -0.85)
What is the intervention and what is the outcome in the following question:
In first-time postpartum mothers, does peer support increase breastfeeding duration at 3 months compared to standard postpartum care?
I - peer support
O - breastfeeding duration
Retrospective
If identities are not collected at all, this is maintained
Anonymity (vs. confidentiality, where identifying information is collected but not shared)
This number tells you how likely your result is due to chance.
P-value
A relative risk of 2.0 between the intervention and control group means:
The exposed/intervention group is twice as likely to experience the outcome
Weight in kilograms is this type of variable
Ratio
(Ranks attributes but equal distance between values with absolute zero point)
This type of research tests cause-and-effect or seeks to establish causal relationships (one variable directly causes another)
Experimental
This framework of principles was developed to address ethical concerns in Indigenous research and recognize community rights in research.
OCAP (ownership, control, access and possession)
This type of error occurs when the researchers reject a true null hypothesis.
Type I error
A study found the mean BP difference was 8 mmHg with a 95% CI of 1 to 15. How should this be interpreted
The researchers are 95% confident the true difference is between 1 and 15 mmHg
This type of variable is manipulated by the researcher in an experiment.
Independent
A design comparing outcomes before and after an intervention in one group
Single-arm pre-post study (quasi-experimental)
Also can be called interrupted time series design
This type of validity examines the extent to which scores on a measure compare to the gold-standard
Criterion validity
The range in which we expect the true value to lie, with a certain level of confidence.
Confidence Interval
Confidence intervals provide information about statistical significance and precision of the estimate
If the p-value is 0.02 and α = 0.05, the result is considered:
Statistically significant (p<alpha)
True or false: Defining anxiety as a "score on the GAD-7 scale" is an example of an operational definition.
True
True or false: In observational research, data is collected by observing without intervening
Bonus: what are some examples of observational study designs?
True
Cohort study, case-control study, cross-sectional survey
The degree to which the effects detected in the study are a true reflection of reality rather than a result of extraneous variables
Internal validity
This type of error occurs when the researchers incorrectly accept the null hypothesis (that there is no difference between groups when in reality there is)
Type 2 error
If the 95% confidence interval for a relative risk is 0.7–1.2 for a measure of dichotomous data, what does that mean
The result is not statistically significant because it includes 1 (dichotomous data - 1.0 is point of no difference between groups)
(When measuring continuous data, if CI contains 0 then the result is not significant)
Patient satisfaction rated as “very dissatisfied” to “very satisfied” is an example of this level of measurement
Ordinal (ordered or ranked categories but distance between categories is not necessarily equal)
What is the key element of an RCT that makes it the "gold standard" for clinical research?
Participants are randomized to intervention or control group (accounts for variation in sample)
If the sample of a quantitative study is not representative of the population, this is a threat to:
Bonus: what can the researchers do to mitigate this?
External validity (generalizability to wider population)
Use of random (probability) sampling; multi-site study; larger sample size
This measure tells us the direction and strength of a relationship between two variables.
Correlation coefficient