chapter 1 Flashcards
experimental study
the researcher manipulates the independent variable and then observes how the dependent variable changes in response to those manipulations
independent variable
It is a variable that stands alone and isn’t changed by the other variables you are trying to measure.
dependent variable
The dependent variable is the variable that is being measured or tested in an experiment and depends on the independent variable
cannot happen earlier in time than the dependent variable
the dependent variable is on which axis
y-axis
the independent variable is on which axis
on the x-axis
confounding variable
the variable that affects both the independent and the dependent variable and it potentially obscures the true relationship between the independent and dependent variables
mediating variable
provides a mechanistic link between an observed relationship between 2 variables
in between both variables
moderating variable
modulates the intensity of a certain relationship
quantitative
numerical values are used
qualitative
if verbal or open-ended measures are used
mixed-methods
if both qualitative and quantitative methods are used
negative controls
in experimental studies, negative controls do not receive the treatnebt or intervention of interest (could be placebo)
positive controls
in experimental studies, positive controls receive a treatment that is known to induce the outcome of interest
randomization
In a lab based experimental study, it’s expected thar samples will be randomly allocated to control or treatment groups
single-blinding
In a single-blind study, patients do not know which study group they are in (for example whether they are taking the experimental drug or a placebo) while the researchers do or the researchers do not know but the participants do. (only one group knows)
double-blinding
In a double-blind study, neither the patients nor the researchers/doctors know which study group the patients are in.
non-blinded
if everyone involved knows whch participants are in which group
Randomized control trial
an experimental study in which participants are randomized to either a control or treatment group
observational studies
used when experimental designs are not feasible
observational designs
analyze pre-existing variation in the population
cross-sectional study
when researchers take a set of people representative of a population, measure various things about them, and look for correlations among those measurements
snapshot of a certain population at a certain time (surveys)
correlation studies
focus on how certain variables are correlated with each other
(whether a high level of one variable predicts a high or low level of another variable, vice versa)
cannot provide information about causality
longitudinal design
multiple measures are made over time
can be observational or experimental
risk factors
independent variables associated with a higher risk of a negative outcome
protective factors
independent variables associated with a lower risk of a negative outcome
prospective cohort studies
subset of longitudinal cross-sectional studies where a group of subjects is assembled according to some organizing principle and followed over time
retrospective cohort studies
take a group of people and look back over time to find an exposure
case-control studies
involve gathering people with the disease “case” and those without the disease “control) and compare them with the goal of identifying differences between tje 2 groups
case-study
researchers can report their expereinces with a certain condition or treatment
single case = case study
multiple cases = case series
systemic reviews
studies in which a researcher combs through the literature on a topic and critically assesses the outcomes of various studies
meta-analyses
multiple studies are combined and re-analyzed
yields strongest available evidence on a given topic
7 principles identified by the NIH for research ethics
- social and clinical value (study must be attempting to answer an important question)
- scientific validity
- fair subject selection (indicates that participants in a study should be chosen based on the relevance for the study’s scientific goals)
- favourable risk-benefit ratio (mandates that the risks of study particpants is minimized and the benefits outweigh the risks
- independent review (an independent board of reviewers should assess the research proposal for any study before it starts)
- informed consent (participants must agree after knowing all the facts)
- respect for potential and enrolled participants (privacy, confidentiality, monitoring particpants)
validity
refers to the extent to which a study’s results are both genuine and generalizable
internal validity
describes the extent to which we can draw causal conclusions from the study data (did we conduct the study in such a way that we know that manipulating variable x caused some change in variable y)
external validity
the extent to which we can generalize our results onto different experimental situations or real life
content validity
how well the test covers the full scope of content the researchers intend to measure
criterion validity
describes how well our test correlates with some other well-respected criterion like an established test of the same measure
predictive validity
reliability
the extent to which study results are consistent
“if we do the study again, will we see similar results”
precision
describes how close together experiminetal measurements are
accuracy
refers to the closeness of a measurement to the actual, real value that we are measuring
self-reporting bias/response bias
occurs when people are allowed to choose their own answers
social desirability bias
tendency of respondents to answer in a way that they think makes them look more socially successful
acqueiescence bias
the tendency to answer yes when asked a question
