Study designs Flashcards
negative control
-a group that does not receive a treament
positive control
- a group receives a treatment with a known effect
- to make sure your experiment setup is working right
- Let’s say you do a cell culture experiment and observe nothing. Is your result meaningful, or is it possible that you just screwed up the cell culture protocol (which is realistic, since cell culture can be a pretty finicky process)? A positive control helps you tell the difference.
observational studies
as the name suggests, involve analyzing something that is happening regardless of whether scientists are interested in it. There are several reasons why a researcher might conduct an observational study. Some common examples include assessing complex population-level phenomena like the impact of diet on heart disease and cancer, or analyzing the spread of an infectious disease among the community. In essence, there are contexts where performing an experiment would be impossible and/or unethical.
cross-sectional studies
- taking a snapshot of a population of interest at a moment in time - record demographic and person info about ppl as well as health parameters in order to study association
- in contrast, a longitudinal study would do this but measure it over time
case-control studies
take ppl with a certain “case” (condition) and match them to similar individuals WITHOUT that condition (control)
RCT
patients are randomly assigned to receive the treatment or control
- not to do with blinding or not, just in the selecting
experimental study
- a study where we test to prove a causal relationship between the independent variable and dependent variable. Participants are randomly assigned to different groups or levels of the independent variable. Between-subjects and within-subjects designs are common experimental studies
- study in which conditions are under the direct control of the investigator” (Last 2001). It is employed to test the efficacy of a preventive or therapeutic measure. Experimental studies can provide the strongest evidence about the existence of a cause-effect relationship .
between-subjects design
participants are randomly assigned to an experimental or control group and the variable is being tested between subjects
within-subjects design
- repeated measures design - each participant is exposed to all the different elevels being tested
- same person in multiple conditions
mixed-methods design
(a study where you use both qualitative and quantitative measures to conduct your study. One example would be using quantitative measures like how would you report your like for this product on a scale of 1 through 10, and then later following up with people who answered either negatively or poorly and asking them for their qualitative opinion.)
cohort
a group of ppl branded together or treated as a group
cohort
a group of ppl branded together or treated as a group
base-rate fallacy
ignoring statistical evidence in favour of using irrelevant, inaccurate information, they incorrectly believe that it is correct, and use this to make a judgment