STAT 11300 Lecture Notes - Lecture 2: Nocebo, Dependent And Independent Variables
Document Summary
Anecdotal evidence: a story from one person or just a few people; not scientific: dateline. Observational study: observes individuals and measures variables of interest but does not attempt to influence the responses: survey. Experiment: deliberately imposes some treatment on individuals to observe them. Lurking variable: has an important effect on the relationship among the variable i(cid:374) a stud(cid:455) (cid:271)ut is(cid:374)"t a(cid:374) e(cid:454)pla(cid:374)ator(cid:455) (cid:448)aria(cid:271)le: possibly show a cause and effect relationship between treatment and response. Explanatory variable: may explain or cause changes in the response variable (independent variable) Response variable: measures outcome or result of study (dependent variable) Treatment: any specific condition applied to the subjects. Problems: lurking variables, placebo effect, bias by researchers. Control or comparison group: helps avoid placebo effect. Randomization to treatment groups: helps to reduce bias. Large sample size (in each treatment group: helps reduce variability; balances out quirks in individuals. Neither the researchers nor the individuals being treated know which treatment is given.