PSY 110 Lecture Notes - Lecture 2: Experiment, Psy

• School: University of Miami
• Department: Psychology
• Course: PSY 110
• Professor: Roderick Gillis

Document Summary

Develop theory explains patterns in data good theory leads to a testable hypothesis. Testable hypothesis not scienti c until you design a testable hypothesis and put it to a test. If yes support hypothesis (statistically via t-test if less than . 05, it is signi cant) **one test does not support a theory, because theory"s are never proven** **theories are designed to advance our knowledge/ thinking (in medicine, biology, technology, etc )** Correlational study: randomly divide subjects into two or more groups, measure two variables, manipulate the independent variable the variable that is randomly assigned in a true experiment, calculate the relationship, measure the dependent variable. Ex: pearson"s correlation= +. 90 (positive= two variables move together; as one goes up the other goes up) Correlation is necessary but not signi cant for causation. May infer that coffee caused an increase in heart rate. **correlational studies often have directionality problems and/or third variable problems.