Sociology 2206A/B Chapter Notes - Chapter 9: Quasi, Hawthorne Effect, Observational Error
9 Apr 2013
School
Department
Course
Professor
Document Summary
3 things done in experiments: begin with hypothesis, modify something in a situation, compare outcomes with and without modifications. Strongest for testing causal relationships because 3 conditions for causality (temporal order, association, no alternative expectations). Match between a research question and technique is not fixed but depends on informed judgement. Questions used confront ethical and practical limitations. Questions that give answers the researcher can manipulate. Valid comparison depends on comparing things that are fundamentally alike. Random assignment facilitates comparison by creating similar groups. Two groups must be similar in more respect except for some alterable variables. Random assignment: method for assigning cases to groups for the purpose of making comparisons. Random describes a process in which each case has a known chance of being selected. Random means a case has an equal chance of ending up in one group over the other. Unbiased probability of selecting a case can be mathematically determined. Divide into 2+ groups by random process.
