This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: If you ensure a representative sample, you can generalize any findings to the population. When we are doing research, we want to establish that one variable causes another variable. Three Criteria of Causation 1. correlation 2. time order 3. Non-spuriousness Correlation – the value of the 2 variables vary together-strength of correlation (0-1)-direction (positive/negative) Spurious correlation – a correlation that is caused by a third unknown variable “control for” the unknown variable Take original sample and divide it into 2 parts based on unknown variable Contextual effect is present when a causal relationship between two variables is dependent upon the social context in which it occurs...
View Full Document
- Summer '08
- Causality, representative, Correlation does not imply causation, Katie Kerr SOC, unknown variable Contextual