PSY 1101 Lecture Notes - Lecture 4: Explained Variation, Statistical Significance, Experiment

• School: University of Ottawa
• Department: Psychology
• Course: PSY 1101
• Professor: Kenneth Campbell

Document Summary

The researcher must indicate what the probability is of finding a difference this large by chance alone. The level of significance is set at 0. 05. A statistician might claim that differences this large could only occur by chance on 5% of. If a pill kills 1/1000 people the level of significance is 0. 0001. Ensure explained variance is large (the size of the experimental effect) Larger differences are more likely to be significant. Were more confident with results from large than small samples. If all individuals have the same score there is no variance (0) If a very large sample is used, very small differences might be statistically significant. One exceptional individual case studied in detail. Sample a small number of individuals from a population. Better to have a small representative sample than one that"s large and unrepresentative. Experiment must often be carried out in a controlled setting (lab) Experimenter compares one group to another (ex. males and females)