PSYC 2002 Lecture Notes - Lecture 6: Level Of Measurement, Standard Score, Null Hypothesis

• School: Carleton University
• Department: Psychology
• Course: PSYC 2002
• Professor: Angel Mackenzie

Document Summary

Effect size: alternative to hypothesis testing, measure of size of difference b/w means, unaffected by sample size. Hypothesis testing w/ 2 sample means (t-tests) Measures of central tendency: mean, median, mode, mean most important in stats, random sampling, population parameters vs. Mean: = population, m = sample (generic) Variance: 2 = population, s2 = sample, sd2 = generic. Standard deviation: = population, s = sample, sd = generic. Sampling distribution of means: theoretical construct (not real , allows us to compare sample mean to distribution of means, & relate sample to pop. Hypothesis testing: relate sample to pop. using sampling distribution, null & alternate hypotheses, set decision criterion ( ) based on probability, measure of variability of distribution of means. Standard error: sd + influenced by sample size. Statistical power: probability of achieving significant result when h1 (research hypothesis) is true. Studies w/ sufficient power have high probability of rejecting null hypothesis if research hypothesis really is true.