PSYC 2002 Lecture Notes - Lecture 7: Null Hypothesis, Standard Deviation, Test Statistic

• School: Carleton University
• Department: Psychology
• Course: PSYC 2002
• Professor: Logan John

Document Summary

T-test as a solution to z-test problems: simple solution standard deviation to problems with z-test, use sample standard deviation to replace population standard deviation, the z-test is now transformed into the test. If n = 2 and m = 6, then the sum of the scores in the sample must be 12. If one of the scores = 8, then a restriction is places on the identity of the other score it must be 4. In this example there is is n-1 or 1 degree of freedom (df) If population standard deviation is known, use z-test. If population standard deviation is unknown, use t-test. Degrees of freedom and t-test: because the t-test uses sample standard deviation it must incorporate degrees of freedom into its usage, as df increases, the better the sample standard deviation s represents the population standard deviation. Increasing df produces essentially the same effect as increasing n.