STAT-S 300 Lecture Notes - Lecture 24: Statistical Significance, Statistical Inference
Document Summary
Section 9. 3 notes- tests about a population mean. 12-4-13: if using table b, round down on degrees of freedom if needed value not there, calculator much more accurate, but use ctlghelp. One sample t tests: when random/normal/independent conditions met, use following steps for one- sample t test: Choose srs of size n from large population with unknown mean. To test h0: , compute one-sample t statistic: Find p-value by calculating probability of getting a t statistic this large or larger in direction specified by ha in a t-distribution with df = n 1. Population distribution is normal or n > 30. Population at least 10 times as large as sample. Inference for means: paired data: paired data- result of study designs that involve making two observations on the same individual, or one observation on each of two similar individuals. When paired data result from measuring same quantitative variable twice, we can make comparisons by analyzing differences in each pair.