PSY 200 Lecture Notes - Lecture 9: Standard Deviation, Statistical Parameter, Local Exchange Trading System
Document Summary
Notice the only difference is using sample sd or sample var instead of. The t-statistic vs the z statistic population sd or population var. Estimated standard error: = (cid:3046) (cid:3041) (cid:1870) (cid:3046)2(cid:3041) The z-score requires more information than researchers typically have available. Requires knowledge of the population of standard deviation () Researchers usually have only the sample data available. The whole point of research is to infer from the sample to the population. If we had that information, we don"t need to stud(cid:411) it! The t-statistic is used in place of the z statistic when population values are not known. The main difference is the t-test uses the estimated standard error instead of standard error. While the z-distribution is the same distribution regardless of sample size, the t distribution depends on the degrees of freedom. The t-distribution approximates the shape of a normal distribution (but is not the same!) Flatter, more spread out=more variability than the normal.