PHYSICS 102 Lecture Notes - Lecture 10: Standard Error, Clinical Trial, Null Hypothesis
Document Summary
Correlation and inferential statistics get p values etc. If is known, use the z test. In the equation, is the average difference: as our null hypothesis claims no difference, this is assumed to be 0. If t critical value is greater than the one relevant to it in the critical values table, there is a significant difference between the two data sets. In this instance, isn"t 0, its whatever the average height is. If the t critical value is less than the value in the table, heights can be considered the same. R t. test(y1, y2 : var. equal = true, alternative= less , alternative= greater performs t-test specifies equal variances specifies one-tailed specifies one-tailed. If critical value is greater than relevant number in table, it is significantly different to expected values: cheating, k = degrees of freedom, as degrees of freedom increases, looks more and more like a normal distribution. If there is a significant difference, variables are linked.