STAT 3005 Lecture Notes - Lecture 6: Randomized Experiment, Dependent And Independent Variables, Confidence Interval
Document Summary
Large sample confidence interval for a difference in proportions. Significance test for a difference in proportions. Comparing the values for two different groups. Use a categorical variable x to distinguish the groups of interest and measure a response y. Consider the following before testing: if the response variable of interest y is categorical, use proportions, if the response variable of interest y is quantitative, use means. Add a subscript of 1 or 2 to identity different groups. To compare proportions, take the difference in proportions: Sample distribution for two proportions: (cid:1868)(cid:2869) (cid:1868)(cid:2870) or (cid:1868)(cid:2870) (cid:1868)(cid:2869) (cid:1868) (cid:2869) (cid:1868) (cid:2870) ~ (cid:4684)(cid:1868)(cid:2869) (cid:1868)(cid:2870) (cid:1868)(cid:2869)(cid:1869)(cid:2869)(cid:2869) +(cid:1868)(cid:2870)(cid:1869)(cid:2870)(cid:2870)(cid:4685) Statistics (cont. : question: as part of the pew internet and american life project, researchers conducted two surveys in late 2009. The first survey asked a random sample of 800 u. s. teens about their use of social media and the internet. A second survey posed similar questions to a random sample of 2253 u. s. adults.