Statistical Sciences 1024A/B Chapter Notes - Chapter 6: Confounding, Marginal Distribution, Ideal Class Group
Document Summary
A two-way table describes 2 categorical variables and organizes counts according to a row variable and a column variable. The marginal distribution of one of the categorical values in a two-way table of counts is the distribution of the values of that variable among all individuals described by the table. %"s are ofte(cid:374) (cid:373)ore i(cid:374)for(cid:373)ati(cid:448)e tha(cid:374) (cid:272)ou(cid:374)ts, espe(cid:272)iall(cid:455) (cid:449)he(cid:374) (cid:272)o(cid:373)pari(cid:374)g groups of different sizes. They tell us nothing about the relationship between 2 variables. A conditional distribution of variable describes the values of that variable among individuals who have a specific of another variable. The counts within the table represent the conditional distributions. Because counts can be (cid:373)isleadi(cid:374)g, (cid:449)e prefer to (cid:272)al(cid:272)ulate %"s or proportio(cid:374)s for the (cid:272)orrespo(cid:374)di(cid:374)g (cid:272)ells. Comparing the conditional distributions allows us to describe the relationship between both categorical variables. The lurking variable creates subgroups, and failure to take these subgroups into consideration can lead to misleading conclusions regarding the association between the 2 variables.