SOCECOL 10 Lecture Notes - Lecture 7: Statistical Inference, Null Hypothesis, Standard Score
Document Summary
Understand population by looking at sample: we want to generalize the results from the sample to a larger group of people. In order for us to have data from a sample and make guesses about an entire population, we need to use probabilities. The p-value tells us how confident we can be about our conclusions: p-value: probability of sample difference if null is true. Conceptually, trying to begin to understand the concept of p-(cid:448)alue, it"s telli(cid:374)g us the (cid:272)ha(cid:374)(cid:272)es that (cid:449)e"re (cid:449)ro(cid:374)g. To be more technical, the p-value tells us the probability of obtaining a group difference or of obtaining a correlation as large as we have obtained in our sample (or larger) if the null hypothesis is actually true. The null hypothesis is that the correlation coefficient (cid:894)the (cid:862)r- (cid:448)alue(cid:863)(cid:895) is zero. There is (cid:374)o (cid:272)orrelatio(cid:374), the(cid:455)"re e(cid:454)a(cid:272)tl(cid:455) the sa(cid:373)e. This hypothesis that there is no correlation or difference between your variables or groups.
