pol 51 lecture 10

pol 51 lecture 10 - statistic. Has standard deviation get...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Measurement metric (know what that means for midterm) If you ignore Z you can get completely wrong inferences. Difference of means test (continuous X, categorical Y). statistically significant (measurably different from 0). Frequently used test when analyzing experimental data because this is a BIVARIATE TEST and experiments is the only time when you don’t need to worry about Z. Difference of means test: we have two groups/samples of data and we want to know if the means are the same. We should also wonder if they have the same variance, standard deviation, mode, ect. Mean is most common because a lot of phenomenon has normal distribution and that focuses mostly on the mean. We do it because IT IS CONVENIENT. Suppose the null hypothesis is true, then how unlikely is the data? X^2 bigger than critical value, significant; smaller than critical value, not significant T test measures the difference of means. The further apart the means are, the bigger the t
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: statistic. Has standard deviation get larger, then standard error gets larger, confident intervals get larger, but t statistic gets smaller. So we have a statistic and now we need to compare it to a critical value. If statistic is greater than critical value, then there is relationship between two variables if the statistic is less than crictial value, then no relationship. First we need to know degrees of freedom. This gets you through hurdle 3 Correlation: Positive correlation as X increases, Y increases Negative correlation as X decreases, Y decreases Use Pearsons R If all points on line and positive, then it equals 1. If all the points on line and negative slope, then it equals -1. Are sure are we that the correlation is either positive or negative? First get the t statistic and see if its greater than or less than critical value. So now we have to see if its substantly significant....
View Full Document

Page1 / 2

pol 51 lecture 10 - statistic. Has standard deviation get...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online