fundamental skills lecture 5 statistics 3 Flashcards
how do you find the sample size?
the number of observations
what is the degree of freedom?
unique pieces of information used to quantify variation
how is the degree of freedom found?
the number of observations - 1 (the mean)
how do you find the mean sum of squares?
the sum square divided of the df value for ESS and RSS
what is the f-ratio?
the mean sum of squares (for each explanatory variable) divided by the residual mean sum of squares. so f= explained mean square/ residual mean square.
each explanatory variable has its own f ratio
the overall forumla of the f ratio is
to find the explained mean square its the explained SS over model df meaning the variation explained by the variable / the pieces of info (coefficients) it requires
then divide that by the residual SS / residual df which is the pieces of info that contribute to the residual variation and the variation left unexplained by the model
what is the p-value in GLMs?
the probability of the F statistic being that high or higher if the null hypothesis is true
why do we use dfs?
to standardise variation based on the pieces of information we used to quantify it
how do you find the gradient and the y intercept?
the top is the intercept and the bottom is the gradient
how do you find an unknown value?
insert it into the value y = m x + c. This is referred to as the algebraic structure of the model
how do you find f height?
af / am then + at both sides