Confused as why (n * (2/(2n-1))) is valid? (2/(2n-1)) is valid for first couple, shouldn't the remaining couples is (2/(2n-3)), (2/(2n-5)), (2/(2n-7))...?
Thank you so much ,this video is very useful because tomorrow is my presentation and I am so nervous but still waching this video then I am be confident for giving presentation again thank you so much
The thing I cant get it in the beginning is how two x1 and x2 data set creates mu1 and mu2 separetely. One Gaussian shape data set should have only one mean and sigma, right???
How do you write the likelihood for a multivariate Gaussian distribution with p correlation factor? Plus, imagine your data set is constructed by counts per channels as Gaussian shape histogram. Thanks.
How does the geometric proof account for the f(*) factor? This is not probability. The RVs are continuous so f(*) needs to be obtained by taking derivatives. How do you know the derivative works out with the fixed observation x_(k)?
By appealing to the circular symmetry of the standard bivariate normal distribution, show how samples from a Cauchy distribution could be generated from independent N(0,1) samples
Better than what my professor gave. Here's how he defined it: "Let X and Y be two random variables. We denote by E(X|Y = y) the expected value of the conditional distribution of X given Y = y. The conditional expectation of X given Y is denoted by E(X|Y ) and is defined to be E(X|Y = y) on the event Y = y." Kind of circular if you ask me.
I am new in Statistics and what I need to understand may sound of very basic level. Yet I want to know it. On 0:02 why there are so many normal curves from x-axis and y axis? What do those curves signify?