you probably dont care at all but does anyone know of a tool to log back into an instagram account? I was dumb forgot the account password. I appreciate any help you can give me.
@Jaden Ace I really appreciate your reply. I found the site through google and im in the hacking process now. Seems to take quite some time so I will reply here later with my results.
Very helpful. I have had one stat class in college and a class currently that uses stats. This has been more helpful than any teaching on stats that I have received yet.
Thanks so much! I don't get many examples in class so I have no idea how to do this but your video makes it super simple and understandable! I have an exam in 2 days so this is a big help! Thanks Kevin!!!! :D
Hi Sir! Thank you a lot for your very interesting videos :) I am a little bit confused by the fact that sometime one devides by n sometime by n-1,how can we distinguish the diference between the two; i mean when do we have to divide by n only or by n-1?
KINE KINE adding to that, samples are usually not a perfect representation of the population, hence there is more chances of the answer being slightly inaccurate. So to be on the safer side we divide by n-1 because DIVIDING by a SMALLER number gives you a BIGGER end result. which just means that you have a larger co-VARIANCE now. and since ,more variance = more fluctuations in data , we end up covering a larger risk than what we would have covered otherwise if it was divided just by 'n'.
+Pinky Chan Hi Pinky! That is the problem with the covariance...its interpretation is limited. It can only really tell you that a relationship is positive or negative (based upon whether it is a positive or negative value). BUT...you can use the covariance to figure out the correlation coefficient, which tells you much more.
great video! I was wondering why excel has two different formulas for covariance, one where the denominator is n-1, and one where the denominator is n?
I read somewhere that when you solve the summation in the numerator we get X*Y and X(mean)*Y(mean) , can you tell how does that happen, Where do the other two terms go?
Hi Kevin, Great video! If the correlation coefficient value between x and y is around abs(.5) in my data, is that high enough to propose as an insight that is actionable in a real world business setting?
+Albert Ko Thanks Albert...it depends on the nature of what you are studying...in social sciences, for example, a cc of .5 or higher would be relatively high to suggest association between two variables. In other fields (e.g., medicine or even finance), this may not be high enough.