Current Events > math friends of the CE; can anyone explain the log likelihood criterion

Topic List	Page List: 1
LotrMorgoth 06/28/17 7:32:32 PM #1:	I'm been looking into different sources which understandably use a lot of proofs and math-heavy explanation. Can anyone translate into layman's terms as I need to be able to explain this as part of a 2-step cluster analysis (SPSS does it automatically so I don't have to compute it) --- "You will not be happy if you continue to search for what happiness consists of. You will never live if you are looking for the meaning of life"-Camus <cite>LotrMorgoth posted [p:881989303] in math frien... [t:75511265]...</cite> <quote>I'm been looking into different sources which understandably use a lot of proofs and math-heavy explanation. Can anyone translate into layman's terms as I need to be able to explain this as part of a 2-step cluster analysis (SPSS does it automatically so I don't have to compute it)</quote> ... Copied to Clipboard!
tiornys 06/28/17 7:45:09 PM #2:	You might be looking more for "stats friends" than math friends. I have a basic handle on log likelihood functions after a quick look at wikipedia, but I don't have the stats background/google-fu needed to figure out how it applies to 2-step cluster analysis. --- http://etrosgate.com/ <cite>tiornys posted [p:881989941] in math frien... [t:75511265]...</cite> <quote>You might be looking more for "stats friends" than math friends. I have a basic handle on log likelihood functions after a quick look at wikipedia, but I don't have the stats background/google-fu needed to figure out how it applies to 2-step cluster analysis.</quote> ... Copied to Clipboard!
LotrMorgoth 06/28/17 7:47:42 PM #3:	i get the 2-step part, i don't get the basic math lol. Because my data set uses both continuous and discontinuous variables, the 2-step is my only option. It automatically uses the log-likelihood as a way of controlling for the potential influence of both types of variables. But i don't get exactly what it's doing. I believe its related to probability in some based on obtained results but I don't know more than that --- "You will not be happy if you continue to search for what happiness consists of. You will never live if you are looking for the meaning of life"-Camus <cite>LotrMorgoth posted [p:881990085] in math frien... [t:75511265]...</cite> <quote>i get the 2-step part, i don't get the basic math lol. Because my data set uses both continuous and discontinuous variables, the 2-step is my only option. It automatically uses the log-likelihood as a way of controlling for the potential influence of both types of variables. But i don't get exactly what it's doing. I believe its related to probability in some based on obtained results but I don't know more than that</quote> ... Copied to Clipboard!
Topic List	Page List: 1