I am new to statistics and Data Science.
I participated in couple of Hackathons organised by AV , in order to get myself familiar with analytics and statistics.I heard from lot of fellow Data Scientists here , and on some other forums , that we should use some X technique (regression , decision tree , boosting , etc…) to improve our prediction.
I even tried my hand on some techniques in R , and it improved my prediction.But the problem is , even my result is improved , i didn’t understand , how it impacted my result , what is underlying methodology , conceptually.
For example i used glm() followed by randomForest() in R , and it improved my result a lot , but i don’t understand the technicality behind it.
So , all i want as a solution from this question is , some links or books , which i can use to read and understand deeply the reason for using the techniques i should use and also to decide which technique would be better to use , according to problem in hand.
Something , which can explain , for example , the result of the summary function ( in R) applied on model ( lm , glm , etc.) .
All the statistics jargons (like F/P/T - test or chi-sq., etc…)
I hope you understand my question.