The problem of induction-I

David hume was the first modern epistemologist.He argued against naive empiricism.Pure empiricism implies necessarily being fooled by randomness.How many effects we take for granted may not be there.Say, take the statement-accidents happen closer to home, but people spend more of their time driving closer to home.But, a more dangerous aspect of empiricism is you can use data to disprove a proposition,never to prove one, because it is a long distance from has never happened to never happens.Such assymetry lies art the core of knowledge, also at the core of decision making under uncertainty.Our future does not have to resemble our current past when our past by bringing surprises did not resemble our past's past.
one cannot infer much from a single experiment in a random environment-an experiment needs a repeatability showing some causal component.
Induction means going from plenty of particulars to the general.We need to accept the assymetry in knowledge; there are situations in which using statistics and econometrics can be useful, but i don't want my life to depend on it.Statistics and inductive methods are useful but when making decisions under uncertainty you should note that they are not always right.
Reference-Chapter 7 of Fooled by Randomness by Nicholas Taleb.