When there are many factors that have an impact on a system, statistical analysis yields unreliable results. Computer simulations give you exquisitely precise unreliable results. Those who run such simulations and call what they do “science” are deceiving themselves.

Beware also of models that fit historical data (especially "corrected" or "adjusted" data) but do not provide accurate predictions. This applies to macroeconomics, climate change, the stock market, social "sciences", and other complex systems with high causal density. You have to be very very careful you aren't fooling yourself with these models; and, as noted by Feynman, "yourself" is the easiest person to fool. Via Causal Density is a Bear | askblog.