Things Never To Forget

'In finance... data are scarce and, more importantly, markets are arenas of action and reaction, dialectics of thesis, antithesis and synthesis. People learn from past mistakes and go on to make new ones. What's right in one regime is wrong in the next.'

'A little hubris is good. But then, when you're done modelling, you must remind yourself that you're theorizing about [individuals], and that, though God's world can be divined by principles, humanity prefers to remain mysterious. Catastrophes strike when people allow theories to take on a life of their own and hubris evolves into idolatry. Somewhere between these two extremes, a little north of common sense but still south of idolatry, lies the wise use of conceptual models. It takes judgement to draw the line.'
- E. Derman, My Life As A Quant


'In my first year I took an intermediate statistics class with a professor named Harry Roberts... But what I learned from Harry was a philosophy. He gave me an attitude toward statistics that has stuck with me ever since.

With formal statistics, you say something -- a hypothesis -- and then you test it. Harry always said that your criterion should be not whether or not you can reject or accept the hypothesis, but what you can learn from the data. The best thing you can do is use the data to enhance your description of the world. That has been the guiding light of my research. You should use market data to understand markets better, not to say this or that hypothesis is literally true or false. No model is ever strictly true. The real criterion should be: Do I know more about markets when I'm finished than I did when I started? Harry's lesson is one that I've passed on to my students over the 49 years that I've been a teacher.
- E. Fama, 'The best advice I ever got'

There’s No Such Thing As Precision When Investing

"This makes perfect sense in theory. The problem is when investors assume a false sense of precision when using the correlation statistic or any relationship for that matter. It would be much easier to forecast the future movements of the various asset classes and individual holdings within a portfolio if correlations were static, but they aren’t. Correlations are dynamic."

More here.