In statistics there are 2 types of errors that one can make.
A Type 1 error is when you aggressively reject the status quo for change, even if the status quo was just fine (crying wolf!). A Type 2 error is aggressive rejection of change for the status quo, even though the status quo isn't right any longer (not crying wolf!).
There is no way to escape these errors, and depending on evidence, you'll sway one way or another (these errors always exist and are complementary in nature). The financial crisis looked like it could blow up the world (there might be a wolf in the flock!). Assuming status quo - that nothing is happening (no wolf) - you might not prepare for it (a wolf), and if the world blew up you'd lose everything (wolf eats you!). Assuming change (hello wolf!), you prepare and adapt for the crisis where you have to lose a bit (growth/funding/employees sadly), but if it all goes down - you are prepared (wolf meet gun!).
This is an example of the precautionary principle at work, and based on my understanding, Sequoia did an outstanding job. The Federal Reserve also did a great job (during the crisis). I have no opinion about the lax rates in the lead up to the bubble - but I presume that was highly detrimental to our collective financial health! :D
Sequoia are the best in the business, they've been around the block a couple of times, and all they care about is making sure their companies survive. RIP Good Times was prudent.
Better to cry wolf, than to not do so, and be eaten while you sleep.
When the cost/benefit balance changes, assume catastrophe, minimise chances of a Type 2 error (bias yourself towards change - a Type 1 error), and plan for the worst thing that you can possibly imagine - think of it like paying for insurance against storm damage if the data shows a few too many clouds over the Atlantic.
A false positive error, commonly called a "false alarm" is a result that indicates a given condition has been fulfilled, when it actually has not been fulfilled. In the case of "crying wolf" - the condition tested for was "is there a wolf near the herd?", the actual result was that there had not been a wolf near the herd. The shepherd wrongly indicated there was one, by calling "Wolf, wolf!".
In terms of folk tales, an investigator may be "crying wolf" without a wolf in sight (raising a false alarm) (H0: no wolf).
A false positive (with null hypothesis of health) in medicine causes unnecessary worry or treatment, while a false negative gives the patient the dangerous illusion of good health and the patient might not get an available treatment. [1]
The future is very uncertain. Act accordingly.
Or as our ancestors would say:
If you hear any type of rustling in the bushes; always assume that it's a tiger trying to kill you. Temporary fear/worry is a good deal better than a permanent and painful death.
In statistics there are 2 types of errors that one can make.
A Type 1 error is when you aggressively reject the status quo for change, even if the status quo was just fine (crying wolf!). A Type 2 error is aggressive rejection of change for the status quo, even though the status quo isn't right any longer (not crying wolf!).
There is no way to escape these errors, and depending on evidence, you'll sway one way or another (these errors always exist and are complementary in nature). The financial crisis looked like it could blow up the world (there might be a wolf in the flock!). Assuming status quo - that nothing is happening (no wolf) - you might not prepare for it (a wolf), and if the world blew up you'd lose everything (wolf eats you!). Assuming change (hello wolf!), you prepare and adapt for the crisis where you have to lose a bit (growth/funding/employees sadly), but if it all goes down - you are prepared (wolf meet gun!).
This is an example of the precautionary principle at work, and based on my understanding, Sequoia did an outstanding job. The Federal Reserve also did a great job (during the crisis). I have no opinion about the lax rates in the lead up to the bubble - but I presume that was highly detrimental to our collective financial health! :D
Sequoia are the best in the business, they've been around the block a couple of times, and all they care about is making sure their companies survive. RIP Good Times was prudent.
Better to cry wolf, than to not do so, and be eaten while you sleep.
When the cost/benefit balance changes, assume catastrophe, minimise chances of a Type 2 error (bias yourself towards change - a Type 1 error), and plan for the worst thing that you can possibly imagine - think of it like paying for insurance against storm damage if the data shows a few too many clouds over the Atlantic.
A false positive error, commonly called a "false alarm" is a result that indicates a given condition has been fulfilled, when it actually has not been fulfilled. In the case of "crying wolf" - the condition tested for was "is there a wolf near the herd?", the actual result was that there had not been a wolf near the herd. The shepherd wrongly indicated there was one, by calling "Wolf, wolf!".
In terms of folk tales, an investigator may be "crying wolf" without a wolf in sight (raising a false alarm) (H0: no wolf).
A false positive (with null hypothesis of health) in medicine causes unnecessary worry or treatment, while a false negative gives the patient the dangerous illusion of good health and the patient might not get an available treatment. [1]
The future is very uncertain. Act accordingly.
Or as our ancestors would say:
If you hear any type of rustling in the bushes; always assume that it's a tiger trying to kill you. Temporary fear/worry is a good deal better than a permanent and painful death.
[1] - http://en.wikipedia.org/wiki/Type_I_and_type_II_errors
[2] - http://en.wikipedia.org/wiki/Precautionary_principle