Hacker News Reader

Comment by paulpauper | Hacker News Reader

What about all the businesses that try this or try to reinvent themselves and fail. This is why business case studies are BS and unscientific. It is easy in hindsight to explain why something worked. having a visionary CEO worked for Apple; did not work so well for the company that made the Segway. If case studies were so effective, if you be possible to find companies that meet all the criteria, buy their stock cheap, and get rich. Dominoes stock went up because for some reason there was this sudden surge of demand for pizza, and domino's pizza somehow rose to the top in an otherwise very crowded market. All pizza chains have apps and online delivery.

View on HN

Case studies are more like a Paul graham blog post than they are documentation. Read it, get some ideas, learn some lessons and advice, apply some of it your situation.

But what's the alternative to looking at examples of success? Looking at examples of failure? Working from a-priori theories? Both seem worse.

> But what's the alternative to looking at examples of success?

Controlled experiments and/or causal analysis.

People generally don’t hand out multimillion dollar assets to do controlled experiments on, and even then the “control” would be relatively weak since there are so many uncontrolled variables.

Does statistical causal analysis work when there are this many variables? Feels like that would just be essentially a case study again.

> Does statistical causal analysis work when there are this many variables?

Yes, that's the whole point. It works when you can "simulate" experiments by looking at a large number of events.

E.g. DNA evolution in genetics, drug testing in medicine, studying failure modes in aeronautics...

I guess you could watch The Apprentice shudder

Some management theories are quite useful.

Clayton's Christensen's disruption theory was useful.

But nothing's bulletproof, of course.

So maybe looking at the methodologies serious business academics use to write their PHD, and their work in general, is a good alternative to case studies ?

You should look at both successes and failures. When you only look at one or the other, the features you pick out might not be unique to that group.

RCTs > Natural Experiments > case studies > anecdotes > talking out of your ass.

There is a lot of knowledge in the world that we'll never get RCTs for and we just have to learn the best we can.

RCT == Randomized Control Trial - https://en.m.wikipedia.org/wiki/Randomized_controlled_trial

> If case studies were so effective, if you be possible to find companies that meet all the criteria, buy their stock cheap, and get rich.

This is what investing is.

Also, when they did this no-one had apps or delivery. The pizza market is growing but DPZ took massive share as well. It is surprising to me that so many people are armchair quarterbacking this (I know someone who bought them at $5...all of the stuff mentioned in the article was the bull case: online growth, mismanaged, etc.).

Dominoes stock price has been on a steady rise for over 5 years. When did this supposed surge in demand for pizza happen?

It's not pizza that increased in popularity, it's Dominoe's being competitive.

This inspired me to find a quote from War and Peace about generals who explain their strategic brilliance after the battle is over. They had no grand strategy in the moment, it is all post-hoc BS. I can't find the quote though, if anyone knows this quote i will give you unwavering gratitude!

Reply on news.ycombinator.com