signal-to-noise ratio. The smaller the sample, the more they worry about noise (wrong people, inaccuracies or untruths, groupthink, etc.) So they compensate with bigger sample sizes. But more numbers often make more noise.
me and ask them questions and peek around the corner when they think I'm not listening. My master plan was I had a lot of kids. I have six kids. Three girls that are six, a 15-year-old, 18-year-old and 22-year-old. I have the perfect research team in my house." http://acupofteawithphd.wordpress.com/2013/06/19/live-from-cannes-cannes-lions-2013-so-farpart-4-its-diddy/
discipline of listening to their best customers and identifying new products that promise greater proﬁtability and growth are rarely able to build a case for investing in disruptive technologies until it is too late.” - Clay Christensen, The Innovator’s Dilemma
much information? But this is categorically the wrong attitude to take toward forecasting, especially… where the data is so noisy. Statistical inferences are much stronger when backed up by theory or at least some deeper thinking about their root causes.”
research manager from a project manager into a Scrum master. Their role is to remove obstacles to progress, and to facilitate communication. Their responsibility to the team is to facilitate hypothesis testing, and to create opportunities to challenge assumptions.
your decisions for you - that’s not their job. Don’t let the report be the end of your learning process - it’s just a way to memorialize what you’ve learned and provide a reference when you encounter similar issues again.
data that helps us make decisions, that helps us create value for our customers, and that helps us develop empathy for people so deep that we can anticipate solutions to problems they can’t yet express… That will enable the kind of analysis suﬃciently advanced to be indistinguishable from magic.