My rule of thumb is "when you have so many data points you can't just talk to all the subjects directly" is when you can start deriving value from quant based DS methods. More broadly, a good researcher can pull information all along data volume the spectrum
Serious question: how much data do you need before data science is useful? I doubt there's a hard and fast rule, but I can't help remember that statistical significance testing, a cornerstone of modern statistics, was invented to make better decisions about industrial processeshttps://twitter.com/JohnDCook/status/1348658451665322005 …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
"Statistics" is especially useful with small data. Going from small-n survey to generalizing to a population is a great example. Not sure if that falls under "DS" but the small-data -> population inference I count as a very valuable skill.
-
Great point. That's definitely a place where some expertise adds a ton of value
End of conversation
New conversation -
-
-
My rule: 1) literature/google/net search according to business problem. 2) has someone done something? Y: good, try w/ their rules. N: make my own rules according to business owners requirements and internal data. Problem framing takes time but it is definitely worthwhile..
-
How often would you say you find prior art in step 1?
- Show replies
New conversation -
-
-
"statistical significance testing, a cornerstone of modern statistics, was invented to make better decisions about industrial processes" Actually, to make tea better
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
As soon as it starts to look like data and not just anecdote, it's useful for keeping your sanity like: no, the mean of these 5 numbers is not a good indicator of typical behavior--look at that skew, or improvements on these 20 convenient points are interesting but not reliable
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.