6) Then, we go from the basic statistical analysis and ask, "Does 2016/2017 mark a substantively interesting or notable point of change? Is there something there that might have changed that might take a share about 1/3—though it deviated from year to year— and cause it increase the course nearly a decade by 50%/~17 percentage points up …
6) Then, we go from the basic statistical analysis and ask, "Does 2016/2017 mark a substantively interesting or notable point of change? Is there something there that might have changed that might take a share about 1/3—though it deviated from year to year— and cause it increase the course nearly a decade by 50%/~17 percentage points up to ~1/2? Can you think of anything?
*****************************************
Good statistical analysis can provide insight, directing us to consider something we might not have seen. Bad statistical analysis can direct us to things that are not there, or hide from us things that are.
Good statistical analysis can lend further evidence to support ideas that already have. Bad statistical analysis can provide false evidence for bad ideas or miss evidence to support good ideas.
As so many have pointed out, the alternative to *good* use of statistics is NOT *no* use of statistics. The alternative is *bad* use of statistics.
Mock all you want, be as flip as as you want, but learning to use qualitative *and* quantitive tools to help us to understand things better is quite valuable.
As is learning to recognize expertise and its limits. Twain was good social commentator and wit. Another master of wit as Oscar Wilde, who was credited with saying "Imitation is the sincerest form of flattery that mediocrity can pay to greatness”.
(I myself rather moved away from wit in college, once I recognized how much of it was merely about insulting other people. Since then, I have made no attempts to be a great wit.)
6) Then, we go from the basic statistical analysis and ask, "Does 2016/2017 mark a substantively interesting or notable point of change? Is there something there that might have changed that might take a share about 1/3—though it deviated from year to year— and cause it increase the course nearly a decade by 50%/~17 percentage points up to ~1/2? Can you think of anything?
*****************************************
Good statistical analysis can provide insight, directing us to consider something we might not have seen. Bad statistical analysis can direct us to things that are not there, or hide from us things that are.
Good statistical analysis can lend further evidence to support ideas that already have. Bad statistical analysis can provide false evidence for bad ideas or miss evidence to support good ideas.
I’m with Mark Twain on this: There are lies, damned lies, and statistics. 😉
As so many have pointed out, the alternative to *good* use of statistics is NOT *no* use of statistics. The alternative is *bad* use of statistics.
Mock all you want, be as flip as as you want, but learning to use qualitative *and* quantitive tools to help us to understand things better is quite valuable.
As is learning to recognize expertise and its limits. Twain was good social commentator and wit. Another master of wit as Oscar Wilde, who was credited with saying "Imitation is the sincerest form of flattery that mediocrity can pay to greatness”.
(I myself rather moved away from wit in college, once I recognized how much of it was merely about insulting other people. Since then, I have made no attempts to be a great wit.)