1. Our Sleep Graphs
Any volunteers for us to look at your graph in detail?
Small groups -- what can we do to make our graphs better?
Data Collection Issues?
what should we title our data so as to be appropriate?
2. http://io9.gizmodo.com/i-fooled-millions-into-thinking-chocolate-helps-weight-1707251800
think back to the samples of M&M's ... most contained the true mean, but one did not!
3. What do we know at this point
what kind of data is it?
what kind of answer do we want from it?
what metrics will allow us to know whether the is a trend, a value, or some type of value from it?
4. Points from Naked Statistics:
a (well done) poll overall matches the ideas of the central limit theorem. While the results won't be EXACT, they will be around
"In theory, in 19 cases out of 20, overall results based on such samples will differ by no more than 3 percentage points in either direction from what would have been obtained by seeking to interview all American adults."
the confidence we want from a poll is important -- less confidence allows us to call earlier, as the difference will be okay.
"mirrored the population they were drawn from and gave accurate answers"
Homework:
head over to this and make a story about the population of the united states: http://datamapper.geo.census.gov/map.html
here's another implementation of similar data: http://projects.nytimes.com/census/2010/map
this may be one map or multiple maps that you create (you can just print or save them from teh website, but make sure to keep in mind which setting you used or where you zoomed).
it can be over any of the variables, over any of the data. Engage in your results -- what information can you use?
are there any places online you might want to use to add context?
that link came from here: https://www.census.gov/geo/maps-data/ where there are many other data tools. feel free to use the ones that might help you the most.
...that's actually it. this is a light workload, because we're going to have a rougher weekend workload.