Awesome. So ppl who like their sex rough (at least sometimes) are smarter than the always gentle ones (or virgins)https://twitter.com/KirkegaardEmil/status/606611787904122880 …
-
@shoutybrown
@DrZhana@AliceDreger@KirkegaardEmil@ElisaMisu Shining example of manipulating data by constructing a graph w/ a skewed axis.
@WatchtowerNorth @shoutybrown @DrZhana @AliceDreger @ElisaMisu Odd claim. I haven't modified the axis at all. Default settings with ggplot2.
-
-
@KirkegaardEmil @shoutybrown@DrZhana@AliceDreger@ElisaMisu I want to see graph w/0-4 axis. Current's equivalent to http://blogs-images.forbes.com/naomirobbins/files/2012/08/Bush_cuts2.png … -
@WatchtowerNorth Forcing 0-4 means most of plots are full of white space. What is the point?pic.twitter.com/sINgxaPQ4x
-
@KirkegaardEmil It shows the real difference between answers rather than suggesting more significant differences than actually exist. -
@KirkegaardEmil Just like the graph I linked should show 0-100 percent, your graph should scale from 0 right answers to all right answers. -
@KirkegaardEmil So thank you for the new graph. :) -
@WatchtowerNorth Maybe you should just read axis labels. The other is a rather useless way of plotting things. Which is why no major soft.. -
@WatchtowerNorth ware system does it that way by default.
End of conversation
New conversation -
-
-
@KirkegaardEmil@WatchtowerNorth@DrZhana@AliceDreger@ElisaMisu the point is, the presentation of the data is misleading. -
@shoutybrown
@WatchtowerNorth@DrZhana@AliceDreger@ElisaMisu Why? Seems fine to me. -
@KirkegaardEmil@WatchtowerNorth@DrZhana@AliceDreger@ElisaMisu could we have the raw data, please? -
@shoutybrown Well you can scrape it yourself. ;) I won't publish the data before I publish my first paper on it.
-
@KirkegaardEmil ok. I would suggest either noting explicitly that the y axis doesn't start at 0, or replotting the data with y_min=0.
End of conversation
New conversation -
-
-
@KirkegaardEmil@WatchtowerNorth@DrZhana@AliceDreger@ElisaMisu also, significance needs to be calculated. -
@shoutybrown
@WatchtowerNorth@DrZhana@AliceDreger@ElisaMisu NHST is not a good idea. CIs are better. http://ist-socrates.berkeley.edu/~maccoun/PP279_Cohen1.pdf …
End of conversation
New conversation -
-
-
@KirkegaardEmil@WatchtowerNorth@DrZhana@AliceDreger@ElisaMisu finally, pretty sure ggplot2 lets you change the axis scaling :)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.