Commit de70e92c authored by Nathan Rebiscoul's avatar Nathan Rebiscoul
Browse files

Add criticicms

parent e1cd9e81
......@@ -33,7 +33,9 @@ feet_size = [17.5,17.5,17.5,17.5,18,18,18,18,18.5,18.5,18.5,19,19,20,20,20,20.5,
*** Justification and implementation
I think that presenting data with cloud of points is a good idea
because it show a lots of informations (all the data), and it is easy
to read. I put the scatter trend line (the red curve) to highlight it.
to read. I put the scatter trend line (the red curve) to highlight
it. I put feet size on x-axis because it's as a lot element with the
same value so we have not a lot of point hide by other point.
#+begin_src python :results output :exports both
nb_mistakes = [15,18,19,20,16,17,18,19,14,16,17,15,16,13,14,15,12,13,14,15,10,11,13,15,10,12,13,8,10,11,12,8,9,10,7,8,9,11,6,8,9,6,7,8,10,4,6,7,8,5,6,4,5,7,3,4,5,2,3,4,7,2,3,0,1,2,4]
......@@ -66,3 +68,16 @@ On this graph we can see a clear correlation between the feet size and
the number of mistakes. Indeed we can see that students with bigger
feets tends to do less mistakes than students with smaller feets. The
scatter trend line show that this correlation seems to follow a linear way.
*** Criticism
The fact that this graph show all data is a little bit false because
some points can be stacked. So a point can maybe 1 or 20000
points. But it seems that this problems not appear to much with our
dataset. And it's diminished by the scatter trend line.
The choice to put feet size on x-axis is debatable.
** Find another way of presentation
* TODO Conclusion
For instance i can't say more than in interpretation.
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment