4
$\begingroup$

Continuing to explore main-site Analytics, here are the day-averages for "Visits on the main site", for the period June 8th - Aug 30th 2015 (I excluded the first week of June because it was obviously an outlier for the period):

enter image description here

Standard deviations range in the $50-100$ interval.

It is obvious(...) that Economics is not a light hobby - so people get down to it during the workweek, reserving the weekend, especially Saturday, in order to rest (relatively).

The current "Visits per day" metric (all days together) stands at $688$.

$\endgroup$
0

1 Answer 1

Reset to default
2
$\begingroup$

I also did some excel skills:

Upvotes per week day, questions versus answers

upvotes per week day

Things look nicely over the week, perhaps a little downwards trend. On average questions get more upvotes than downvotes.

Up-down ratio per week day, questions versus answers

up-down ratio per week day

Note how the ratio is much better for Monday and Saturday, the beginning of week/week end.

$\endgroup$
3
  • $\begingroup$ "Note that the ratio is never above 50%". Does this mean that downvotes are always more than double the upvotes? (The vertical axis scale on the 2nd graph is $\%$?) $\endgroup$
    – Alecos Papadopoulos
    Sep 15, 2015 at 17:16
  • $\begingroup$ @AlecosPapadopoulos Whoups, I checked again and it's wrong. Somehow my import added the leading dot :D. Here's the underlying query: data.stackexchange.com/economics/query/1718/… $\endgroup$
    – FooBar
    Sep 15, 2015 at 17:35
  • $\begingroup$ Since downvotes are consistently lower than upvotes, I would suggest to either a) Calculate upvotes/downvotes as an "odds ratio", so not expressed as a percentage (i.e. "how many upvotes per one downvote"), or b) calculate downvotes/upvotes and express it as a percentage. $\endgroup$
    – Alecos Papadopoulos
    Sep 15, 2015 at 18:08

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .