Hacker News Reader

Comment by streptomycin | Hacker News Reader

I'm surprised at the comments here. Seems that nearly everyone disagrees with the blog? Is Bill Gates such a saint among the HN crowd that we ignore statistics for him?

Also, see this blog for some more discussion along the same lines: http://ed2worlds.blogspot.com/2013/01/gates-foundation-waste...

Seems pretty clear that Gates' study presents the data in a very misleading manner to make a very weak correlation look like a very strong correlation.

View on HN

The blog post doesn't have any statistics to ignore.

Graphs are not statistics. Why doesn't he give us a correlation coefficient on his big blue blob graph?

You criticize a short blog post for something that is not done in the Gates publication. Do you have some bias, perhaps? Why does Gates not even give us a scatter plot, let alone a correlation coefficient? This is the critical point raised by the blog.

There are quite a few statistics reported in the Gates Foundation publication. Take a look for yourself:

http://www.metproject.org/downloads/MET_Validating_Using_Ran...

I never said they don't report "quite a few statistics". I said they don't report this one specific particularly important statistic, and instead obscure it behind a ridiculous averaging procedure. This was either done because they are incompetent or because they are purposely trying to mislead. That's the whole point of TFA.

What one particular statistic do you want?

Take a look at the FULL report. All the statistics behind the graph you criticize are in Table 1 on page 10.

The next 40 pages seem to be a pretty competent description of both the strengths and weaknesses of their study.

Was thinking the same thing. I think it is: "...correlation coefficient of .35..."

Found it following the link: http://garyrubinstein.teachforus.org/2012/02/26/analyzing-re...

Reply on news.ycombinator.com