Stephen Downes

"People often think of quantitative data as objectively true," writes Eric Ekholm. "A corollary of this that I run into often is that the data should 'speak for itself.'" Maybe sometimes this is the case, but more often it is not. "This isn't to say that we ought to twist statistics to serve some predetermined narrative... rather that one of the skills in working with data is essentially a journalistic one - being able to comb through data to identify compelling, actionable stories. In other words, data should be opinionated." Quite right. What we are looking for almost always determines what we find; what question we are asking almost always dictates what sort of answer we'll get. Working with data is mostly about asking and looking, not measuring and sampling.