Quote:
Originally Posted by rkomar
You can't point to a few authors and say, just because their numbers differ, that the statistics for the industry as a whole are wrong. Unless every author experienced the changes in sales in exactly the same way (highly unlikely), then you would expect that some did well and some did poorly. It's the distribution that matters statistically, not how any particular author did. Likewise, you can't use the distribution to predict precisely how any particular author will do. All you can do is make broad statements about the industry as a whole. So, pointing to a few authors proves nothing. Pointing to a sample of 10,000 authors is much more telling. This is all basic statistics.
|
But they don't point at any authors, that's the issue. This is a model without any validation. It's not a sampling of 10,000 authors, it's some guy who who tries to figure out what the actual sales numbers are based on various indicators. If he was actually comparing his guesses to the real sales figures for a sampling of 10,000 authors that might be a reasonable way to validate his model, depending on the sampling. You can't calculate something from nothing even with basic statistics. Garbage in/Garbage out.
Let's put it this way, what this guy is doing is the equivalent of in basebase, looking at the a batter's second at bat for 5 games a month and using that to project a likely batting average for the season. Of course, in baseball, we actually know what a given hitter's batting average is, so we know that most of the time, this methodology doesn't yield accurate projections.
I get that people really want to know the actual sales figures. People like surety. That's why there are analyst making a lot of money in a lot of fields. Heck, that's also why fortune tellers are still with us and still making money. But sometimes you just have to accept that you aren't going to know.