Wednesday, May 09, 2007

Why Should We Even Teach Statistics?

The title link is to a PDF with the following front portion:
1. Who Is Better Off?
The English weekly newsmagazine The Economist once showed Figure 1 in an article
as part of a series on statistics:


Figure 1. A comparison of wages for bosses and workers. (Source: The Economist, May 16, 1998, p. 79)
The purpose of the graph was to make a comparison between the wages of Bosses and
Workers. The comparison was made with time-series data over a ten-year span, and the
graphs plot three aspects of wages against time.


And then on the other side is a place that takes random factors and tries to see a correlation as in: Order From Randomness. I love the place but it is exactly what the above article is questioning? The last one I saw was that they tried to correlate between having low percentage of births of mothers over 35 with low number of 4 year degrees. I guess this is suppose to show that to get a degree you need to wait till you are old to have babies. Of course they use the red/blue state divide that did show the lower percentages for Republican states. But even here this is based on only one vote and thus not really a reliable indicator of political leanings that can change very rapidly. I do question using stats that are on a state wide basis. It tends to be very lumpy and not really a good practice to compare such diverse population samples. I think district break downs would be better.

0 Comments:

Post a Comment

Links to this post:

Create a Link

<< Home