My photo
Racine, Wisconsin, United States
We (my wife and I) are celebrating the 11th Anniversary of HAPLR, and more importantly, our 38th Anniversary. The HAPLR system uses data provided by 9,000 public libraries in the United States to create comparative rankings. The comparisons are in broad population categories. HAPLR provides a comparative rating system that librarians, trustees and the public can use to improve and extend library services. I am the director of Waukesha County Federated Library System.

Thursday, January 7, 2010

Index Requirements

Back in 2000, LJ Index co-author Keith Lance asserted in his article in American Libraries entitled “Lies, Damn Lies, and Indexes,” that a “proper” index must consist of variables that are correlated by between 0.60 and 0.80. He produced a correlation matrix on HAPLR, noted that some of my variables were above or below those numbers, and criticized it for that.

I could not find the correlation matrix for the LJ Index anywhere in LJ’s “transparent” web site, so I did my own calculations. By my calculations, only visits and circulation per capita meet the definition. The web site asserts that you rejected reference because it did not meet the criteria. However, you make no mention of the fact that attendance and public internet use also fail the test.

I stopped calling HAPLR an index, assuming that my lack of a PhD in statistics had led me astray in naming the product. I now refer to it as a scorecard. I kept the web site name because of domain name requirements.

I have no desire to go back to calling HAPLR an index. I wonder, though, if the “generally accepted statistical principles” Lance cited in 2000 have changed. If so, can Lance please direct me to sources? If not will you consider a name change?

No comments:

Post a Comment

Blog Archive