I've had a couple requests to add the "Triola vector" to my matrix of stats. textbooks. Since the requests came from "family", I tried to oblige. The vector
T4 1 1 0 0 0
is close to the origin.
However, I was really not trying to get into the reviewing business. What I wanted was to provide a simple, crude test that could be applied by anyone to a potential textbook, i.e., I wanted YOU to do the counting, not ME!
To that end, I should have added a little more detail about how I counted, though it is more important that you count consistently than just as I did. I counted PAGES referenced; 142-144 counted as three pages. If a topic got subheadings, I counted multiple references to the same page, e.g., I counted
outliers real bad, 162 not so bad, 162 hardly worth mentioning, 163
as 3 page references. Remember, I was trying to get a handle on the importance accorded these topics, and I felt multiple consecutive pages, or an index listing with subheadings, both indicated high importance for the topic.
I should also note that the numbers after the abbreviations for the books indicated editions. I did not have the latest editions of Johnson or Triola because I won't take them when publisher's representatives offer them. More recent editions might rate higher, but I would be very concerned about improvements which are merely cosmetic. The counts are just symptoms of something much deeper -- two (note the data are bimodal) very different conceptions as to the basic nature of statistics. Indeed, the whole point of the exercise was to get a quick measure of which side of this dichotomy a book inhabited.
_ | | Robert W. Hayden | | Department of Mathematics / | Plymouth State College | | Plymouth, New Hampshire 03264 USA | * | Rural Route 1, Box 10 / | Ashland, NH 03217-9702 | ) (603) 968-9914 (home) L_____/ email@example.com fax (603) 535-2943 (work)