[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: -varabbrev- setting [was: st: re: question about "testparm"]

From   David Radwin <>
To   <>
Subject   RE: -varabbrev- setting [was: st: re: question about "testparm"]
Date   Mon, 2 Feb 2009 14:06:32 -0800

If you can stand one more bit of gasoline trivia, a better measure probably would be km/g or some other function of distance and mass rather than distance and volume, because gasoline is less dense at higher temperatures. (But it probably does not save you any money to fill up at night rather than during the day.)

"California drivers were overcharged $376.4 million on gasoline in one year because fuel pumps don't adjust for changing temperatures, according to a state study."


At 4:27 PM +0000 2/2/09, Nick Cox wrote:
I think in Britain, which naturally I consider part of Europe, it is
still common to talk of mileage (and not just because of the uneven and
snail-like progress of metrication here). The fact that you should
regress on gpm := 1/mpg for all sorts of good reasons -- which I have
often enjoyed demonstrating -- does not affect the fact that drivers
care about how far they can go before they need to refill with fuel, so
to that extent mpg is a natural unit too.


Kit Baum

It is an Americanism to say 'your mileage may vary', as a European would more sensibly* talk about litres/kilometre than miles/gallon. But there it is.

* It is readily seen that the relationship between price and mpg is not nearly as linear (and the linear fit not nearly as good) as that between price and 1/mpg.

*   For searches and help try:

David Radwin //
Office of Student Research and Campus Surveys, University of California, Berkeley
*   For searches and help try:

© Copyright 1996–2023 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index