[Previous Months][Date Index][Thread Index][Join - Register][Login]
[Message Prev][Message Next][Thread Prev][Thread Next]

Re: [IP] Measure of control?

On 28 May 99 at 8:27, David C Breeden wrote:

> If you had a month's worth of home bg testing data, what numbers would
> you look at to evaluate the control of the tester?

I try to look at the average and standard deviation for the month as a whole 
and then for each week.  I also pick several "windows of interest" in the data 
and calculate for that slice.  The idea is to see if there is an overall trend 
up or down in the averages for the weeks or for successive three to five day 
windows...  This is one of those areas where YMWV must be repeated several 
times for impact...

Randall P. Winchester
* The views expressed here are mine and do not necessarily *
* reflect the official position of anyone in particular.            *
* There's no guarantee on anything said here...
* If I say I understand something completely the only thing
* we can both be assured of is that I must have completely
* misunderstood something. 
Insulin Pumpers website http://www.insulin-pumpers.org/
for mail subscription assistance, contact: HELP@insulin-pumpers.org