On 31 Jul 2003 13:48:48 -0700, [EMAIL PROTECTED] (Louis T) wrote: > Hi ! > > I'm doing an internship on software testing and I have to classify reported > bugs. The bug list is important so I decided to make a sampling. I know that > by doing a sampling I may introduce an error when I will generalize my > result to the whole population, and I am ready to assume it. But I want to > be able to measure the trust I can have in my work. I feel I have to use the > "chi square" test. Is it true and are there other tests ?
What "work" are you trying to have trust in? I've read some about software testing, and I don't remember much about any *statistical* testing, at all - except, say, that each project has a different set of problems. And each programmer is different. I think you need to give an example or two of what you are trying to conclude... And do some reading in the area. Knuth? I think there is a famous piece on "the mythical man-month" -- I don't remember if the original piece was written about programming, but I remember seeing the theme applied to programming. > > The detail of my classification will depend on the amount of work I have to > make as my time is limited (no big news in this !). In my case, I have ten > categories with a sub-division in 33 categories (not for each category but > for all of them). The number of reported bugs should be around 3000. (I > could get a more precise number on this, but haven't searched yet). What > should be the correct size of my sample if I use the ten categories? And > if I use the 32 subcategories? > > I have some knowledge of statistics so I guess I could apply, and hopefully > understand, any formula as long as I could find one. Something about this particular question-asking is really annoying to me, so I'm just going to quit here. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html "Taxes are the price we pay for civilization." Justice Holmes. . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
