Let's think a little bit about what you want to do with the results. Suppose you had data on all 130 projects. Presumably there would be no 'error,' true? But you just defined your population as all 130 projects. Therefore, any conclusions you draw apply only to those 130. You cannot make any projections toward behavior of the next projects undertaken.
Is this what you want? I doubt it. Not particularly useful to discuss only what was already complete. Suppose you define your population as "all the projects that were or can be performed by this one corporation, using the conditions that have applied in the past (whatever conditions influence the part of the project you are measuring and analyzing.) Now the population is infinite, and there is no FPC factor to worry about. And, you can use your conclusions to predict how projects will run in the future. If I were a manager in that firm, I'd want to know this a heck of a lot more than how the completed projects went. I mean, I can look at those old ones all I want - they are done and gone. Does this help you any? Jay Mats Lingblad wrote: > I have data on 70 out of 130 projects completed in one firm. What is > the correct way to think about the the standard errors in regression > analysis, if I want to generalise to the firm? > 1. Adjust with the FPC factor since a large portion of the population > is covered. > 2. Do not adjust with the FPC factor since it is the potential number > of projects started by the firm that constitute the "true" population. > > Alternative 2 is safer and more conservative, but it also seems a bit > too hard since the large n/N ratio should count for something. > > I would also appreciate it if somebody has references on this subject. > > Finally does anyone have the formula for adjusting the F-test in > standard OLS regression models for a finite population? > > Regards, > > Mats Lingblad > LBS > London > . > . > ================================================================= > Instructions for joining and leaving this list, remarks about the > problem of INAPPROPRIATE MESSAGES, and archives are available at: > . http://jse.stat.ncsu.edu/ . > ================================================================= -- Jay Warner Principal Scientist Warner Consulting, Inc. 4444 North Green Bay Road Racine, WI 53404-1216 USA Ph: (262) 634-9100 FAX: (262) 681-1133 email: [EMAIL PROTECTED] web: http://www.a2q.com The A2Q Method (tm) -- What do you want to improve today? . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
