On Thursday 27 September 2001 06:36 pm, you wrote:
There is definitely something wrong with the regression calculations in the data analysis tools. It seems that the standrard error for the parameter estimates are switched (and then all the calculations based on them seem to be wrong).
Yes, I just observed that too. However, for something like quadratic fit regression, the error seems to be more severe. The following I attach a file, that I originally created using MS Excel. I opened it using gnumeric, and copy the data, and did Regression in the second sheet (I put label in the title for which one was created using Excel and which one was created using gnumeric, so it should be clear.) What I did basically I select Data Analysis, Tool, Regression, put the dependent data in Input Y Range, and the independent data in Input X Range, and hit OK. Let me know if I can be of any more help. Reuben D. Budiardja
Attachment:
age_data.gnumeric
Description: GNU Zip compressed data
Attachment:
hogs_data.gnumeric
Description: GNU Zip compressed data