✊🏿 Black Lives Matter. Please consider donating to Black Girls Code today.
⚾️ It's finally Baseball season! Root for the home team... & Register for our Sports Analytics Webinar!

# Incorrect parameter estimates for linear regression in Chart Studio

I think the parameter estimates are being calculated incorrectly for linear regression. I have a small data set as a reproducible example (CSV format):

zip,race,income
60626,10,11744
60640,22.2,9323
60613,19.6,9948
60657,17.3,10656
60614,24.5,9730
60610,54,8231
60611,4.9,21480
60625,7.1,11104
60618,5.3,10694
60647,21.5,9631
60622,43.1,7995
60631,1.1,13722
60646,1,16250
60656,1.7,13686
60630,1.6,12405
60634,1.5,12198
60641,1.8,11600
60635,1,12765
60639,2.5,11084
60651,13.4,10510
60644,59.8,9784
60624,94.4,7342
60612,86.2,6565
60607,50.2,7459
60623,74.2,8014
60608,55.5,8177
60616,62.3,8212
60632,4.4,11230
60609,46.2,8330
60653,99.7,5583
60615,73.5,8564
60638,10.7,12102
60629,1.5,11876
60636,48.8,9742
60621,98.9,7520
60637,90.6,7388
60652,1.4,13842
60620,71.2,11040
60619,94.1,10332
60649,66.1,10908
60617,36.4,11156
60655,1,13323
60643,42.5,12960
60628,35.1,11260
60627,47.4,10080
60633,34,11428
60645,3.1,13731

I’ve built a scatterplot with race on the x-axis and income on the y-axis. From the Analyze menu, I can now fit a linear model. The Parameter Estimates are listed as 12597.187567819898 for the intercept and -56.740206144976604 for the slope.

Using R, I can do the same calculation and I get 12776.65 for the intercept and -59.48 for the slope.