# Why does Desmos give a different exponential regression than my TI 84 and my Calculus text?

I obtained this data from a calculus text (Stewart's Single Variable Calculus, Early Transcendentals, 2nd Ed.). The text and my TI 84 graphing calculator both give similar values for $a$ and $b$ ($0.00807079266$ and $1.013731$, respectively).

Below is my result from Desmos. What magic is it working? Why might it be so different? The regression line in the textbook also looks much better.

Am I handling Desmos correctly?

• My GeoGebra agrees with your calculator and text, except that it makes $a$ like a million times smaller (same digits, only with a lot more (I didn't count) zeroes in front). – Arthur Jan 28 '17 at 22:59
• Yes, my TI 84 does the same. I neglected to mention this as it didn't worry me. The population figures are in millions. – Adam Hrankowski Jan 28 '17 at 23:02
• Problem solved: I enabled log mode. (Note the unchecked box in the sample illustration.) This puts the figures in line with the other calculators. The desmos site explains: support.desmos.com/hc/en-us/articles/204349605 – Adam Hrankowski Jan 28 '17 at 23:37
• @AdamHrankowski Could you please convert your comment into an answer so this question can be removed from the "Unanswered" queue? Answering one's own question can feel odd, but since you solved your own problem, it seems like the best course of action here. – Robert Howard Nov 25 '18 at 3:06