Trying to make a regression model; question about fitlm and intercept!

Hi.

So I am trying to make a simple regression model for my measurement data. I used the following code:

function regg2
x=[19.8044	19.8044	19.8044	19.8044	19.8044	19.8044	19.8044	19.8044	35.278	35.278	35.278	35.278	35.278	35.278	20.0042	20.0042	20.0042	20.0042	20.0042	20.0042	25.3008	25.3008	25.3008	25.3008	25.3008]';
y=[4.5	7	2	2	4	6	5	6.8	1	0	0	0.4	1	0	10	2	5	8.1	1.9	2	4.6	3.6	10	1.6	0.8]';

mdl= fitlm(x,y)
plotAdded(mdl)

And I get this nice little figure:

But I discussed this with my teacher and he seem to think it is not correct. He says that my model should have an intercept. The fitlm gives me intercept of 10 which means that b0 is approx. 1. But it does not seem to be the case.

I am sorry if I am a bit unclear. But the idea is to make a simple linear regression model and get the standard equation which would normally be:

y=b0+b1*x1

Am I misunderstanding the method? Am I wrong? If I am wrong, how should I go about my code to get my regression model and a similar figure?

Thanks in advance!

Answer 1

[Star Strider]

‘... intercept of 10 which means that b0 is approx. 1’

That does not appear to be correct. The intercept, ‘b0’ in your equation would be the y-intercept, and 10 would appear to be reasonable (from visual extrapolation only). The slope ‘b1’ appears to be about -0.3 (again visually).

[Punto]

I did the calculation in 3 different ways and get the same answer. 10 as b0 and approx 0.3 as b1. So you are probably right.

[Star Strider]

Thank you.

If my Answer helped you solve your problem, please Accept it!

.