1
00:00:00,333 --> 00:00:04,581
[MUSIC]

2
00:00:04,581 --> 00:00:09,558
Okay, so that represented a kind of
high level overview about this module,

3
00:00:09,558 --> 00:00:14,650
as well as, other aspects that we're
going to touch upon in this course.

4
00:00:14,650 --> 00:00:19,400
But now let's delve into a specific
case of simple linear regression and

5
00:00:19,400 --> 00:00:21,340
talk about what this means.

6
00:00:21,340 --> 00:00:23,980
So going back to our flowchart,

7
00:00:23,980 --> 00:00:29,250
what we're gonna talk about now is
specifically the machine learning model.

8
00:00:29,250 --> 00:00:33,350
So that's that highlighted green box and
everything else is grayed out so

9
00:00:33,350 --> 00:00:35,270
you can forget about everything else for
now.

10
00:00:35,270 --> 00:00:38,570
We're just talking about our model and
what form it takes.

11
00:00:38,570 --> 00:00:40,880
So our simple linear
regression model is just that.

12
00:00:40,880 --> 00:00:41,630
It's very simple.

13
00:00:41,630 --> 00:00:43,430
We're assuming we have just one input,

14
00:00:43,430 --> 00:00:46,520
which in this case is,
square feet of the house and

15
00:00:46,520 --> 00:00:50,522
one output which is the house sales
price and we're just gonna fit a line,.

16
00:00:50,522 --> 00:00:54,420
A very simple function here
not that quadratic function or

17
00:00:54,420 --> 00:00:57,680
higher order polynomials we talked
about before, just a very simple line.

18
00:00:57,680 --> 00:00:59,940
And what's the equation of a line?

19
00:00:59,940 --> 00:01:04,720
Well, it's just intercept plus slope
times our variable of interest so

20
00:01:04,720 --> 00:01:09,620
that we're gonna say that's wo + w1x.

21
00:01:09,620 --> 00:01:13,700
And what this regression model then
specifies is that each one of our

22
00:01:13,700 --> 00:01:19,570
observations yi is simply that
function evaluated at xi.

23
00:01:19,570 --> 00:01:25,560
So that's w0 plus w1xI plus the error
term which we called epsilon i.

24
00:01:25,560 --> 00:01:32,060
So this is our regression model, and
to be clear, this error, epsilon i,

25
00:01:32,060 --> 00:01:37,520
is the distance from our specific
observation back down to the line.

26
00:01:40,205 --> 00:01:44,510
Okay, so
the parameters of this model Are w0 and

27
00:01:44,510 --> 00:01:50,130
w1 are intercept and slope and
we call these the regression coefficients.

28
00:01:50,130 --> 00:01:53,090
So that summarizes our simple
linear regression model.

29
00:01:53,090 --> 00:01:53,980
Very straight forward.

30
00:01:53,980 --> 00:01:55,600
Very simple.

31
00:01:55,600 --> 00:01:57,495
But we'll get to more
complicated things later.