00:01
This exercise is about linear regression and predicting an outcome using the regression equation.
00:09
Now, we are given this data on 42 -inch tvs.
00:13
We have, for each tv, we have the price and the score.
00:17
And for part a, we are asked to develop a regression equation.
00:22
Now, we can develop our regression equation, our estimated regression equation, using the least squares method.
00:31
And using that method means that we're finding a slope b sub 1, according to the first equation, and the intercept according to the second formula.
00:41
So let's first find this slope, and let's do this on the excel spreadsheet.
00:48
So we want to solve for the slope, b1, and it has a numerator and denominator.
00:54
So let's solve for the numerator and denominator separately, and then divide them.
01:04
Now the first step is to find the average price and the average score.
01:16
And then the numerator is the sum of for each price, we subtract the average price, and then multiply it by the score, subtract the average score.
01:53
And then we sum these to get our numerator.
02:02
So first make the calculation for each data pair, and then sum them.
02:12
And then for the denominator, it is the price minus the average price squared.
02:27
And that is done for each price value, and then we sum them.
02:43
And so then our slope is equal to the numerator divided by the denominator, and we get 0 .0127.
03:03
And now we can calculate the intercept.
03:05
So this is 29 .6 minus 0 .0 .0 .1 .7.
03:16
127 times 49 .6.
03:24
And this comes out to 12 .017.
03:33
So our regression equation is therefore 12 .017 plus 0 .12127 times x...