1
00:00:00,960 --> 00:00:07,380
So we have seen how to run a logistic regression with single predictor and how to interpret it is that

2
00:00:07,380 --> 00:00:10,470
we get now we'll be running.

3
00:00:10,730 --> 00:00:12,720
So just integration with multiple predictors.

4
00:00:15,130 --> 00:00:20,080
It isn't exactly same as what we did with single predictor only defenses.

5
00:00:20,550 --> 00:00:28,890
The inverse of this price variable will be using all other variables to denote that we want all variables

6
00:00:29,010 --> 00:00:32,250
except the independent except be dependent variable.

7
00:00:32,400 --> 00:00:33,430
We can user dort.

8
00:00:34,830 --> 00:00:42,510
So instead of just place, we'll be using all independent variables and the dependent variable is same

9
00:00:42,510 --> 00:00:42,960
method.

10
00:00:44,460 --> 00:00:46,310
So we need to link both of these statements.

11
00:00:47,220 --> 00:00:47,760
And on them.

12
00:00:54,410 --> 00:00:55,590
So here is the result.

13
00:00:56,630 --> 00:00:59,750
You can see the list of variables is on the left.

14
00:01:00,500 --> 00:01:04,560
These are all the variables that we had in our dataset.

15
00:01:06,050 --> 00:01:08,720
On the right, we have beta values.

16
00:01:09,500 --> 00:01:13,220
This intercept is beta zero, which is minus two point one three.

17
00:01:14,480 --> 00:01:18,830
Price has a end of minus zero point two seven and so on.

18
00:01:20,600 --> 00:01:22,820
The second column is standard error.

19
00:01:23,270 --> 00:01:23,810
Third is.

20
00:01:24,400 --> 00:01:24,810
Lou.

21
00:01:25,460 --> 00:01:33,020
We are not really concerned about standard error and devalues in straight away look at the P value to

22
00:01:33,020 --> 00:01:39,020
identify which all variables are significantly impacting our response variable.

23
00:01:40,790 --> 00:01:47,780
So using just those two lines, we can pretty model and see the estimate coefficient.