1.
1
http://www.amitsharma.in
http://www.github.com/amit-sharma/causal-inference-
tutorial

2.
2

3.
3

4.
4

5.
5

6.
Use these correlations to make a predictive model.
Future Activity ->
f(number of friends, logins in past month)

6

7.
7

8.
8

9.
9

10.
10

11.
11

12.
12

13.
13

14.
14

15.
15

16.
16

17.
17

18.
18

19.
19
Algorithm A Algorithm B
50/1000 (5%) 54/1000 (5.4%)

20.
20
Algorithm A Algorithm B
10/400 (2.5%) 4/200 (2%)
Algorithm A Algorithm B
40/600 (6.6%) 50/800 (6.2%)

21.
Is Algorithm A better?
Algorithm A Algorithm B
Success Rate for
Low-Activity users
10/400 (2.5%) 4/200 (2%)
Success Rate for
High-Activity users
40/600 (6.6%) 50/800 (6.2%)
Total Success Rate 50/1000 (5%) 54/1000 (5.4%)
21

22.
22

23.
Average comment length decreases over time.
23
But for each yearly cohort of users, comment length
increases over time.

24.
24

25.
25

26.
26

27.
27http://plato.stanford.edu/entries/causation-mani/

28.
28http://plato.stanford.edu/entries/causation-counterfactual/

29.
29

30.
30

31.
31

32.
32

33.
33

34.
34

35.
35

36.
36

37.
37

38.
38Dunning (2002), Rosenzweig-Wolpin (2000)

39.
39

40.
40

41.
41

42.
42

43.
43

44.
44

45.
45

46.
46

47.
47http://tylervigen.com/spurious-correlations

48.
http://www.github.com/amit-sharma/causal-inference-tutorial
amshar@microsoft.com
48