1
00:00:09,500 --> 00:00:12,960
The topic of this recitation
is election forecasting,

2
00:00:12,960 --> 00:00:14,850
which is the art and
science of predicting

3
00:00:14,850 --> 00:00:17,690
the winner of an election
before any votes are actually

4
00:00:17,690 --> 00:00:22,910
cast using polling data
from likely voters.

5
00:00:22,910 --> 00:00:26,170
In this recitation, we are going
to look at the United States

6
00:00:26,170 --> 00:00:27,740
presidential election.

7
00:00:27,740 --> 00:00:29,170
In the United
States, a president

8
00:00:29,170 --> 00:00:30,800
is elected every four years.

9
00:00:30,800 --> 00:00:33,260
And while there are a number
of different political parties

10
00:00:33,260 --> 00:00:35,470
in the US, generally
there are only two

11
00:00:35,470 --> 00:00:37,260
competitive candidates.

12
00:00:37,260 --> 00:00:38,720
There's the
Republican candidate,

13
00:00:38,720 --> 00:00:40,780
who tends to be
more conservative,

14
00:00:40,780 --> 00:00:43,550
and the Democratic candidate,
who's more liberal.

15
00:00:43,550 --> 00:00:46,290
So for instance a recent
Republican president

16
00:00:46,290 --> 00:00:49,570
was George W. Bush, and a
recent Democratic president

17
00:00:49,570 --> 00:00:52,400
was Barack Obama.

18
00:00:52,400 --> 00:00:55,340
Now while in many countries
the leader of the country

19
00:00:55,340 --> 00:00:58,840
is elected using the
simple candidate who

20
00:00:58,840 --> 00:01:01,970
receives the largest number of
votes across the entire country

21
00:01:01,970 --> 00:01:04,540
is elected, in the
United States it's

22
00:01:04,540 --> 00:01:06,850
significantly more complicated.

23
00:01:06,850 --> 00:01:08,860
There are 50 states
in the United States,

24
00:01:08,860 --> 00:01:11,730
and each is assigned a
number of electoral votes

25
00:01:11,730 --> 00:01:13,539
based on its population.

26
00:01:13,539 --> 00:01:16,170
So for instance, the most
populous state, California,

27
00:01:16,170 --> 00:01:20,300
in 2012 had nearly 20 times
the number of electoral votes

28
00:01:20,300 --> 00:01:22,270
as the least populous states.

29
00:01:22,270 --> 00:01:23,920
And these number
of electoral votes

30
00:01:23,920 --> 00:01:25,850
are reassigned
periodically based

31
00:01:25,850 --> 00:01:28,920
on changes of populations
between states.

32
00:01:28,920 --> 00:01:32,180
Within a given state
in general, the system

33
00:01:32,180 --> 00:01:34,960
is winner take all in the sense
that the candidate who receives

34
00:01:34,960 --> 00:01:38,430
the most vote in that state
gets all of its electoral votes.

35
00:01:38,430 --> 00:01:40,310
And then across
the entire country,

36
00:01:40,310 --> 00:01:43,520
the candidate who receives
the most electoral votes

37
00:01:43,520 --> 00:01:46,920
wins the entire
presidential election.

38
00:01:46,920 --> 00:01:49,700
Now while it seems like a
somewhat subtle distinction,

39
00:01:49,700 --> 00:01:53,259
the electoral college versus
the simple popular vote model,

40
00:01:53,259 --> 00:01:55,600
it can have very
significant consequences

41
00:01:55,600 --> 00:01:57,400
on the outcome of the election.

42
00:01:57,400 --> 00:02:00,500
As an example, let's look at
the 2000 presidential election

43
00:02:00,500 --> 00:02:03,670
between George W.
Bush and Al Gore.

44
00:02:03,670 --> 00:02:06,340
As we can see on the
right here, Al Gore

45
00:02:06,340 --> 00:02:10,520
received more than 500,000 more
votes across the entire country

46
00:02:10,520 --> 00:02:14,060
than George W. Bush in
terms of the popular vote.

47
00:02:14,060 --> 00:02:15,820
But in terms of
the electoral vote,

48
00:02:15,820 --> 00:02:18,000
because of how those
votes were distributed,

49
00:02:18,000 --> 00:02:20,060
George Bush actually
won the election

50
00:02:20,060 --> 00:02:25,050
because he received five more
electoral votes than Al Gore.

51
00:02:25,050 --> 00:02:27,860
So our goal will be to
use polling data that's

52
00:02:27,860 --> 00:02:30,850
collected from likely
voters before the election

53
00:02:30,850 --> 00:02:32,960
to predict the
winner in each state,

54
00:02:32,960 --> 00:02:34,570
and therefore to
enable us to predict

55
00:02:34,570 --> 00:02:37,190
the winner of the
entire election

56
00:02:37,190 --> 00:02:39,730
in the electoral college system.

57
00:02:39,730 --> 00:02:42,260
While election prediction has
long attracted some attention,

58
00:02:42,260 --> 00:02:43,680
there's been a
particular interest

59
00:02:43,680 --> 00:02:46,540
in the problem for the
2012 presidential election,

60
00:02:46,540 --> 00:02:48,550
when then-New York
Times columnist Nate

61
00:02:48,550 --> 00:02:50,810
Silver took on the
task of predicting

62
00:02:50,810 --> 00:02:54,020
the winner in each state.

63
00:02:54,020 --> 00:02:55,829
To carry out this
prediction task,

64
00:02:55,829 --> 00:02:59,329
we're going to use some data
from RealClearPolitics.com that

65
00:02:59,329 --> 00:03:01,740
basically represents polling
data that was collected

66
00:03:01,740 --> 00:03:06,560
in the months leading up to
the 2004, 2008, and 2012 US

67
00:03:06,560 --> 00:03:08,400
presidential elections.

68
00:03:08,400 --> 00:03:10,870
Each row in the data
set represents a state

69
00:03:10,870 --> 00:03:13,150
in a particular election year.

70
00:03:13,150 --> 00:03:15,830
And the dependent variable,
which is called Republican,

71
00:03:15,830 --> 00:03:17,280
is a binary outcome.

72
00:03:17,280 --> 00:03:19,650
It's 1 if the Republican
won that state

73
00:03:19,650 --> 00:03:21,329
in that particular
election year,

74
00:03:21,329 --> 00:03:23,829
and a 0 if a Democrat won.

75
00:03:23,829 --> 00:03:25,610
The independent
variables, again,

76
00:03:25,610 --> 00:03:27,960
are related to polling
data in that state.

77
00:03:27,960 --> 00:03:31,870
So for instance, the Rasmussen
and SurveyUSA variables

78
00:03:31,870 --> 00:03:33,970
are related to two
major polls that

79
00:03:33,970 --> 00:03:37,040
are assigned across many
different states in the United

80
00:03:37,040 --> 00:03:38,140
States.

81
00:03:38,140 --> 00:03:40,720
And it represents the
percentage of voters

82
00:03:40,720 --> 00:03:42,950
who said they were
likely to vote Republican

83
00:03:42,950 --> 00:03:44,410
minus the percentage
who said they

84
00:03:44,410 --> 00:03:45,710
were likely to vote Democrat.

85
00:03:45,710 --> 00:03:49,520
So for instance, if the variable
SurveyUSA in our data set

86
00:03:49,520 --> 00:03:53,310
has value -6, it means
that 6% more voters

87
00:03:53,310 --> 00:03:55,420
said they were likely
to vote Democrat

88
00:03:55,420 --> 00:03:58,880
than said they were likely to
vote Republican in that state.

89
00:03:58,880 --> 00:04:00,430
We have two additional
variables that

90
00:04:00,430 --> 00:04:03,290
capture polling data from
a wider range of polls.

91
00:04:03,290 --> 00:04:06,420
Rasmussen and SurveyUSA are
definitely not the only polls

92
00:04:06,420 --> 00:04:09,100
that are run on a
state by state basis.

93
00:04:09,100 --> 00:04:12,240
DiffCount counts the number
of all the polls leading up

94
00:04:12,240 --> 00:04:16,000
to the election that predicted a
Republican winner in the state,

95
00:04:16,000 --> 00:04:19,160
minus the number of polls that
predicted a Democratic winner.

96
00:04:19,160 --> 00:04:22,420
And PropR, or
proportion Republican,

97
00:04:22,420 --> 00:04:24,850
has the proportion of all
those polls leading up

98
00:04:24,850 --> 00:04:29,160
to the election that
predicted a Republican winner.