You are on page 1of 2

# METHODOLOGY

The NBC News Online Survey was conducted online by SurveyMonkey August 7-10, 2015 among a
national sample of 9,127adults aged 18 and over. Respondents for this non-probability survey were
selected from the nearly three million people who take surveys on the SurveyMonkey platform each
day.
Data for this survey have been weighted for age, race, sex, education, and region using the Census
Bureaus American Community Survey to reflect the demographic composition of the United States.
Because the sample is based on those who initially self-selected for participation rather than a
probability sample, no estimates of sampling error can be calculated. All surveys may be subject to
multiple sources of error, including, but not limited to sampling error, coverage error, and measurement
error. Polls conducted in one day may include additional error due to the limited time period that
panelists have to respond to and complete the survey.
To assess the variability in the estimates and account for design effects, we create a bootstrap
confidence interval to produce an error estimate, meaning we use the weighted data to generate 5000
independent samples and calculate the 95% confidence intervals for the weighted average.
When analyzing the survey results and their accuracy, this error estimate should be taken into
consideration in much the same way that analysis of probability polls takes into account the margin of
sampling error. For example, if 47 percent of voters say they support Candidate A and 43 percent of
voters support Candidate B, and the error estimate is plus or minus 3.5 percentage points, Candidate A
could be supported by as low as 44 percent of voters and Candidate B could have as high as 47 percent
of support. Therefore, Candidate A does not have a "lead."
The following table provides the unweighted sample sizes and the error estimate that has been
calculated in place of the margin of sampling error for a variable that is expected to have close to an
even split in most groupings (such as gender):

Group
Total sample

Unweighted N
Plus or minus
9,127
1.5 percentage points

Republican RVs
Democrat RVs

3,991
3,214

## 2.2 percentage points

2.6 percentage points

18-29
30-44
45-64
65+

1,109
2,015
4,273
1,730

## 4.1 percentage points

3.1 percentage points
2.2 percentage points
3.2 percentage points

White
Black
Hispanic
Other

7,375
566
453
733

## 1.5 percentage points

5.2 percentage points
5.9 percentage points
4.9 percentage points

We discovered an error in how we calculated respondents who skipped the primary question or had no
answer; we present the following tables to show how recalculating the no answers would change the
percentages. No percentage category changed more than 1 point, and the April numbers for the Democratic
nomination question had no differences. The table highlighted in yellow is what we originally published; the
green highlights indicate where a number shifted. We will use this new calculation going forward and publish
only the recalculated trends.

## [ASK OF DEMOCRATS AND LEAN DEMOCRATS]

19. Here is a list of possible candidates for the Democratic nomination for president in 2016. If the 2016
Democratic presidential primary or caucus in your state were being held today, for whom would you vote?
[RANDOMIZE RESPONSES 1-]
Joe Biden
Hillary Clinton
Martin OMalley
Bernie Sanders
Elizabeth Warren
Jim Webb
Lincoln Chafee
Someone else
Wouldnt vote/Dont know

7.20-26.15 RV
7
49
1
26
N/A
1
*
3
13
1

4.6-8.15 RV
7
50
2
5
16
1
N/A
1
19
*

Joe Biden
Hillary Clinton
Martin OMalley
Bernie Sanders
Elizabeth Warren
Jim Webb
Lincoln Chafee
Someone else
Wouldnt vote/Dont know

7.20-26.15 RV
7
48
1
26
N/A
1
*
3
13
1

4.6-8.15 RV
7
50
2
5
16
1
N/A
1
19
*