Methodology Statement and Topline for iMediaEthics Poll on Supreme Court Nominee - iMediaEthics
Menu

Home » Media Polls»

(Credit: Tim Sackton via Flickr)

Methodology Statement and Topline for iMediaEthics Poll on Supreme Court Nominee

Conducted by Princeton Survey Research Associates International (PSRAI)

 

This survey was sponsored by iMediaEthics, which designed the questions, and was funded by the Perry and Donna Golkin Foundation. The actual interviewing was conducted by Princeton Survey Research Associates International (PSRAI) in its April 2016 Omnibus Week 1 poll. For further information about the survey, please contact Sydney Smith at iMediaEthics (sydney@imediaethics.org). Read the analysis here.

PSRAI obtained telephone interviews with a nationally representative sample of 1,000 adults living in the continental United States. Telephone interviews were conducted by landline (500) and cell phone (500, including 318 without a landline phone). Interviews were done in English and Spanish by Princeton Data Source from April 7-10, 2016. Statistical results are weighted to correct known demographic discrepancies. The margin of sampling error for the complete set of weighted data is ± 3.6 percentage points.

 

Final Topline Results Prepared by PSRAI

April 11, 2016

 

Total:1,000 adults age 18 and older
Margin of error: plus or minus 3.6 percentage points
Half sample A:466 adults age 18 and older
Margin of error: plus or minus 5.3 percentage points
Half sample B:534 adults age 18 and older
Margin of error: plus or minus 5.0 percentage points

 

INTERVIEW DATES: April 7-10, 2016

 

LANDLINE INTRODUCTION:

Hello, my name is _________________ and I’m calling for Princeton Survey Research. We’re conducting a study about some important issues today, and would like to include your household. [RANDOMIZE RESPONDENT SELECTION: May I please speak with the YOUNGEST ADULT MALE, age 18 or older, who is now at home? (IF NO MALE AT HOME NOW, ASK: May I please speak with the YOUNGEST ADULT FEMALE, age 18 or older, who is now at home?) / May I please speak with the YOUNGEST ADULT FEMALE, age 18 or older, who is now at home? (IF NO FEMALE AT HOME NOW, ASK: May I please speak with the YOUNGEST ADULT MALE, age 18 or older, who is now at home?)]

 

CELL PHONE INTRO:

Hello, I am ___ calling for Princeton Survey Research. We’re conducting a study about some important issues today. [IF RESPONDENT SAYS DRIVING/UNABLE TO TAKE CALL: Thank you. We will try you another time…]

 

CELL PHONE SCREENING INTERVIEW:

S1. Are you under 18 years old, OR are you 18 or older? [CONTINUE IF 18 OR OLDER; ALL OTHERS TERMINATE]

READ TO ALL CELL PHONE – INTRODUCTION TO MAIN INTERVIEW: If you are now driving a car or doing any activity requiring your full attention, I need to call you back later. The first question is…

 

Notes: Due to rounding, percentages may not add to 100%. An asterisk (*) indicates values less than 0.5%. Volunteered responses are indicated by (VOL.).

 

IMED1. How much, if anything, have you heard about Barack Obama’s choice of Merrick Garland to be the next Supreme Court justice? Have you heard [READ IN ORDER]?

%
A lot29
A little42
Nothing at all29
(VOL.) Don’t know*
(VOL.) Refused0

 

IMED2A. From what you’ve seen and heard so far, do you think the Senate should or should not confirm Merrick Garland to the Supreme Court?

 

Based on half sample A (n=466)

%
Should 39
Should not30
(VOL.) Don’t know28
(VOL.) Refused2

 

IMED2A-1. If the Senate DOES NOT confirm Merrick Garland to the Supreme Court, how upset would you be (READ)

 

Based on half sample A who think Senate SHOULD confirm (n=188)

%
Very 36
Somewhat31
Not too8
Not upset at all20
(VOL.) Don’t know4
(VOL.) Refused1

 

IMED2A-2. If the Senate DOES vote to confirm Merrick Garland to the Supreme Course, how upset would you be (READ)

 

Based on half sample A who think Senate SHOULD NOT confirm (n=144)

%
Very 28
Somewhat31
Not too17
Not upset at all23
(VOL.) Don’t know*
(VOL.) Refused0

 

IMED2B. From what you’ve seen and heard so far, do you think the Senate should or should not confirm Merrick Garland to the Supreme Court – or are you unsure?

 

Based on half sample B (n=534)

%
Should 24
Should not18
Unsure/Don’t know56
(VOL.) Refused1

 

IMED2B-1. If the Senate DOES NOT vote to confirm Merrick Garland to the Supreme Court, how upset would you be (READ)

 

Based on half sample B who think Senate SHOULD confirm (n=154)

%
Very 47
Somewhat29
Not too9
Not upset at all14
(VOL.) Don’t know1
(VOL.) Refused*

IMED2B-2. If the Senate DOES vote to confirm Merrick Garland to the Supreme Court, how upset would you be (READ)

 

Based on half sample B who think Senate SHOULD NOT confirm (n=115)

%
Very 46
Somewhat33
Not too8
Not upset at all11
(VOL.) Don’t know2
(VOL.) Refused0

 

DEMOGRAPHICS

 

I have one last set of questions to help us better understand the people who took part in our survey.

 

SEX Respondent’s sex [DO NOT ASK]

%
Male49
Female51

 

EMPLOY Are you now employed full-time, part-time, or not employed?

%
Employed full-time42
Employed part-time14
Not employed43
(VOL.)Don’t know/Refused1

 

PAR Are you the parent or guardian of any children under 18 years of age?

%
Yes25
No72
(VOL.) Don’t know/Refused3

 

AGE What is your age?

%
18 to 2919
30 to 4929
50 to 6428
65 and older16
(VOL.) Refused8

 

EDUC What is the highest level of school you have completed or the highest degree you have received? [DO NOT READ]

%
Less than high school (Grades 1-8 or no formal schooling)3
High school incomplete (Grades 9-11 or Grade 12 with NO diploma)6
High school graduate (Grade 12 with diploma or GED certificate)31
Some college, no degree (includes some community college)19
Two year associate degree from a college/university12
Four year college or university degree/Bachelor’s degree17
Some postgraduate or professional schooling, no postgraduate degree*
Postgraduate or professional degree, including master’s, doctorate, medical or law degree9
Don’t know/Refused2

 

Summary: Race/Ethnicity

HISP Are you of Hispanic or Latino origin, such as Mexican, Puerto Rican, Cuban or some other Spanish background?

RACE What is your race? Are you white, black, Asian, or some other race? [IF RESPONDENT SAYS HISPANIC OR LATINO, PROBE: Do you consider yourself a WHITE (Hispanic/Latino) or a BLACK (Hispanic/Latino)?

%
White, non-Hispanic63
Total non-White34
Black, non-Hispanic11
Hispanic15
Asian/Pacific Islander, non-Hispanic4
Other, non-Hispanic4
(VOL.) Don’t know/Refused3

 

Summary: Income

INC Last year – that is, in 2015 – approximately what was your total family income before taxes? Just tell me when I get to the right category.

INC1 [IF “DON’T KNOW” OR “REFUSED”, ASK:] Keeping in mind that this is a completely confidential survey, can you please tell me if your total household income BEFORE taxes last year was over or under $75,000?

INC2 [IF UNDER $75,000, ASK:] was it over or under $50,000?

INC3 [IF UNDER $50,000, ASK:] was it over or under $30,000?

%
$75,000 or more25
$50,000 to under $75,00011
$30,000 to under $50,00017
Under $30,00036
Undesignated 11

 

REG Which of these statements best describes you? [READ IN ORDER]

%
Are you ABSOLUTELY CERTAIN that you are registered to vote at your current address72
Are you PROBABLY registered, but there is a chance your registration has lapsed, OR6
Are you NOT registered to vote at your current address?21
(VOL.) Don’t know/Refused1

 

PARTY In politics TODAY, do you consider yourself a Republican, Democrat, or Independent?

%
Republican 24
Democrat 33
Independent 35
(VOL.) No preference3
(VOL.) Other party*
(VOL.) Don’t know/Refused5

 

That completes the interview. Thank you very much for your time and cooperation. Have a nice day/evening.

 

###

Methodology

April 2016 Omnibus Week 1

Prepared by Princeton Survey Research Associates International

April 2016

 

The PSRAI April 2016 Omnibus Week 1 obtained telephone interviews with a nationally representative sample of 1,000 adults living in the continental United States. Telephone interviews were conducted by landline (500) and cell phone (500, including 318 without a landline phone). The survey was conducted by Princeton Survey Research Associates International (PSRAI). Interviews were done in English and Spanish by Princeton Data Source from April 7-10, 2016. Statistical results are weighted to correct known demographic discrepancies. The margin of sampling error for the complete set of weighted data is ± 3.6 percentage points.

Details on the design, execution and analysis of the survey are discussed below.

DESIGN AND DATA COLLECTION PROCEDURES

 

Sample Design

 

A combination of landline and cellular random digit dial (RDD) samples was used to represent all adults in the continental United States who have access to either a landline or cellular telephone. Both samples were provided by Marketing Systems Group (MSG) according to PSRAI specifications.

Numbers for the landline sample were drawn with equal probabilities from active blocks (area code + exchange + two-digit block number) that contained one or more residential directory listings. The cellular sample was not list-assisted, but was drawn through a systematic sampling from dedicated wireless 100-blocks and shared service 100-blocks with no directory-listed landline numbers.

Contact Procedures

Interviews were conducted from April 7-10, 2016. As many as three attempts were made to contact every sampled telephone number. Sample was released for interviewing in replicates, which are representative subsamples of the larger sample. Using replicates to control the release of sample ensures that complete call procedures are followed for the entire sample. Calls were staggered over times of day and days of the week to maximize the chance of making contact with potential respondents. Each phone number received at least one daytime call when necessary.

For the landline sample, interviewers asked to speak with the youngest adult male or female currently at home based on a random rotation. If no male/female was available, interviewers asked to speak with the youngest adult of the other gender. This systematic respondent selection technique has been shown to produce samples that closely mirror the population in terms of age and gender when combined with cell interviewing. Prior to dialing, the landline sample was scrubbed of numbers that have been ported to wireless service by comparing the sample file to the most recently available Intermodal Ported Telephone Number Identification Service database.

For the cellular sample, interviews were conducted with the person who answered the phone. Interviewers verified that the person was an adult and in a safe place before administering the survey.

WEIGHTING AND ANALYSIS

 

Weighting is generally used in survey analysis to compensate for sample designs and patterns of non-response that might bias results. The sample was weighted to match national adult general population parameters. A two-stage weighting procedure was used to weight this dual-frame sample.

The first stage of weighting corrected for different probabilities of selection associated with the number of adults in each household and each respondent’s telephone usage patterns. This weighting also adjusts for the overlapping landline and cell sample frames and the relative sizes of each frame and each sample.

This first-stage weight for the ith case can be expressed as:

WTi=[(SLLFLL×1ADi×LLi)+(SCPFCP×CPi)(SLLFLL×1ADi×LLi×SCPFCP×CPi)]-1

 

Where SLL = the size of the landline sample

FLL = the size of the landline sample frame

SCP = the size of the cell sample

FCP = the size of the cell sample frame

ADi = Number of adults in household i

LLi=1 if respondent has a landline phone, otherwise LL=0.

CPi=1 if respondent has a cell phone, otherwise CP=0.

 

The second stage of weighting balanced sample demographics to population parameters. The sample is balanced by form to match national population parameters for sex, age, education, race, Hispanic origin, region (U.S. Census definitions), population density, and telephone usage. The basic weighting parameters came from the US Census Bureau’s 2014 American Community Survey data. The population density parameter was derived from Census 2010 data. The telephone usage parameter came from an analysis of the January-June 2015 National Health Interview Survey.

Weighting was accomplished using SPSSINC RAKE, an SPSS extension module that simultaneously balances the distributions of all variables using the GENLOG procedure. Weights were trimmed to prevent individual interviews from having too much influence on the final results. The use of these weights in statistical analysis ensures that the demographic characteristics of the sample closely approximate the demographic characteristics of the national population. Table 1 compares weighted and unweighted sample distributions to population parameters.

 

Table 1: Sample Demographics  
ParameterUnweightedWeighted
Gender
Male48.3%49.2%48.6%
Female51.7%50.8%51.4%
Age
18-2412.9%7.2%12.1%
25-3417.6%16.7%18.0%
35-4416.7%12.0%16.1%
45-5417.8%14.3%17.8%
55-6416.4%18.3%16.8%
65+18.6%31.5%19.2%
Education
HS Graduate or Less40.7%33.9%40.4%
Some College/Assoc Degree31.5%25.2%31.0%
College Graduate27.8%40.9%28.6%
Race/Ethnicity
White/not Hispanic65.3%73.3%66.4%
Black/not Hispanic11.8%7.4%10.5%
Hispanic15.3%11.8%15.3%
Other/not Hispanic7.6%7.5%7.8%
Region
Northeast18.2%18.5%18.4%
Midwest21.3%22.1%21.6%
South37.6%33.6%36.7%
West22.9%25.8%23.3%
County Pop. Density
1 – Lowest19.9%20.4%19.7%
220.0%21.9%20.3%
320.1%19.2%19.7%
420.0%19.4%20.2%
5 – Highest20.0%19.1%20.0%
Household Phone Use
LLO6.2%6.7%6.2%
Dual 43.1%61.5%44.1%
CPO50.7%31.8%49.7%

 

Effects of Sample Design on Statistical Inference

Post-data collection statistical adjustments require analysis procedures that reflect departures from simple random sampling. PSRAI calculates the effects of these design features so that an appropriate adjustment can be incorporated into tests of statistical significance when using these data. The so-called “design effect” or deff represents the loss in statistical efficiency that results from unequal weights. The total sample design effect for this survey is 1.37.

PSRAI calculates the composite design effect for a sample of size n, with each case having a weight, wi as:

 

In a wide range of situations, the adjusted standard error of a statistic should be calculated by multiplying the usual formula by the square root of the design effect (√deff ). Thus, the formula for computing the 95% confidence interval around a percentage is:

 

where is the sample estimate and n is the unweighted number of sample cases in the group being considered.

The survey’s margin of error is the largest 95% confidence interval for any estimated proportion based on the total sample— the one around 50%. For example, the margin of error for the entire sample is ±3.6 percentage points. This means that in 95 out every 100 samples drawn using the same methodology, estimated proportions based on the entire sample will be no more than 3.6 percentage points away from their true values in the population. The margin of error for estimates based on the form split is ±5.3 percentage points. It is important to remember that sampling fluctuations are only one possible source of error in a survey estimate. Other sources, such as respondent selection bias, questionnaire wording and reporting inaccuracy, may contribute additional error of greater or lesser magnitude.

 

RESPONSE RATE

 

Table 2 reports the disposition of all sampled telephone numbers ever dialed from the original telephone number samples. The response rate estimates the fraction of all eligible sample that was ultimately interviewed. Response rates are computed according to American Association for Public Opinion Research standards. Thus the response rate for the landline samples was 5 percent. The response rate for the cellular samples was 4 percent.

 

Table 2. Sample Disposition
LandlineCell
1,29258Non-residential/Business
455—-Cell in landline frame
1,74758OF = Out of Frame
26,3063,052Not working
95937Computer/fax/modem
27,2653,089NWC = Not working/computer
2,9212,427UHUONC = Non-contact, unknown if household/unknown other
4,9628,785Voice mail
9831Other non-contact
5,0608,816UONC = Non-contact, unknown eligibility
2,5152,743Refusals
519832Callbacks
3,0343,575UOR = Refusal, unknown if eligible
4673O = Other
152Child’s cell phone
152SO = Screen out
71109R = Refusal, known eligible
500500I = Completed interviews
40,64418,799T = Total numbers sampled
23.1%80.8%e1 = (I+R+SO+O+UOR+UONC)/(I+R+SO+O+UOR+UONC+OF+NWC) – Est. frame eligibility of non-contacts
100.0%80.0%e2 = (I+R)/(I+R+SO) – Est. screening eligibility of unscreened contacts
38.9%29.0%CON = [I + R + (e2*[O + UOR])]/[I + R + (e2*[O + UOR + UONC]) + (e1*e2*UHUONC)]
13.7%14.2%COOP = I/[I + R + (e2*[O + UOR])]
5.3%4.1%AAPOR RR3=I/[I+R+[e2*(UOR+UONC+O)]+[e1*e2*UHUONC]] = CON*COOP

UPDATED: 6/24/2016 12:42 PM EST

Submit a tip / Report a problem

Methodology Statement and Topline for iMediaEthics Poll on Supreme Court Nominee

Share this article:

Comments Terms and Conditions

  • We reserve the right to edit/delete comments which harass, libel, use coarse language and profanity.
  • We moderate comments especially when there is conflict or negativity among commenters.
  • Leave a Reply

    Your email address will not be published. Required fields are marked *