PWGSC Contract #: 35035-161432/001/CY

POR Registration #: POR – 081-16

Contract Award Date: 12/12/2016

Government Priorities Quantitative Survey – Winter 2017 – Methodological report

Submitted to:

Privy Council Office (PCO)

March 29, 2017

For more information: por-rop@pco.gc.ca

Ce rapport est aussi disponible en français.

EKOS Research Associates
359 Kent Street, Suite 300

Ottawa, ON K2P 0R6
p. 613.235.7215

f. 613.235.8498

e. pobox@ekos.com

EKOS RESEARCH ASSOCIATES

Ottawa Office
359 Kent Street, Suite 300
Ottawa, Ontario
K2P 0R6
Tel: (613) 235 7215
Fax: (613) 235 8498
E-mail: pobox@ekos.com

Toronto Office
51 Wolseley Street
Toronto, Ontario M5T 1A4
Tel: (416) 598-8002
Fax: (416) 533-4713
Email: toronto@ekos.com

Winnipeg Office
7 Prominence Point
Winnipeg, Manitoba
R3Y 0A9
Tel: (204) 221-9923
E-mail: winnipeg@ekos.com

www.ekos.com{#_Toc505493043 .anchor}

Executive Summary

Background

The Communications and Consultations Secretariat of the Privy Council Office (PCO) provides advice and support to the Government of Canada, the Clerk of the Privy Council and to departments/agencies on matters relating to communications and consultations, and facilitates the coordination of the Government of Canada’s activities in these areas. One tool used in order to fulfil its mandate is public opinion research.

PCO commissioned EKOS Research Associates to conduct a survey to assess the concerns and the perceptions of Canadians on government priorities.

Research Purpose and Objectives

Through the use of this survey, PCO assessed the perceptions of Canadians on government priorities, which may include for example, their opinions on the economy. This input is needed because complex issues are often difficult to communicate to the Canadian public in a manner that is easily and clearly understood. By carrying out this research PCO will be able to ensure a better understanding of the views and concerns of the public, and develop effective communications strategies and products.

Methodology

The methodology for this study involved a telephone survey with a representative random sample of some 6,000 Canadians. In order to increase the proportion of younger Canadians (i.e. 18-34 years) in the sample, EKOS incorporated roughly 20 per cent cell phone only (CPO) respondents.

The survey was approximately 12 minutes on average and was conducted over a 12-week period, with data collection spread evenly over this field collection window. Thus, each week EKOS completed a random, representative sample of some 500 Canadians of which roughly 400 were landline respondents and 100 were CPO respondents. In total, we collected 6,048 cases: 4,206 landline and 1,842 cell phone (of which 1,219 were cell phone only).

PCO provided an updated questionnaire at different points over the field period (approximately every 2 weeks).

Expenditure

Total expenditure on this project was $199,800.95 (including HST).

I hereby certify as Senior Officer of EKOS Research Associates Inc. that the deliverables fully comply with the Government of Canada political neutrality requirements outlined in the Communications Policy of the Government of Canada and Procedures for Planning and Contracting Public Opinion Research. Specifically, the deliverables do not include information on electoral voting intentions, political party preferences, standings with the electorate or ratings of the performance of a political party or its leaders.

Derek Jansen

Vice President

EKOS Research

Appendix A Methodology

Overview of Methodology

The methodology for this study involved a telephone survey with a representative random sample of some 6,000 Canadians. In order to increase the proportion of younger Canadians (i.e. 18-34 years) in the sample, EKOS incorporated roughly 20 per cent cell phone only (CPO) respondents.

The survey was approximately 12 minutes on average and was conducted over a 12-week period, with data collection spread evenly over this field collection window. Thus, each week EKOS completed a random, representative sample of some 500 Canadians of which roughly 400 were landline respondents and 100 were CPO respondents. In total, we collected 6,048 cases: 4,206 landline and 1,842 cell phone (of which 1,219 were cell phone only).

PCO provided an updated questionnaire at different points over the field period (approximately every 2 weeks).

Pre-test

The questionnaire was pre-tested over the telephone in English and in French on January 4, 2017. The objective of the pre-test was to ascertain the clarity of the questions, the flow of the sequencing, the overall length of the interviews and any factors that may affect the response rate. No significant problems were revealed through the pre-test (other than the length of the survey, resulting in some question cuts), and full fieldwork commenced.

Survey Implementation/Quality Control

Throughout the data collection, survey supervisors continuously monitored interviewing to ensure consistency of questionnaire administration and interviewing techniques.

Up to eight call-backs were made to each member of the sample for which initial attempts at contact were unsuccessful. Follow-up calls were made on subsequent days, at varying time periods to maximize the potential for reaching a given respondent. Appointments were made for respondents wishing to reschedule a survey. Daily records were kept of all calls made, whether successful or not.

Weighting

Results were weighted according to age, region, and gender to ensure the sample was representative of the general public aged 18 years and older. Weighting for age, region and gender was based on Statistics Canada data.

Analysis of Non-Response Bias

The table below provide a comparison of the (unweighted) survey sample with population parameters across region, gender and age to help determine the potential for non-response bias in the sample. The population parameters were obtained through Statistics Canada data.

As can be seen, the survey sample generally reflects the population in terms of gender and region, although the survey sample contains somewhat fewer Ontario and Quebec residents, and somewhat more men. The survey sample contains somewhat fewer of those aged less than 35, and more of those aged 55 and over than is found in the population.

We also examined (unweighted and weighted) differences between the survey sample and population parameters across other demographics (education and income) to help determine other potential non-response bias in the sample. The population parameters were obtained through Statistics Canada data.

As can be seen, the survey sample generally reflects the population in terms of income, however, the survey sample contains more respondents with university education, and fewer with high school education or less, than is found in the population.

Survey Response Rate

The tables below provide the call disposition and the response rate for the survey using MRIA calculations.

The empirical response rate for the completed interviews was 12.5% for the landline telephone sample and 6.8% for the cell sample (9.8% overall). The response rate is calculated by dividing the in-scope responding eligible by the total (functional) sample – see tables below.

Call Disposition - Overall

Call Disposition - Landline

Call Disposition - Cell

Appendix B questionnaire