Statistics Canada organizes conferences to bring together analysts, researchers, planners, and policy- and decision-makers to network, share insights and discuss topics of interest.

Upcoming conferences

• Canadian Research Data Centre Network (CRDCN) 2025 preconference workshops

Past conferences

• 2024 Health Data User Conference
• 2024 International Methodology Symposium

• For information on conferences held before 2024, please email infostats@statcan.gc.ca

The Visitor Travel Survey (VTS) provides a full range of statistics on the volume of international visitors to Canada and detailed characteristics of their trips. In recent years, there has been an increased interest in estimating sub-provincial inbound travel spending. Direct estimates of foreign travel spending can be obtained from the VTS, but they would be reliable only if the sample sizes are large enough. Therefore, a Small Area Estimation (SAE) methodology is now used to improve the quality of sub-provincial estimates, using Payment processors' (acquirer) data provided by Destination Canada. This document briefly describes this methodology.

1. Introduction

The VTS was introduced in January 2018 to replace the U.S. and overseas visitors to Canada component of the International Travel Survey (ITS). The objective of the VTS is to provide a full range of statistics on the volume of international visitors to Canada and detailed characteristics of their trips such as expenditures, activities, places visited and length of stay. The target population of the VTS is all U.S. and overseas residents entering Canada. Excluded from the survey's coverage are diplomats and their dependents, refugees, landed immigrants, military, crew and former Canadian residents.

The demand for inbound travel spending estimates at smaller geographical levels has greatly increased in recent years. Standard weighted estimates (or direct estimates) at sub-provincial levels can be obtained from the VTS. However, these direct estimates can be considered reliable as long as the sample size in the area of interest is large enough. To address this issue, a SAE methodology is used to improve the quality of sub-provincial estimates, using Payment processors' data provided by Destination Canada.

SAE methods attempt to produce reliable estimates when the sample size in the area is small. In this application of the methodology, the small area estimate is a function of two quantities: the direct estimate from the survey data, and a prediction based on a model – sometimes referred to as the indirect, or synthetic estimate. The model involves survey data from the geographical area of interest, but also incorporates data from other areas (as input to the model parameters) and auxiliary data. The auxiliary data must come from a source that is independent of the VTS, and it must be available at the appropriate levels of geography. The SAE model uses the Payment processors' data which includes a portion of credit and debit card payments made by international visitors to Canada, as the auxiliary data. More precisely, the Payment data along with the direct survey estimates, are used to derive the small area estimates. For the smallest areas, the direct estimates are not reliable and the small area estimates are driven mostly by the predictions from the model. However, for the largest areas, this is the opposite and the small area estimates tend to be close to the direct estimates.

There are two types of SAE models: area-level (or aggregate) models that relate small area means to area-specific auxiliary variables, and unit-level models that relate the unit values of the study variable to unit-specific auxiliary variables. The VTS uses an area-level model as the auxiliary information (i.e., Payment data) is aggregated.

Section 2 describes the requirements to produce sub-provincial inbound travel spending estimates. In section 3, diagnostics used for model validation and evaluation of small area estimates are briefly discussed.

2. Area-level model

The small area estimates were obtained through the use of the small area estimation module of the generalized software G-EST^{Footnote 1} version 2.02 (Estevao et al., 2017a, 2017b). For each area i, three inputs need to be provided to the G-EST in order to obtain small area estimates:

i) Direct estimates ${\hat{\theta }}_i$, which are calculated using survey weights
${\hat{\theta }}_i=\sum _{k\in s_i}{w}_k{y}_k$
where $y_k$ represents spending by unit k in domain i, and $w_k$ is the sampling weights assigned to unit k on the VTS sample

ii) Smoothed variance estimates at the domain of interest, which are obtained by applying a piecewise smoothing approach on the variance estimates that are calculated using mean bootstrap weights

iii) Vector of auxiliary variables $z_i$

For the estimation of inbound travel spending, the domain of interest are defined as: 11 country / country groups × 22 tourism regions / grouped tourism regions

The 11 country / country groups are as follows:

The 84 tourism regions are grouped into 22 domains, as shown in the following table.

It should be mentioned that for the VTS, a modification of the basic area-level model, piecewise area-level model, was used. The piecewise area-level is useful when a single linear model does not provide an adequate explanation on the relationship between the variable of interest and the covariates. The area specific auxiliary variable i.e., spending from the Payment data, is partitioned into intervals and a separate line segment is fit to each interval.

3. Evaluation of small area estimates

The accuracy of small area estimates depends on the reliability of the model. It is therefore essential to make a careful assessment of the validity of the model before releasing estimates. For instance, it is important to verify that a linear relationship actually holds between direct estimates from VTS (${\hat{\theta }}_i$) and payment data ($z_i$), at least approximately.

For the VTS, diagnostic plots and tests in the G-EST are used to assess the model, and outliers are identified iteratively by examining the standardized residuals from that model.

A concept that is useful to evaluate the gains of efficiency resulting from the use of the small area estimate ${\hat{\theta }}_i^{\mathrm{SAE}}$ over the direct estimate ${\hat{\theta }}_i$ is the Mean Square Error (MSE. The MSE is unknown but can be estimated (see Rao and Molina, 2015). Gains of efficiency over the direct estimate are expected when the MSE estimate is smaller than the smoothed variance estimate or the direct variance estimate. In general, the small area estimates in the VTS were significantly more efficient than the direct estimates, especially for the areas with the smallest sample size.

References

Estevao, V., You, Y., Hidiroglou, M., Beaumont, J.-F. (2017a). Small Area Estimation-Area Level Model with EBLUP Estimation- Description of Function Parameters and User Guide. Statistics Canada document.

Estevao, V., You, Y., Hidiroglou, M., Beaumont, J.-F. and Rubin-Bleuer, S. (2017b). Small Area Estimation-Area Level Model with EBLUP Estimation- Methodology Specifications. Statistics Canada document.

Rao, J.N.K., and Molina, I. (2015). Small Area Estimation. John Wiley & Sons, Inc., Hoboken, New Jersey.

Statistics Canada. (2017). Monthly Labour Force Survey Small Area Estimation- Documentation to accompany small area estimates. Statistics Canada document.

As we chart new paths and methods of collecting data, we want to underline that at Statistics Canada, your privacy is protected every day. It is our obligation to keep your data safe and we take this responsibility seriously. Your trust allows us to do our job. We must continue to provide accurate and timely economic and social data, and insights to enable sound policy decisions.

As part of our commitment to transparency, Statistics Canada invites you to meet our Trust Centre team. If you have any questions, please contact us.

André Loranger, Chief Statistician of Canada

André Loranger is an experienced senior public official, having worked at Statistics Canada for 26 years, leading large and complex statistical programs covering all aspects of the Canadian economy. He has previously served in various senior leadership positions in the Agency including Assistant Chief Statistician for Economic Statistics and Assistant Chief Statistician for Strategic Data Management, Methods and Analysis. In that capacity, Mr. Loranger was also Statistics Canada's Chief Data Officer responsible for the overall stewardship of the organization's information data holdings.

Mr. Loranger represents Statistics Canada on various international expert groups pertaining to economic statistics. He is currently the chair of the United Nations Network of Economic Statisticians and the chair of the United Nations Committee of Experts on Environmental-Economic Accounting. He is also a board member of the Canadian Association for Business Economics and the Conference on Research in Income and Wealth.

Mr. Loranger holds an M.A. (Economics) degree and a Bachelor of Social Sciences (Economics) from the University of Ottawa.

Stéphane Dufour, Special Advisor

Stéphane Dufour has been with Statistics Canada for 33 years and has held various key positions—mostly in collection and operations—and lead several major transformational initiatives along the way. He became an executive in 2006, taking on the role of Director of Administrative Support Services. In 2008, Stéphane was appointed as Director General of the Collection and Regional Services Branch and, in 2012, he was appointed as Director General of the Human Resources Branch. Later in that same year, he became the Assistant Chief Statistician responsible for Corporate Services and the Chief Financial Officer.

Prior to his current role, Stéphane served as the Assistant Chief Statistician of the Census, Regional Services and Operations Field. Most recently, he has been appointed as a Special Advisor within the agency. Additionally, he is the co-chair of the executive board for the United Nations High-Level Group for the Modernisation of Official Statistics and has been involved in several international cooperation projects over his career.

Stéphane holds a bachelor's degree in business administration (accounting) from Université du Québec à Hull (now Université du Québec en Outaouais) and studied economics at the University of Ottawa. He also holds a graduate certificate in Advanced Public Sector Management from the University of Ottawa and participated in the Advanced Leadership Program of the Canada School of Public Service.

Kathleen Mitchell, Assistant Chief Statistician, Corporate Strategy and Management Field, and Chief Financial Officer

Kathleen Mitchell has been the Assistant Chief Statistician of the Corporate Strategy and Management Field and the Chief Financial Officer at Statistics Canada since September 2022. Kathleen was previously the Director General of the Finance, Planning and Procurement Branch and the Deputy Chief Financial Officer of the agency from April 2018 to September 2022. She began her career at Statistics Canada in 1998 as a student and took on various functions within the former Finance Branch, including eight years as an executive. She previously accepted the position of Director, Resource Management, at the Department of Justice in December 2016 before returning to Statistics Canada as Director General. Kathleen has a keen interest in team leadership and all aspects of human resources. She also has a busy family and appreciates time to read.

Geoff Bowlby, Assistant Chief Statistician, Census, Regional Services and Operations Field

Geoff Bowlby has been with Statistics Canada for 29 years, with a background as an economist and project manager.

Prior to taking on the role of Assistant Chief Statistician in 2024, Geoff was Canada’s Census Manager and steered the agency’s most extensive and complex statistical program through the impact of a global pandemic. He also served as the Director General of Collection and Regional Services Branch, the director responsible for the monthly Labour Force Survey, as well as the director of Special Surveys.

Geoff is currently running two UN task forces focussed on the revision of the international manuals being developed for the next worldwide round of population and housing censuses.

Outside of work, Geoff is active with his family. For years, he coached his son’s hockey team, and with his wife, attended figure skating to cheer on their two daughters.

Geoff has a bachelor’s degree in Economics from Glendon College at York University and a master’s in Economics from the University of Waterloo. In addition, he graduated from the University of Ottawa’s Certificate Program in Public Sector Leadership in 2020.

Josée Bégin, Assistant Chief Statistician, Social, Health and Labour Statistics Field

Josée Bégin has a master's degree in mathematics and statistics (MSc) from the University of Ottawa. She started her career at the Canada Revenue Agency in 1994 before joining Statistics Canada in 2002, where she gained experience in overseeing large and complex statistical programs. Josée became the Assistant Chief Statistician of the Social, Health and Labour Statistics Field in January 2023.

The Social, Health and Labour Statistics Field provides accurate, timely and relevant information across a range of social topics to decision makers at all levels of government, non-governmental organizations, researchers and the Canadian public. Its portfolio includes a number of large survey and administrative data programs, such as the Centre for Population Health Data; the Canadian Centre for Justice and Community Safety Statistics; the Centre for Gender, Diversity and Inclusion Statistics; and the Centre for Labour Market Information. This field is also home to Canadian census content expertise.

Her favourite hobbies include yoga and reading.

Mélanie Scott, Chief Information Officer and Assistant Chief Statistician of the Digital Solutions Field

Committed to creating a diverse and bilingual and inclusive work environment throughout her career, Mélanie previously served as the Assistant Deputy Minister of the Digital Services Branch at Shared Services Canada. Prior to that, she provided leadership as an executive in IT security, data management business relationships and partnerships, and IT operations in various senior roles at the Communications Security Establishment Canada, and Library and Archives Canada.

A recipient of the Governor General's Academic Medal of Canada, Mélanie holds a Bachelor of Computer Science from the University of Sherbrooke and a Master of Business Administration EMBA (Executive MBA Program) from the University of Ottawa. A busy mother of three who enjoys running and skiing in her free time, Mélanie is currently completing the Certificate in Public Leadership and Governance with the University of Ottawa.

Eric Rancourt, Assistant Chief Statistician, Strategic Data Management, Methods and Analysis Field

Eric Rancourt is the Assistant Chief Statistician for the Strategic Data Management, Methods and Analysis Field at Statistics Canada. He is also Statistics Canada's Chief Data Officer.

He has worked at Statistics Canada for 33 years and has occupied several roles, such as Director General of the Modern Statistical Methods and Data Science Branch, Director General of Strategic Data Management, Director of International Cooperation, Director of Corporate Planning, Head of research, Production manager of Survey Methodology Journal, and Researcher.

His main areas of work have been on the treatment of non-response, estimation, and the use of administrative and alternative data in statistical programs. Recently, he has worked on frameworks for optimizing privacy and information, data ethics, and modern statistical designs.

He holds a BSc in Statistics from University Laval, BAs in Arts (Ancient Studies; Medieval and Renaissance Studies), as well as a BA in philosophy from the University of Ottawa focusing on data ethics. He is Chair of the Board for the Canadian Statistical Sciences Institute (CANSSI). He has been involved in many professional associations, including the International Association of Survey Statisticians (IASS) for which he is Vice-President, and the International Association for Official Statistics (IAOS), and is an elected member of the International Statistical Institute (ISI). He is Chair-Elect for the Survey Research Methods Section of the American Statistical Association (ASA) and he is also a member of the Statistical Society of Canada (SSC).

Jennifer Withington, Acting Assistant Chief Statistician for Economic Statistics

Jennifer Withington has been working at Statistics Canada for 27 years. As an executive since 2016, Jennifer has held various roles including Director General of the Macroeconomic Accounts, and Director of the International Accounts and Trade Division. She is responsible for key economic indicators such as the Consumer Price Index, Gross Domestic Product, and International Merchandise Trade.

Jennifer represents Statistics Canada on several International Committees including the United Nations (UN) Advisory Expert Group on National Accounts and the Group of Experts on National Accounts.

Jennifer holds a bachelor’s degree in economics and political Science as well as a master’s degree in economics from McGill University.

Learn about how we protect your data privacy

• Why your privacy is our top concern
• Is my information safe and private?
• Why does my information need to be collected?
• What are the laws surrounding data privacy?
• Transparency and accountability

Introduction

Statistics Canada is modernizing its methods of data access to improve its service to users of Statistics Canada data. The goal of modernization is to fully realize the potential of the data holdings created for the public good and increase collaboration and partnerships between data users and providers while ensuring that all data assets are protected against unauthorized use and disclosure.

Objective

This privacy impact assessment identifies and explores privacy, confidentiality and security issues associated with the use of video surveillance monitoring (camera monitoring) in secure facilities designed for the purposes of data access and makes recommendations for issue resolution or mitigation.

Description

As a first prototype, Statistics Canada undertakes to provide access to anonymized data for statistical research projects at the Virtual Federal Research Data Centre (vFRDC) located at Canada Mortgage and Housing Corporation (CMHC) headquarters in Ottawa. CMHC will benefit from this access by being able to create statistical information to improve policy decision-making, specifically, the Federal Government's National Housing Strategy.

This arrangement is referred to as a vFRDC because the anonymized data are no longer housed in the designated certified room. They are housed on secure servers at Statistics Canada headquarters and are accessed through Statistics Canada IT access protocols and devices in the designated certified room with a controlled entry swipe card system. Until now, this room has been open to only approved federal employees when a Statistics Canada employee is present (this security protocol was put in place to protect the data when they were housed on servers inside the designated certified room). Under the new prototype, where data are no longer housed in the secure room, a camera system will be used as an additional measure to monitor activities and access to the designated certified room when a Statistics Canada employee is not present.

The additional layer of camera monitoring of the designated certified room will provide more hours of operation with similar levels of security monitoring and decreased personnel costs for the client. Statistics Canada's use of the camera monitoring includes making recordings of activities in the secure designated room to offer enhanced protection of employees and assets.

Risk Area Identification and Categorization

The PIA also identifies the risk areas and categorizes the level of potential risk (level 1 representing the lowest level of potential risk and level 4, the highest) associated with the collection and use of personal information of employees.

• Type of program or activity – Level 2: Administration of program or activity and services.
• Type of personal information involved and context – Level 1: Only personal information, with no contextual sensitivities, collected directly from the individual or provided with the consent of the individual for disclosure under an authorized program.
• Program or activity partners and private sector involvement – Level 2: With other government institutions.
• Duration of the program or activity – Level 3: Long-term (ongoing) program.
• Program population – Level 1: The program's use of personal information for internal administrative purposes affects certain employees.
• Personal information transmission – Level 2: The personal information is used in a system that has connections to at least one other system.
• Technology and privacy: The new project involves the implementation of a new electronic system to support the program but does not involve the implementation of new technologies.
• Privacy breach: There is a very low risk of a breach of some of the personal information being disclosed:
  1. The impact on the employee would be minimal as it would only divulge a digital recording of the individual taken in the designated certified room.
  2. The impact on the institution would be minimal due to the low sensitivity of the information.

Conclusion

Statistics Canada has ensured that there are measures in place that meet central agency and Statistics Canada security standards for the protection of personal information captured by the system and the program.

This assessment concludes that, with the existing safeguards, any remaining risks are such that Statistics Canada is prepared to accept and manage the risk.