Skip to content

Jan Kestle and Vivek Goel – The Need For Good Data

May 10/2013

Go to the Globe and Mail homepage

For The Globe and Mail

This morning's census, dimmed by Ottawa, shows the need for good data

Published Tuesday, May. 07, 2013 12:24PM EDT

Last updated Wednesday, May. 08, 2013 08:08AM EDT

On Wednesday, Statistics Canada is releasing the first results from the National Household Survey (NHS). The NHS replaces what was previously known as the mandatory long-form census, which was completed by 20 per cent of households. Back in 2010, there was considerable controversy with regards to this change, as many felt that moving from a mandatory to a voluntary survey might reduce the quality of data available for a variety of purposes. With the release on Wednesday, we will start to learn if those concerns were warranted.

Why is this an important issue? Data of this type are invaluable for the functioning of our society. In the public sector we use this data to guide development, implementation and monitoring of programs in areas such as education, housing, transportation, and health. In the private sector these data are used to develop and deliver products and services that meet the needs of consumers. When businesses have accurate demographic data on cities and neighbourhoods, they know where growing families need childcare services and toy stores and whether car buyers are more likely to choose pickup trucks or minivans. And because the data help marketers better understand the tastes and preferences of specific neighbourhoods, consumers receive offers that are relevant to them, such as coupons they will actually use and events they are more likely to attend. Even not-for-profits benefit from demographic data when designing programs to combat cancer or launching fundraising campaigns in support of the arts.

What are we going to be looking for today? Data users across the country will be examining the results from the NHS to look for the completeness of the information, and any biases that may exist. By completeness we mean: do we have a full count for the variables that are examined? In particular, we need to assess whether the counts are complete across different geographies in the country, particularly at the small area, or neighbourhood level. By bias we mean: are the results reflective of the “truth”? Bias could be introduced if some population groups were less likely to respond to the survey, or some of its questions. This might mean that the reported result for a particular community is higher or lower than it really is. Errors in such data can lead to programs not being properly planned or evaluated, or services, both public and private, being delivered in the wrong way or place.

We hope that Wednesday’s release of the NHS initiates a discussion about the importance of reliable national statistics. We recognize that the debates in the summer of 2010 may have been emotional at times. We trust that now, with knowledge of how the NHS has actually fared, we can have an informed discussion about whether it meets the collective needs of a large country and its communities.

Jan Kestle is founder and president of Environics Analytics. Vivek Goel is president and CEO of Public Health Ontario