Before you start searching, analyze your data needs. Consider some of the following elements.
|
Who What |
Who or what are you interested in studying? What is your topic or area of interest? Be specific so that you can narrow your search, but be flexible in order to tailor your needs to existing sources. What is the unit of analysis that you are interested in (e.g individual level, economic regions, household, business). |
| Where |
What geographic coverage are you interested in? Are you interested in studying something at a local level or more broader? Have you considered using spatial data? It can exist in a variety of formats and contain more than just location (e.g. a geospatial hospital point dataset may contain information about year of construction, number of beds, or other relevant details). |
| When |
What time period do you want to study? Things to think about: are you interested in a "snapshot" or one-time study (think cross-sectional surveys), or how about time series data that studies changes over time. How about historical information? Not all historic information is available in digital formats and you may need to consider consulting print materials. How recent is the information? Keep in mind that there is usually a time lag before data will be published. The most current information available may be a couple years old. |
| Type |
Are you interested in statistics? Aggregated or microdata? Aggregate data are higher-level data that have been compiled from smaller units of data. For example, the Census data that you find on the Statistics Canada website have been aggregated to preserve the confidentiality of individual respondents. Or you may be interested in the climate daily times series from Environment and Climate Change Canada instead of their aggregated climate normals spanning 3 decades. Microdata consists of the data directly observed or collected from a specific unit of observation. A good example is the Public Use Microdata File (PUMF) for the Census, it provides access to the actual survey data from the Census, but eliminates information that would identify individuals. |