Thanks for listening to our inaugural podcast! If you haven’t listened yet, you can do so using the player above or by searching for Mean, Median, and Moose in your favourite podcast app. We’ll be using these blog posts to provide images and links to some of the items we discuss during the podcast, and also to cover what we may have missed in our discussions.
We covered a lot of ground talking about income statistics in Canada. We chose this topic because of Katie’s work examining the participation rate in Windsor. In it was this interesting graph for our neck of the woods:
Coincidentally Frazier had a similar graph in one of his recent blog posts:
Funnily enough we didn’t talk much about male/female income trends in Windsor, Ontario or Canada during the podcast (we’ll have to save that for later), but this was our jumping off point.
We talked mainly about the T1 Family File statistics during the podcast. You can find all of Stats Canada’s data sets for that survey here. We also talked about income and the census. You can find the income related census data here. We also talked briefly about vendor provided data sets like Environics’ Prizm data set.
We spent some time on the GINI coefficient. The OECD has some good tools to compare countries to each other. Here is some information on the Palma Index. We also talked about inequality between Canadian regions.
While researching this we developed this heatmap to show the income growth trends over the last twenty years:
Here’s the heatmap for raw incomes instead of income growth. This is heavily distorted by cost of living in the various regions which we talked a little about in the podcast as well (when incomes do and don’t reflect living expenses).
Data and code for those heatmaps is here if you want to see how to build them. The discussion was wide ranging. We even touched on the constitution and equalization, so be sure to have a listen if you haven’t already.
We all talked about how, no matter how many tools you learn to use, Excel is still powerful and useful. In the spirit of that and the fact that there is always something new to learn about Excel, here’s a video on 25 tips for how to use it better. Did you know you can now build choropleth maps in Excel? Go figure. Also, here’s a great resource from Microsoft on using Excel for data cleansing.
Frazier talked about Beyond 20/20, Statistics Canada’s browser for detailed census data located in IVT files. You can download it here.
Finally, Doug talked about how much he loves MS SQL Server. Did you know that there’s a version that’s free now? Also, there’s even a linux version? Even if you’re a database snob, you’re running out of excuses to not at least try it out. And the tooling for the database server is second to none. Doug mentioned the tool SSIS. A few years back he did a tutorial on using SSIS to access public API data, using Bank of Canada interest rates as the sample data source.
That’s it for this month! Be sure to rate and comment on the podcast so that more people can learn about us and open data in Canada!