This project explores the historical population of horses in Canada between 1906 and 1972 for each province.
Horse population data were sourced from the Government of Canada’s Open Data website (Government of Canada 2017).
The Python programming language (Van Rossum and Drake 2009) and the following Python packages were used to perform the analysis: pandas (McKinney 2010), altair (VanderPlas 2018), click (Team 2020), as well as Quarto (Allaire et al. 2022). Note: this report is adapted from Timbers (2020).
We can see from Figure 1 that Ontario, Saskatchewan and Alberta have had the highest horse populations in Canada. All provinces have had a decline in horse populations since 1940. This is likely due to the rebound of the Canadian automotive industry after the Great Depression and the Second World War. An interesting follow-up visualisation would be car sales per year for each Province over the time period visualised above to further support this hypothesis.
Suppose we were interested in looking in more closely at the province with the highest spread (in terms of standard deviation) of horse populations. We present the standard deviations in Table 1.
| Province | Std |
|---|---|
| Saskatchewan | 377266 |
| Ontario | 266435 |
| Alberta | 266063 |
| Manitoba | 122404 |
| Quebec | 111411 |
| New Brunswick | 22019.5 |
| Nova Scotia | 19879.3 |
| British Columbia | 14945.7 |
| P.E.I. | 11355.7 |
Standard deviation of historical (1906-1972) horse populations for each Canadian province.
Note that we define standard deviation (of a sample) as
\[s = \sqrt{\frac{\sum_{i=1}^N (x_i - \overline{x})^2}{N-1} }\]
Additionally, note that in Table 1 we consider the sample standard deviation of the number of horses during the same time span as Figure 1.
In Figure 2 we zoom in and look at the province of Saskatchewan which had the largest spread of values in terms of standard deviation.