Who are against immigration?

Canada has built a reputation over the last decades as one of the most welcoming countries for immigrants. In a recent plan announced by the government, Canada is going to accept more than one and a half million immigrants in the next three years. This inflow of immigrants has the potential to reshape the political arena of Canada. The recent evidence is the emergence of the People Party in the 2019 election of Canada (Canada.ca). The party sees immigration as an issue because it changes “the cultural character and social fabric of our [Canada] country” (People Party’s official website). Although the People Party only gained around 300,000 votes in the recent election, it alarms the transformation of public discourse over immigration. Therefore, there should be a closer look at the attitude of Canadians toward immigration, the topic of this study.

The goal of this study is to explore the importance of socio-demographic factors in shaping attitudes toward immigration in Canada.

This project uses Canadian Election Studies’ (CES) data in 2019 to explore public opinion toward immigration in Canada.  CES is a public institution whose goal is to collect a rich source of data on the political behaviors of Canadians and their opinion toward different issues. The 2019 survey was conducted in all provinces of Canada in two waves of before and after the election. Overall, 37,822 people living in Canada participated in the campaign period survey in which 10340 of them are contacted for the post-election survey. In this analysis, I use both post-election and pre-election surveys. After coding and removing the missing values, 3574 observations remained.

The independent variable measuring the opinion of Canadians toward immigration is extracted from the following question: Do you this Canada should admit more, about the same or fewer immigrants. Fewer immigrants are coded as 1, About the same as 2 and More immigrants as 3.

Figure 1 shows the percentage and number of respondents in our data that asked for different levels of immigration. The figure suggests that 45.5 percent of Canadians supported the status quo and asked for about the same number of immigrants. 37.1 percent of respondents in our sample also mentioned that Canada should decrease the number of immigration and only 17.4 percent of Canadians support an increase in immigration intake.

Analysis

Question:
What are the attitudes of different socio-demographic groups toward immigration?

Sample codes that Generated above graphs

x,y = 'cps19_employment', 'cps19_imm'
df1 = df.groupby(x)[y].value_counts(normalize=True)
df1 = df1.mul(100)
df1 = df1.rename('Percent').reset_index()
g = sns.catplot(x=x,y='Percent',hue=y,kind='bar',data=df1,height=7,aspect=3,palette="Set3",legend=False)
plt.legend(fontsize=20)
g.ax.set_ylim(0,100)
plt.xlabel("Employment status")
plt.ylabel("Percentage")
plt.xticks(rotation=45)
for p in g.ax.patches:
    txt = str(p.get_height().round(2)) + '%'
    txt_x = p.get_x() 
    txt_y = p.get_height()
    g.ax.text(txt_x,txt_y,txt,fontsize=15,rotation=90)
plt.xlabel('Employment status',fontsize=30)
plt.ylabel('Percent',fontsize=30)

plt.xticks(fontsize=25)
plt.yticks(fontsize=25)
plt.xticks(rotation=90)

g.savefig('Employment status.png')

Regression Analysis

I use linear regression to understand the impact of different socio-demographic variables

model2 = ols('attitude ~C(cps19_religion	) + C(cps19_employment)+ C(cps19_province)+C(cps19_employment)+C(cps19_gender)+C(cps19_education)+C(cps19_bornin_canada)+age+cpes19_nativism5+cpes19_nativism1+cpes19_immigjobs+ccps19_own_fin_retro', data=df)
fitted_model2 = model2.fit()
fitted_model2.summary()

Warnings:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 1.14e+04. This might indicate that there are
strong multicollinearity or other numerical problems.In [19]:

1. Regarding the education variable, the omitted category is Atheist. The categories of Hindu, Anglican, Baptist, Catholics, Orthodox, United church of Canada, and Salvation Army are significant. Interestingly, for all the categories the coefficients are negative meaning that they are more against immigration than Atheists. Therefore, the table suggests that among all the religions Atheists are more welcome toward immigration than any other groups.
2. For the employment status variable, the reference category is people working full time. The coefficient for the Retired category is significant but positive. it means that retired people are more welcome than people working full-time. This finding is surprising because it is against the welfare economic model of attitude toward immigration. Based on the Welfare Theory, people are against immigration because they think immigrants’ payments on taxes are lower than services received from the government.
3. The omitted category for the province is Alberta. The coefficient for Saskatchewan is negative showing that even after controlling for all salience socio-demographic variables people living in Saskatchewan are more against any other provinces in Canada. . Regarding Gender, there is no difference between females and males’ attitudes toward immigration.

I add voting behavior variable to model 1 to analyze the importance of political affiliation on attitudes towards immigration

The above graph can well explain the importance of party support on attitude toward immigration. The figure suggests that there is no difference between supporters of NDP, the Green party and the Liberal party. However, supporters of Conservatives, Bloc, people and those who did not cast their vote in the 2019 election are more against immigration than the Liberal party.

Tableau

Presentation

Links to Project

See the project on Tableau online
See the project on Github