Datasets
I wanted to have a palce to which you can refer to see some details about the datasets that we’re using here.
colo
This data comes from a few different sources.
hospitals
andicu_beds
are from KHN.tpop
-urban_rural
come from the US Census.phys_health
-inactivity
come from County Health Rankings and Roadmaps.wkly_wage
comes from the BLS.
Here is a brief description of the variables.
colo_covid
The colo_covid
dataset comes from the NY Times running total of Covid-19 cases and deaths. You can obtain it here. The case and death counts are the current values, not the daily values. The variables are:
gss
(Canada)
The gss
dataset (which is in the file data/gss2016.rda
) is the 2016 Canadian General Social Survey. The data that you load will have all of the variables. The output below shows the ones we’re using.
The table for the full dataset is below
gsss16
(USA)
The gss16
data frame (which is in the data/gss16.rda
file) comes from the 2016 US General Social Survey.
The table for the entire dataset is below.
Davenport-Soule-Armstrong Data
These data are replication data from an article I wrote with Christian Davenport and Sarah Soule. There are lots of variables in the dataset, but these are the ones we will use. For more information on the data collection project, see here.
France 2004
These data are from a survey concerning peoples’ vote choices in the 2004 French election. The variables in the dataset are as follows:
ces19
These data come from the Canadian Election Study’s 2019 survey.
Snijders and Bosker Multileve School Data
These are data used by Snijders and Bosker for most of the examples in their book - Multilevel Analysis. You can find more about the data here. Here are the variables in the dataset.
World Values Survey (multilevel)
These data are used in the multilevel models chapter. They come from the World Values Survey, wave 6 (2010-2014). I randomly sampled 50 observations from each country for computational efficiency. The variables are as follows:
Repression Data
These are data that I used in the article “Measuring the Democracy Repression Nexus” in Electoral Studies in 2009. They come from various different sources. The descriptions of the variables are as follows:
Oil and Democracy Dataset
These are data that we use in the TSCS/Panel chapte. They come from:
Ross, Michel (2001) “Does Oil Hinder Democracy?” World Politics 53(3): 325-361.
There are lots of variables in the dataset, but here are the ones we’re primarily using.
PoliticalDemocracy
These are data that we use in the measurement chapter. They come from
Bollen, K. A. (1979). “Political democracy and the timing of development.” American Sociological Review, 44, 572-587.
We are getting this particular data frame from the lavaan
package. The variables in the dataset are.