Check coverage
The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.
This walks through a complete workflow with
contentiousR: construct a country-year panel from several
sources, check its coverage, and estimate a rare-events logit of
revolutionary onset. It is rather a demonstration of package mechanics
than a substantive research claim — the model below is illustrative and
has not been vetted as a serious specification.
library(contentiousR)
library(dplyr)
#> Warning: package 'dplyr' was built under R version 4.5.2
#>
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#>
#> filter, lag
#> The following objects are masked from 'package:base':
#>
#> intersect, setdiff, setequal, union
panel <- build_states_panel(1900, 2010, coding_system = "cow") |>
add_gdp(dataset = "fariss") |>
add_population(dataset = "wpp") |>
add_vdem(vars = c("v2x_polyarchy", "v2x_libdem", "v2x_execorr")) |>
add_leader_data(dataset = "archigos") |>
add_military_expenditure(dataset = "nmc") |>
add_conflict(dataset = "beissinger", aggregate = TRUE) |>
select(
cow, year, country, fariss_gdppc, wpp_pop, nmc_milex,
v2x_polyarchy, v2x_execorr, leader_tenure, beissinger_onset
) |>
mutate(across(starts_with("beissinger_"), ~ tidyr::replace_na(.x, 0))) |> # fill non-onsets with zeros
add_spell_duration() |>
add_lag(
vars = c(
"fariss_gdppc", "wpp_pop", "v2x_polyarchy",
"v2x_execorr", "leader_tenure", "nmc_milex"
),
n = 1
)
#> Multiple campaigns or episodes per country-year detected in 'beissinger'. Aggregating to country-year using max() for numeric columns. Use `aggregate = FALSE` or `conflict_data()` for record-level data.
dim(panel)
#> [1] 11257 17| cow | year | country | fariss_gdppc | wpp_pop | nmc_milex | v2x_polyarchy | v2x_execorr | leader_tenure | beissinger_onset | beissinger_spell | fariss_gdppc_l | wpp_pop_l | v2x_polyarchy_l | v2x_execorr_l | leader_tenure_l | nmc_milex_l |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | 1900 | United States | 17.37 | NA | 41481 | 0.42 | 0.06 | 4 | 0 | 0 | NA | NA | NA | NA | NA | NA |
| 2 | 1901 | United States | 18.07 | NA | 36087 | 0.42 | 0.06 | 1 | 0 | 1 | 17.37 | NA | 0.42 | 0.06 | 4 | 41481 |
| 2 | 1902 | United States | 18.44 | NA | 39722 | 0.42 | 0.06 | 2 | 0 | 2 | 18.07 | NA | 0.42 | 0.06 | 1 | 36087 |
| 2 | 1903 | United States | 18.69 | NA | 43814 | 0.42 | 0.06 | 3 | 0 | 3 | 18.44 | NA | 0.42 | 0.06 | 2 | 39722 |
| 2 | 1904 | United States | 18.74 | NA | 47918 | 0.42 | 0.06 | 4 | 0 | 4 | 18.69 | NA | 0.42 | 0.06 | 3 | 43814 |
| 2 | 1905 | United States | 19.34 | NA | 45098 | 0.42 | 0.06 | 5 | 0 | 5 | 18.74 | NA | 0.42 | 0.06 | 4 | 47918 |
add_conflict(dataset = "beissinger", aggregate = TRUE)
is used rather than aggregate = FALSE: Revolutionary
Episodes Dataset is an episode dataset, and a handful of country-years
have more than one recorded episode (e.g. Germany in 1918). Left
unaggregated, those country-years would produce duplicate
cow-year rows. replace_na(0)
treats “not covered” as “no onset” so that
add_spell_duration() (which cannot span NA)
can compute a peace-years counter (beissinger_spell) across
the whole panel. This is a modeling choice, not a neutral default.
Onsets are rare, which biases a regular logit model. The model below
uses brglm2’s Jeffreys-prior penalized likelihood
(method = "brglmFit", type = "MPL_Jeffreys")
instead (see Kosmidis and Firth 2009), with a natural spline on
beissinger_spell to flexibly control for time since the
last episode and year fixed effects. One-year lagged controls are
included in the estimation.
library(brglm2)
#> Warning: package 'brglm2' was built under R version 4.5.2
model <- glm(
beissinger_onset ~ log(fariss_gdppc_l + 0.1) + wpp_pop_l +
v2x_polyarchy_l + I(v2x_polyarchy_l^2) + v2x_execorr_l +
leader_tenure_l + I(leader_tenure_l^2) + nmc_milex_l +
splines::bs(beissinger_spell, 3) + as.factor(year),
family = binomial("logit"),
method = "brglmFit", type = "MPL_Jeffreys",
data = panel
)
co <- summary(model)$coefficients
co[!grepl("factor\\(year\\)", rownames(co)), ]
#> Estimate Std. Error z value
#> (Intercept) -5.541799e+00 1.498218e+00 -3.69892691
#> log(fariss_gdppc_l + 0.1) -4.060932e-03 1.003844e-01 -0.04045379
#> wpp_pop_l 7.641351e-07 5.520638e-07 1.38414286
#> v2x_polyarchy_l 4.426545e+00 1.712848e+00 2.58431858
#> I(v2x_polyarchy_l^2) -7.618338e+00 2.127482e+00 -3.58091810
#> v2x_execorr_l 9.530371e-01 3.739849e-01 2.54833000
#> leader_tenure_l 4.071753e-02 3.080048e-02 1.32197699
#> I(leader_tenure_l^2) -1.284174e-03 9.780690e-04 -1.31296835
#> nmc_milex_l 1.222355e-09 4.452181e-09 0.27455192
#> splines::bs(beissinger_spell, 3)1 -1.056449e+00 9.026917e-01 -1.17033190
#> splines::bs(beissinger_spell, 3)2 2.167424e+00 1.148905e+00 1.88651350
#> splines::bs(beissinger_spell, 3)3 -9.242953e-01 1.363052e+00 -0.67810722
#> Pr(>|z|)
#> (Intercept) 0.0002165129
#> log(fariss_gdppc_l + 0.1) 0.9677313433
#> wpp_pop_l 0.1663147150
#> v2x_polyarchy_l 0.0097571622
#> I(v2x_polyarchy_l^2) 0.0003423890
#> v2x_execorr_l 0.0108240028
#> leader_tenure_l 0.1861758143
#> I(leader_tenure_l^2) 0.1891936135
#> nmc_milex_l 0.7836605077
#> splines::bs(beissinger_spell, 3)1 0.2418674308
#> splines::bs(beissinger_spell, 3)2 0.0592257915
#> splines::bs(beissinger_spell, 3)3 0.4977037154Year fixed effects are omitted from the printed table above for readability.
Kosmidis, I., and D. Firth. 2009. “Bias Reduction in Exponential Family Nonlinear Models.” Biometrika 96 (4): 793–804. https://doi.org/10.1093/biomet/asp055.
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.