Data - INSEE
ip2020[[2]][[3]] %>%
mutate(effectifs_cum = 1 - cumsum(effectifs)/sum(effectifs)) %>%
ggplot(.) + theme_minimal() + xlab("Net monthly wage") + ylab("Countercumulative Distribution Function") +
geom_point(aes(x = salaires_max, y = effectifs_cum)) +
scale_x_log10(breaks = c(1000, 1500, 2000, 3000, 4000, 6000, 8000),
labels = dollar_format(prefix = "", accuracy = 1, suffix = " €")) +
scale_y_log10(breaks = c(seq(0.01, 0.05, 0.01), 0.1, 0.2, 0.4, 1))
fit1 <- ip2020[[2]][[3]] %>%
mutate(effectifs_cum = 1 - cumsum(effectifs)/sum(effectifs)) %>%
filter(effectifs_cum <= 0.2) %>%
filter(is.finite(salaires_max)) %>%
lm(log(effectifs_cum) ~ log(salaires_max), data = .)
summ(fit1)| Observations | 58 |
| Dependent variable | log(effectifs_cum) |
| Type | OLS linear regression |
| F(1,56) | 974123.23 |
| R² | 1.00 |
| Adj. R² | 1.00 |
| Est. | S.E. | t val. | p | |
|---|---|---|---|---|
| (Intercept) | 20.06 | 0.02 | 852.14 | 0.00 |
| log(salaires_max) | -2.67 | 0.00 | -986.98 | 0.00 |
| Standard errors: OLS |
ip2020[[2]][[3]] %>%
mutate(effectifs_cum = 1 - cumsum(effectifs)/sum(effectifs)) %>%
filter(effectifs_cum <= 0.2) %>%
ggplot(.) + theme_minimal() + xlab("Net monthly wage") + ylab("Countercumulative Distribution Function") +
geom_point(aes(x = salaires_max, y = effectifs_cum)) +
scale_x_log10(breaks = c(1000, 1500, 2000, 3000, 4000, 5000, 6000, 7000, 8000),
labels = dollar_format(prefix = "", accuracy = 1, suffix = " €")) +
scale_y_log10(breaks = c(seq(0.01, 0.05, 0.01), 0.1, 0.2, 0.4, 1)) +
geom_function(aes(colour = paste0("Slope (Coefficient of Pareto): ", round(fit1$coefficients[2],3))), fun = function(x) exp(fit1$coefficients[1] + fit1$coefficients[2]*log(x))) +
theme(legend.position = c(0.8, 0.9),
legend.title = element_blank())
fit1 <- ip2020[[2]][[3]] %>%
mutate(effectifs_cum = 1 - cumsum(effectifs)/sum(effectifs)) %>%
filter(effectifs_cum <= 0.1) %>%
filter(is.finite(salaires_max)) %>%
lm(log(effectifs_cum) ~ log(salaires_max), data = .)
summ(fit1)| Observations | 47 |
| Dependent variable | log(effectifs_cum) |
| Type | OLS linear regression |
| F(1,45) | 845874.36 |
| R² | 1.00 |
| Adj. R² | 1.00 |
| Est. | S.E. | t val. | p | |
|---|---|---|---|---|
| (Intercept) | 20.13 | 0.03 | 785.32 | 0.00 |
| log(salaires_max) | -2.68 | 0.00 | -919.71 | 0.00 |
| Standard errors: OLS |
ip2020[[2]][[3]] %>%
mutate(effectifs_cum = 1 - cumsum(effectifs)/sum(effectifs)) %>%
filter(effectifs_cum <= 0.1) %>%
ggplot(.) + theme_minimal() + xlab("Net monthly wage") + ylab("Countercumulative Distribution Function") +
geom_point(aes(x = salaires_max, y = effectifs_cum)) +
scale_x_log10(breaks = c(1000, 1500, 2000, 3000, 4000, 5000, 6000, 7000, 8000),
labels = dollar_format(prefix = "", accuracy = 1, suffix = " €")) +
scale_y_log10(breaks = seq(0.01, 0.1, 0.01)) +
geom_function(aes(colour = paste0("Pente (coeff Pareto): ", round(fit1$coefficients[2],3))), fun = function(x) exp(fit1$coefficients[1] + fit1$coefficients[2]*log(x))) +
theme(legend.position = c(0.8, 0.9),
legend.title = element_blank())
ip2020[[2]][[5]] %>%
rename(variable = 1) %>%
gather(year, value, -variable) %>%
year_to_date2() %>%
group_by(variable) %>%
mutate(value = 100*value/value[date == as.Date("1996-01-01")]) %>%
ggplot() + ylab("Salaire net en EQTP depuis 1996, en € constants") + xlab("") + theme_minimal() +
geom_line(aes(x = date, y = value, color = variable)) +
scale_x_date(breaks = seq(1920, 2025, 2) %>% paste0("-01-01") %>% as.Date,
labels = date_format("%Y")) +
theme(legend.position = c(0.15, 0.85),
legend.title = element_blank()) +
scale_y_log10(breaks = seq(10, 300, 2),
labels = dollar_format(accuracy = 1, prefix = ""))
ip2020[[2]][[5]] %>%
rename(variable = 1) %>%
gather(year, value, -variable) %>%
year_to_date2() %>%
filter(date >= as.Date("2008-01-01")) %>%
group_by(variable) %>%
mutate(value = 100*value/value[date == as.Date("2008-01-01")]) %>%
ggplot() + ylab("Salaire net en EQTP depuis 2008, en € constants") + xlab("") + theme_minimal() +
geom_line(aes(x = date, y = value, color = variable)) +
scale_x_date(breaks = seq(1920, 2025, 1) %>% paste0("-01-01") %>% as.Date,
labels = date_format("%Y")) +
theme(legend.position = c(0.15, 0.85),
legend.title = element_blank()) +
scale_y_log10(breaks = seq(10, 300, 1),
labels = dollar_format(accuracy = 1, prefix = ""))