Twitch Leak on October 6, 2021

Data - Pareto

Author

Sans Regression

Code

twitch_leak %>%
  filter(Rank <= 200) %>%
  ggplot(.) + theme_minimal() + xlab("Gross Earning") + ylab("Rank") + 
  geom_point(aes(x = GrossEarning / 1000000, y = Rank)) +
  scale_x_log10(breaks = 0.001*c(250, 800, 1000, 1500, 2000, 3000, 4000, 6000, 8000),
                labels = dollar_format(accuracy = .1, suffix = "M")) + 
  scale_y_log10(breaks = c(1, 2, 4, 8, 16, 32, 64, 100, 200))

Fit

Regression

Code

fit1 <- twitch_leak %>%
  filter(Rank <= 200) %>%
  lm(log(Rank) ~ log(GrossEarning / 1000000), data = .)

summ(fit1)

Observations	200
Dependent variable	log(Rank)
Type	OLS linear regression

F(1,198)	29214.72
R²	0.99
Adj. R²	0.99

	Est.	S.E.	t val.	p
(Intercept)	4.39	0.01	788.91	0.00
log(GrossEarning/1e+06)	-1.79	0.01	-170.92	0.00
Standard errors: OLS

With fit

Code

twitch_leak %>%
  filter(Rank <= 200) %>%
  ggplot(.) + theme_minimal() + xlab("Gross Earning") + ylab("Rank") + 
  geom_point(aes(x = GrossEarning / 1000000, y = Rank)) +
  scale_x_log10(breaks = 0.001*c(250, 800, 1000, 1500, 2000, 3000, 4000, 6000, 8000),
                labels = dollar_format(accuracy = .1, suffix = "M")) + 
  scale_y_log10(breaks = c(1, 2, 4, 8, 16, 32, 64, 100, 200)) +
  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())