Created
September 7, 2019 17:26
-
-
Save statwonk/beab6f60e70369bf1f9f379dd3033f6e to your computer and use it in GitHub Desktop.
The relationship between intra-arrival times and count models.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(tidyverse) | |
# https://www.kellogg.northwestern.edu/faculty/weber/decs-430/Notes%20on%20the%20Poisson%20and%20exponential%20distributions.pdf | |
# http://www.mscs.mu.edu/~jsta/issues/11(3)/JSTA11(3)p2.pdf | |
# Case 1: memoryless intra-arrival times. They're not correlated. | |
tibble::tibble( | |
durations_between = rexp(3e4, rate = 20) | |
) %>% | |
mutate(time = cumsum(durations_between)) %>% | |
mutate(time_interval = cut(time, breaks = seq(0, 1e4, 1), labels = FALSE)) %>% | |
count(time_interval) %>% | |
pull(n) %>% | |
head(-1) %>% | |
fitdistrplus::fitdist("pois") %>% | |
plot() | |
# Case 2: same, Gamma(shape = 1, rate) ~ Exp(rate) | |
tibble::tibble( | |
durations_between = rgamma(3e4, shape = 1, rate = 20) # equivalent | |
) %>% | |
mutate(time = cumsum(durations_between)) %>% | |
mutate(time_interval = cut(time, breaks = seq(0, 1e4, 1), labels = FALSE)) %>% | |
count(time_interval) %>% | |
pull(n) %>% | |
head(-1) %>% | |
fitdistrplus::fitdist("pois") %>% | |
plot() | |
# Case 3: clustered intra-arrival times. | |
tibble::tibble( | |
durations_between = rgamma(3e4, shape = 0.5, rate = 20) # now with clustered times | |
) %>% | |
mutate(time = cumsum(durations_between)) %>% | |
mutate(time_interval = cut(time, breaks = seq(0, 1e4, 1), labels = FALSE)) %>% | |
count(time_interval) %>% | |
pull(n) %>% | |
head(-1) %>% | |
fitdistrplus::fitdist("nbinom") %>% # notice negative binomial | |
plot() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment