statwonk

library(tidyverse)

# CPI
# https://data.bls.gov/timeseries/CUSR0000SA0&output_view=pct_1mth
readxl::read_xlsx("~/Downloads/SeriesReport-20220817182003_bb0f80.xlsx", skip = 10) %>%
  mutate(date = seq.POSIXt(as.POSIXct("1957-02-01"), by = "month", length.out = n())) %>%
  select(date, cpi = Value) %>%
  inner_join(
    # Short-term Interest Rates - https://fred.stlouisfed.org/series/DGS1MO
    read_csv("~/Downloads/DGS1MO (1).csv", col_types = cols(

statwonk

library(tidyverse)

# CPI
# https://data.bls.gov/timeseries/CUSR0000SA0&output_view=pct_1mth
readxl::read_xlsx("~/Downloads/SeriesReport-20220807120638_733b06.xlsx", skip = 10) %>%
  mutate(date = seq.POSIXt(as.POSIXct("1947-02-01"), by = "month", length.out = n())) %>%
  select(date, cpi = Value) -> cpi

cpi %>%
  filter(date >= as.POSIXct("1949-01-01")) %>%

statwonk

library(tidyverse)
library(forecast)
library(urca)
library(dynlm)
library(lmtest)
library(sandwich)

# https://data.bls.gov/timeseries/CUSR0000SA0&output_view=pct_1mth
read_csv("~/Downloads/inflation.csv", skip = 11) %>%
  janitor::clean_names() %>%

statwonk

library(tidyverse)
library(gamlss); select <- dplyr::select
library(fmpapi)
library(Quandl)

fmp_daily_prices("ASAN") -> d
fmp_daily_prices("TEAM") -> team
Quandl("USTREASURY/YIELD") -> yc

yc %>%

statwonk

library(tidyverse)
library(lmtest)
library(sandwich)

5e2 -> students
20 -> schools

tibble(student_id = 1:students) %>%
  mutate(school_id = rep(1:schools, max(student_id) / schools)) %>%
  left_join(tibble(school_id = 1:schools, school_effect = rnorm(schools)),

statwonk

library(tidyverse)
library(fitdistrplus)
dplyr::select -> select
.Machine$double.eps -> eps
1975 -> N # number of responses

tibble(lower = c(0, 0.25, 0.5, 0.75), # lower bins
       upper = c(0.25 + eps, 0.5 + eps, 0.75 + eps, 1), # upper bins
       pct = c(0.32, 0.51, 0.15, 1 - sum(0.32, 0.51, 0.15)), # response shares
       n = floor(pct * N)) %>% # implied responses + eps

statwonk

library(tidyverse)
library(rvest)
library(gamlss)
library(brms)
library(tidybayes)
select <- dplyr::select

####################################################################################
# Model the market capitalizations of members of the S&P 500.
####################################################################################

statwonk

library(tidyverse)
library(rvest)
library(gamlss)
library(brms)
library(tidybayes)
select <- dplyr::select

####################################################################################
# Model the market capitalizations of members of the S&P 500.
####################################################################################

statwonk

library(tidyverse)
library(quantmod)
library(gamlss)
select <- dplyr::select
posix <- function(x) { as.POSIXct(x, origin = "1970-01-01") }

## "Fat tails"
## Here we compare the residuals from the normal and t distributional models.
## Notice standardized error is worse in the normal model. This happens
## because returns are leptokurtic (large surprises should be expected, there's risk in stock returns),

statwonk

library(tidyverse)
library(ggthemes)
expand.grid(
  risk = seq(0.1/5e3, 1/5e3, 1e-05), # average daily risk e.g. - 1,000 infected per day in Alabama / 5,000,000 AL population
  units_of_exposure = seq_len(31) # days of exposure (up to 31 days)
) %>% as_tibble() %>%
  mutate(total_risk = map2_dbl(risk, units_of_exposure, ~ 1 - (1 - .x)^(.y)),
         total_odds = 1/total_risk,
         risk_threshold = case_when(total_odds <= 5e2 ~ "Worse than 1 in 500",
                                    total_odds <= 1e3 ~ "Worse than 1 in 1k chance",