dreidpath

################################################################################
# Using the US CDC life tables for White Males (2020), I wanted to estimate the 
# Probability that if Joe Biden or Donald Trump became the next US president
# They would die in office. The general approach could be used for any interval.
# The life tables can be found here: https://stacks.cdc.gov/view/cdc/118055
################################################################################

library(tidyverse)
library(lubridate)

dreidpath

In about:config set dfjs.disableFontFace to true

see https://bugzilla.mozilla.org/show_bug.cgi?id=1738609

dreidpath

version_new <- list.files('~/R/x86_64-pc-linux-gnu-library/4.2')
version_old <- list.files('~/R/x86_64-pc-linux-gnu-library/4.1')

target <- version_old[!(version_old %in% version_new)]
install.packages(target)

dreidpath

#' In a dataframe, find all variable names that match var_pattern
#'
#' @param var_pattern a character string ("pattern" to match)
#' @param dframe  a dataframe
#'
#' @return all variable names in the dataframe that match var_pattern
#' @export
#'
#' @examples
#' find_var(iris, "idth")

dreidpath

# A quick visual analysis of Donald Trump's BMI assuming that his reported weight
# in 2018 and 2019 are correct, and his real height lies between his claimed
# height of 6'3" (1.9m) and a more likely height of 6'1" (1.854m)
# https://www.theguardian.com/us-news/2018/jan/17/a-tall-tale-accuracy-of-trumps-medical-report-and-new-height-questioned

# Include the ggplot library
library(ggplot2)  

# Function to calculate BMI from height (m) and mass/weight (Kg)
bmicalc <- function(height, mass){

dreidpath

phred <- function(q){
  10^(-q/10)
}

inv_phred <- function(p){
  10 * log10(p)
}

dreidpath

# These data appeared in a graph on climate.gov: http://bit.ly/2AFNBJz. 
# Paraphrasing from the website:
# The data are for each November since 1979 to 2017.
# The variable 'area' represents the combined November sea ice 
# area for the Chukchi and Beaufort Seas, the two sub-basins of 
# the Arctic Ocean that touch Alaska’s Arctic (northern) coast. 
# Larger values means more sea ice in the combined basin in square kilometres.
# The variable 'temp' is the November temperature (Fahrenheit) at Utqiaġvik,
# also known as Barrow (71°17′26″N 156°47′19″W).
# The data were digitised using Plot Digitizer 

dreidpath

# This is a quick script to create two time series plots using World Bank data downloaded using the wbstats package
# and plotted using ggplot2.
# The first plot uses Malaysia data only, and is a time series plot showing Life Expectancy at Birth changes
# in the whole population and for males and females separately.
# The second plot uses data for a handful of Southeast Asian countries and Australia and shows changes in the 
# Infant Mortality Rate over time.


library(wbstats)
library(tidyverse)

dreidpath

######################################################################################################################################
# This is a small piece of R-Code to support a recent blog-post of mine on country-level inequalities in life expectancy.            #
# If you are so inclined, you can read the blog-post here: http://wp.me/p8fOE1-13                                                    #
#                                                                                                                                    #
# For the purposes of re-use, the code is released under an MIT License (https://choosealicense.com/licenses/mit/)                   #
# The code is provided "as is" and without warranties.                                                                               #
#                                                                                                                                    #
####### Notes                                                                  

dreidpath

# Imagine that the probability of dying over a whole year is 0.5.  Assuming risk is constant, 
# what is the probability of dying in any single month?  This trivial function (thank you Mark)
# ensures that the monthly-p results in an annual probability of 0.5.  I wanted somewhere to 
# remember it

p-Divide <- function(P, n){
  1-(1-P)^(1/n)
}