adambear91

library(tidyverse) 

#### FUNCTIONS ####
# Recalculate my expectation for a given recursive step
recalculate_expectation <- function(x0, tau) {
  # possible dollar values of your card
  # (Note: I use a finer grain than 1-cent increments for more precision)
  x <- seq(.0001, .9999, .0001) 
  
  # probability you don't reveal your card based on its value

adambear91

adambear91

require(ggplot2)
require(GGally)
require(VGAM)

# Function to create a simulated data set and run models on it
oneRun <- function(number_of_obs,eff_IV1,eff_IV2,baseline,sd,lowerCutoff,upperCutoff,roundOn){
  # partition data into 4 conditions, specified by IV1 and IV2
  partition <- number_of_obs /4
  df <- expand.grid(IV1 = c(T,F), IV2 = c(T,F))
  df <- df[rep(row.names(df), partition), 1:2]

adambear91

%   %   %   %   %   %   %   %   %   %   %   %   %   %   %   %   %   %   %
%                 CODE FOR BEAR, KAGAN & RAND (2017) PROCB
%                                                                       
% This MATLAB script runs the low mutation limit (steady state) calculations     
% shown in Figures S1-S12
%                                                                       
% This script calls the following functions:  
%
% calculate_payoff_YDYI(strategy1,strategy2,b,c,d,p,YD,YI)
%       - returns the payoff of strategy1 against strategy2 given   

adambear91

%   %   %   %   %   %   %   %   %   %   %   %   %   %   %   %   %   %   %
%                 CODE FOR BEAR RAND (2016) PNAS                        
%                                                                       
% This MATLAB script runs the low mutation limit (steady state) calculations     
% shown in Figures 2a and S1-S3, as well as the agent-based simulations 
% for higher mutation rates shown in Figure S3, and plots the results.  
%                                                                       
% This script calls the following functions:  
%
% calculate_payoff(strategy1,strategy2,b,c,d,p)