Shreyes2010

## Reading the relevent files

install.packages("zoo")
library(zoo)

ife <- read.csv("CPI_Data.csv")
ife_wpi <- read.csv("WPI_Data_1.csv")

# Function to compute Y-o-Y inflation rate

Shreyes2010

	Augmented Dickey-Fuller Test

data:  Full sample
Dickey-Fuller = -2.4901, Lag order = 4, p-value = 0.3734
alternative hypothesis: stationary 

	Augmented Dickey-Fuller Test

data:  First 80 obs
Dickey-Fuller = -2.9479, Lag order = 4, p-value = 0.1882

Shreyes2010

a <- read.csv("Data.csv")

# Pretty functions to compute the MOM and YOY inflation rates

mom.inf <- function(series){
  x <- rep(NA,length(series))
  for(i in 2:length(series))x[i] <- ((series[i] - series[i-1])/series[i-1])*100
  return(x)
}

Shreyes2010

data <- read.csv("IFE_Update.csv")

# Plotting the foreign reserves of all the countries

png("IR_Relative.png", height = 800, width = 1000)
par(mfrow = c(3, 2)) ## This is to specify the number of rows and columns you want for the plots
# India
plot(data$Index, (data$India.Millions/max(data$India.Millions[!is.na(data$India.Millions)])), 
     type="l", xlab= "Months", ylab= "Foreign reserves (in $ millions)", col="green", lwd = 2, 
     main ="India's foreign reserves since 2002")

Shreyes2010

# Specifying functions:

CalcResiduals <- function(th, data) {
   # Calculates the e_t and h_t for the GARCH(1, 1) model with given parameters.
   #
   # Argumentss:
   #   th: Parameters
   #          th[1] -> mean
   #          th[2] -> alpha.0
   #          th[3] -> alpha.1

Shreyes2010

############################################################################################
####################### READING THE RELEVANT FILES #########################################

train.data <- read.csv("train_sample.csv")

## Set seed for reproducing the random numbers
set.seed(10001)

## This is to confirm the selection of trade_price_last{1-10}

Shreyes2010

# Aggregate demand curve 

ad.curve <- function(c, A, b, ms, h, k ,y) # We are trying to arrive at a relation between 
# Prices and output.
{
  alpha <- 1/(1-c)
  omega <- (k/h) - (1/alpha*b)
  P <- (ms/h)/(y*omega + (A/b)) # This is just basic algebra, you substitute "i" in terms of 
# "P" and "Y" from the IS and LM equations and find a relation between prices and output.
  return(P)

Shreyes2010

# IS curve equation
# y = output; c = marginal propensity to consume; alpha = 1/(1-c) A = autonomous component;
# b = Senstivity to interest rates; i = interest rates
# I = I.0 - b*i (investment equation)
# y = alpha*A - alpha*b*i

IS.curve <- function(c, A, b, i)
{ 
  y = (1/(1-c))*A - (1/(1-c))*b*i
  return(y)

Shreyes2010

Y = C + I + G + (X - M)

Y: Output produced in the economy
C: Total consumption demand
I: Total investment
G: Total govt. spending
X: Total value of exports
M: Total value of imports

We assume a closed economy so the identity boils down to 

Shreyes2010

single.call <- function(limit) { # Another cute function that returns the vector that contains the number of iterations for each number.

        memo <- rep(-1, limit)   
        memo[1] <- 0

        for(i in c(2:limit)) {  
                l <- 0
                n <- i
                while(n >= i) {  # Check only so long as "n > i" and not "1" this is basically the optimization we wanted. 
                        l <- l + 1