#Install & update necessary packages and libraries install.packages("readxl") library("readxl") update.packages("readxl") #DESCRIPTIVE STATISTICS ##EPU_Index_Developed #Load the Excel data EPU_Index <- read_xlsx("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "EPU Index") #Select the subset of developed countries EPU_Index_Developed <- EPU_Index[341:672, 3:15] View(EPU_Index_Developed) #Convert list in vector data #as.numeric requires a vector of values Vector_data <- unlist(EPU_Index_Developed) #Numeric data conversion #to convert the vector in numeric data Numeric_data <- as.numeric(Vector_data) is.numeric(Numeric_data) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data, na.rm = TRUE) mean_value <- mean(Numeric_data, na.rm = TRUE) sd_value <- sd(Numeric_data, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##EPU_Index_Emerging #Select the subset of emerging countries EPU_Index_Emerging <- EPU_Index[679:1010, 3:10] View(EPU_Index_Emerging) #Convert list in vector data #as.numeric requires a vector of values Vector_data_2 <- unlist(EPU_Index_Emerging) #Numeric data conversion #to convert the vector in numeric data Numeric_data_2 <- as.numeric(Vector_data_2) is.numeric(Numeric_data_2) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_2, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_2, na.rm = TRUE) mean_value <- mean(Numeric_data_2, na.rm = TRUE) sd_value <- sd(Numeric_data_2, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##Share_Price_Index_Developed #Load the Excel data Stocks <- read_xlsx("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "Stocks") #Select the subset of developed countries Share_Price_Index_Developed <- Stocks[1355:1686, 3:15] View(Share_Price_Index_Developed) #Convert list in vector data #as.numeric requires a vector of values Vector_data_3 <- unlist(Share_Price_Index_Developed) #Numeric data conversion #to convert the vector in numeric data Numeric_data_3 <- as.numeric(Vector_data_3) is.numeric(Numeric_data_3) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_3, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_3, na.rm = TRUE) mean_value <- mean(Numeric_data_3, na.rm = TRUE) sd_value <- sd(Numeric_data_3, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##Share_Price_Index_Emerging #Select the subset of emerging countries Share_Price_Index_Emerging <- Stocks[1693:2024, 3:10] View(Share_Price_Index_Emerging) #Convert list in vector data #as.numeric requires a vector of values Vector_data_4 <- unlist(Share_Price_Index_Emerging) #Numeric data conversion #to convert the vector in numeric data Numeric_data_4 <- as.numeric(Vector_data_4) is.numeric(Numeric_data_4) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_4, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_4, na.rm = TRUE) mean_value <- mean(Numeric_data_4, na.rm = TRUE) sd_value <- sd(Numeric_data_4, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##Bond_Price_Index_Developed #Load the Excel data Bonds <- read_xlsx("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "Bonds") #Select the subset of developed countries Bond_Price_Index_Developed <- Bonds[491:606, 3:15] View(Bond_Price_Index_Developed) #Convert list in vector data #as.numeric requires a vector of values Vector_data_5 <- unlist(Bond_Price_Index_Developed) #Numeric data conversion #to convert the vector in numeric data Numeric_data_5 <- as.numeric(Vector_data_5) is.numeric(Numeric_data_5) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_5, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_5, na.rm = TRUE) mean_value <- mean(Numeric_data_5, na.rm = TRUE) sd_value <- sd(Numeric_data_5, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##Bond_Price_Index_Emerging #Select the subset of emerging countries Bond_Price_Index_Emerging <- Bonds[613:728, 3:10] View(Bond_Price_Index_Emerging) #Convert list in vector data #as.numeric requires a vector of values Vector_data_6 <- unlist(Bond_Price_Index_Emerging) #Numeric data conversion #to convert the vector in numeric data Numeric_data_6 <- as.numeric(Vector_data_6) is.numeric(Numeric_data_6) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_6, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_6, na.rm = TRUE) mean_value <- mean(Numeric_data_6, na.rm = TRUE) sd_value <- sd(Numeric_data_6, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##Share_Index_Excess_Returns_Developed #Select the subset of developed countries Share_Index_Excess_Returns_Developed <- Stocks[2708:3038, 3:15] View(Share_Index_Excess_Returns_Developed) #Convert list in vector data #as.numeric requires a vector of values Vector_data_7 <- unlist(Share_Index_Excess_Returns_Developed) #Numeric data conversion #to convert the vector in numeric data Numeric_data_7 <- as.numeric(Vector_data_7) is.numeric(Numeric_data_7) #check if Numeric_data is numeric : YES Numeric_data_7_clean <- na.omit(Numeric_data_7) #to omit NA values is.numeric(Numeric_data_7_clean) #Computation of key statistics min_value <- min(Numeric_data_7, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_7, na.rm = TRUE) mean_value <- mean(Numeric_data_7, na.rm = TRUE) sd_value <- sd(Numeric_data_7, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##Share_Index_Excess_Returns_Emerging #Select the subset of emerging countries Share_Index_Excess_Returns_Emerging <- Stocks[3046:3376, 3:10] View(Share_Index_Excess_Returns_Emerging) #Convert list in vector data #as.numeric requires a vector of values Vector_data_8 <- unlist(Share_Index_Excess_Returns_Emerging) #Numeric data conversion #to convert the vector in numeric data Numeric_data_8 <- as.numeric(Vector_data_8) is.numeric(Numeric_data_8) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_8, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_8, na.rm = TRUE) mean_value <- mean(Numeric_data_8, na.rm = TRUE) sd_value <- sd(Numeric_data_8, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##Bond_Index_Excess_Returns_Developed #Select the subset of developed countries Bond_Index_Excess_Returns_Developed <- Bonds[980:1094, 3:15] View(Bond_Index_Excess_Returns_Developed) #Convert list in vector data #as.numeric requires a vector of values Vector_data_9 <- unlist(Bond_Index_Excess_Returns_Developed) #Numeric data conversion #to convert the vector in numeric data Numeric_data_9 <- as.numeric(Vector_data_9) is.numeric(Numeric_data_9) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_9, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_9, na.rm = TRUE) mean_value <- mean(Numeric_data_9, na.rm = TRUE) sd_value <- sd(Numeric_data_9, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##Bond_Index_Excess_Returns_Emerging #Select the subset of emerging countries Bond_Index_Excess_Returns_Emerging <- Bonds[1102:1216, 3:10] View(Bond_Index_Excess_Returns_Emerging) #Convert list in vector data #as.numeric requires a vector of values Vector_data_10 <- unlist(Bond_Index_Excess_Returns_Emerging) #Numeric data conversion #to convert the vector in numeric data Numeric_data_10 <- as.numeric(Vector_data_10) is.numeric(Numeric_data_10) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_10, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_10, na.rm = TRUE) mean_value <- mean(Numeric_data_10, na.rm = TRUE) sd_value <- sd(Numeric_data_10, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##Fama_French_Factors_Developed ##SMB #Load the Excel data Fama_French_Factors <- read_xlsx("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "Fama-French Factors") #Select the SMB factor for the subset of developed countries Fama_French_factors_Developed_SMB <- Fama_French_Factors[342:673, 3:3] View(Fama_French_factors_Developed_SMB) #Convert list in vector data #as.numeric requires a vector of values Vector_data_11 <- unlist(Fama_French_factors_Developed_SMB) #Numeric data conversion #to convert the vector in numeric data Numeric_data_11 <- as.numeric(Vector_data_11) is.numeric(Numeric_data_11) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_11, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_11, na.rm = TRUE) mean_value <- mean(Numeric_data_11, na.rm = TRUE) sd_value <- sd(Numeric_data_11, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) #HML #Select the HML factor for the subset of developed countries Fama_French_factors_Developed_HML <- Fama_French_Factors[342:673, 4:4] View(Fama_French_factors_Developed_HML) #Convert list in vector data #as.numeric requires a vector of values Vector_data_12 <- unlist(Fama_French_factors_Developed_HML) #Numeric data conversion #to convert the vector in numeric data Numeric_data_12 <- as.numeric(Vector_data_12) is.numeric(Numeric_data_12) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_12, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_12, na.rm = TRUE) mean_value <- mean(Numeric_data_12, na.rm = TRUE) sd_value <- sd(Numeric_data_12, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##RMW #Select the RMW factor for the subset of developed countries Fama_French_factors_Developed_RMW <- Fama_French_Factors[342:673, 5:5] View(Fama_French_factors_Developed_RMW) #Convert list in vector data #as.numeric requires a vector of values Vector_data_13 <- unlist(Fama_French_factors_Developed_RMW) #Numeric data conversion #to convert the vector in numeric data Numeric_data_13 <- as.numeric(Vector_data_13) is.numeric(Numeric_data_13) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_13, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_13, na.rm = TRUE) mean_value <- mean(Numeric_data_13, na.rm = TRUE) sd_value <- sd(Numeric_data_13, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##CMA #Select the RMW factor for the subset of developed countries Fama_French_factors_Developed_CMA <- Fama_French_Factors[342:673, 6:6] View(Fama_French_factors_Developed_CMA) #Convert list in vector data #as.numeric requires a vector of values Vector_data_14 <- unlist(Fama_French_factors_Developed_CMA) #Numeric data conversion #to convert the vector in numeric data Numeric_data_14 <- as.numeric(Vector_data_14) is.numeric(Numeric_data_14) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_14, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_14, na.rm = TRUE) mean_value <- mean(Numeric_data_14, na.rm = TRUE) sd_value <- sd(Numeric_data_14, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##Emerging Countries ##SMB #Select the SMB factor for the subset of emerging countries Fama_French_factors_Emerging_SMB <- Fama_French_Factors[342:673, 12:12] View(Fama_French_factors_Emerging_SMB) #Convert list in vector data #as.numeric requires a vector of values Vector_data_15 <- unlist(Fama_French_factors_Emerging_SMB) #Numeric data conversion #to convert the vector in numeric data Numeric_data_15 <- as.numeric(Vector_data_15) is.numeric(Numeric_data_15) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_15, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_15, na.rm = TRUE) mean_value <- mean(Numeric_data_15, na.rm = TRUE) sd_value <- sd(Numeric_data_15, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##HML #Select the HML factor for the subset of emerging countries Fama_French_factors_Emerging_HML <- Fama_French_Factors[342:673, 13:13] View(Fama_French_factors_Emerging_HML) #Convert list in vector data #as.numeric requires a vector of values Vector_data_16 <- unlist(Fama_French_factors_Emerging_HML) #Numeric data conversion #to convert the vector in numeric data Numeric_data_16 <- as.numeric(Vector_data_16) is.numeric(Numeric_data_16) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_16, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_16, na.rm = TRUE) mean_value <- mean(Numeric_data_16, na.rm = TRUE) sd_value <- sd(Numeric_data_16, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##RMW #Select the RMW factor for the subset of emerging countries Fama_French_factors_Emerging_RMW <- Fama_French_Factors[342:673, 14:14] View(Fama_French_factors_Emerging_RMW) #Convert list in vector data #as.numeric requires a vector of values Vector_data_17 <- unlist(Fama_French_factors_Emerging_RMW) #Numeric data conversion #to convert the vector in numeric data Numeric_data_17 <- as.numeric(Vector_data_17) is.numeric(Numeric_data_17) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_17, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_17, na.rm = TRUE) mean_value <- mean(Numeric_data_17, na.rm = TRUE) sd_value <- sd(Numeric_data_17, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##CMA #Select the CMA factor for the subset of emerging countries Fama_French_factors_Emerging_CMA <- Fama_French_Factors[342:673, 15:15] View(Fama_French_factors_Emerging_CMA) #Convert list in vector data #as.numeric requires a vector of values Vector_data_18 <- unlist(Fama_French_factors_Emerging_CMA) #Numeric data conversion #to convert the vector in numeric data Numeric_data_18 <- as.numeric(Vector_data_18) is.numeric(Numeric_data_18) #check if Numeric_data is numeric : YES #Computation of key statistics min_value <- min(Numeric_data_18, na.rm = TRUE) #min function requires numeric data max_value <- max(Numeric_data_18, na.rm = TRUE) mean_value <- mean(Numeric_data_18, na.rm = TRUE) sd_value <- sd(Numeric_data_18, na.rm = TRUE) #Print key statistics print(min_value) print(max_value) print(mean_value) print(sd_value) ##VARIABLES TRANSFORMATIONS? #FREQUENCY HISTOGRAMS #Share_Index_Excess_Returns_Developed Numeric_data_7 #Numeric set of share_index_excess_returns_developed Share_Index_Excess_Returns_Developed_Histogram <- hist(Numeric_data_7) #Share_Index_Excess_Returns_Emerging Numeric_data_8 #Numeric set of share_index_excess_returns_emerging Share_Index_Excess_Returns_Emerging_Histogram <- hist(Numeric_data_8) #Bond_Index_Excess_Returns_Developed Numeric_data_9 #Numeric set of bond_index_excess_returns_developed Bond_Index_Excess_Returns_Developed_Histogram <- hist(Numeric_data_9) #BER_Emerging Numeric_data_10 #Numeric set of bond_index_excess_returns_emerging Bond_Index_Excess_Returns_Emerging_Histogram <- hist(Numeric_data_10) #EPU_Index_Developed Numeric_data EPU_Index_Developed_Histogram <- hist(Numeric_data) #EPU_Index_Emerging Numeric_data_2 EPU_Index_Emerging_Histogram <- hist(Numeric_data_2) #SMB_Developed Numeric_data_11 SMB_Developed_Histogram <- hist(Numeric_data_11) #HML_Developed Numeric_data_12 HML_Developed_Histogram <- hist(Numeric_data_12) #RMW_Developed Numeric_data_13 RMW_Developed_Histogram <- hist(Numeric_data_13) #CMA_Developed Numeric_data_14 CMA_Developed_Histogram <- hist(Numeric_data_14) #SMB_Emerging Numeric_data_15 SMB_Emerging_Histogram <- hist(Numeric_data_15) #HML_Emerging Numeric_data_16 HML_Emerging_Histogram <- hist(Numeric_data_16) #RMW_Emerging Numeric_data_17 RMW_Emerging_Histogram <- hist(Numeric_data_17) #CMA_Emerging Numeric_data_18 CMA_Emerging_Histogram <- hist(Numeric_data_18) #DATA STATIONARITY TESTS install.packages("tseries") #Install & update necessary package for ADF test library("tseries") update.packages("tseries") #EPU_Index_Developed adf.test(Numeric_data) #EPU_Index_Emerging adf.test(Numeric_data_2) #Share_Index_Excess_Returns_Developed adf.test(Numeric_data_7_clean) #Share_Index_Excess_Returns_Emerging adf.test(Numeric_data_8) #Bond_Index_Excess_Returns_Developed adf.test(Numeric_data_9) #Bond_Index_Excess_Returns_Emerging adf.test(Numeric_data_10) ##Developed countries #SMB adf.test(Numeric_data_11) #HML adf.test(Numeric_data_12) #RMW adf.test(Numeric_data_13) #CMA adf.test(Numeric_data_14) ##Emerging countries #SMB adf.test(Numeric_data_15) #HML adf.test(Numeric_data_16) #RMW adf.test(Numeric_data_17) #CMA adf.test(Numeric_data_18) ##MULTIVARIATE LINEAR REGRESSIONS #LOAD DATA FOR REGRESSION ANALYSIS (numeric) SER_Developed <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "Share_Excess_Returns_Developed") SER_Emerging <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "Share_Excess_Returns_Emerging") BER_Developed <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet ="Bond_Excess_Returns_Developed") BER_Emerging <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "Bond_Excess_Returns_Emerging") EPU_Developed <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "EPU_Index_Developed") EPU_Emerging <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "EPU_Index_Emerging") SMB_Developed <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "SMB_Developed") HML_Developed <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "HML_Developed") RMW_Developed <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "RMW_Developed") CMA_Developed <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "CMA_Developed") SMB_Emerging <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "SMB_Emerging") HML_Emerging <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "HML_Emerging") RMW_Emerging <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "RMW_Emerging") CMA_Emerging <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "CMA_Emerging") ##Share_Index_Excess_Returns_Developed Regression_SER_DEV_Data <- cbind(SER_Developed, EPU_Developed, SMB_Developed, HML_Developed, RMW_Developed, CMA_Developed) #create a single data frame for regression 1 Regression_1 <- lm(Australia_SER+Canada_SER+Germany_SER+Spain_SER+France_SER+UK_SER+Greece_SER+Ireland_SER+Italy_SER+Japan_SER+Sweden_SER+Singapore_SER+US_SER #Run regression 1 on SER of developed countries ~ log10(Australia_EPU+Canada_EPU+Germany_EPU+Spain_EPU+France_EPU+UK_EPU+Greece_EPU+Ireland_EPU+Italy_EPU+Japan_EPU+Sweden_EPU+Singapore_EPU+US_EPU) + SMB_Developed + HML_Developed + RMW_Developed + CMA_Developed, data = Regression_SER_DEV_Data, na.action = na.omit) summary(Regression_1) #to have the summary of Regression_1 #CORRELATION MATRIX (EXPLANATORY VARIABLES) - REGRESSION 1 Corr_Mat_Regression_1_Data <- cbind(Numeric_data, Numeric_data_11, Numeric_data_12, Numeric_data_13, Numeric_data_14) #1 single data frame of Regression_1_Explanatory variables Corr_Matrix_Regression_1 <- cor(Corr_Mat_Regression_1_Data) #compute the correlation matrix View(Corr_Matrix_Regression_1) View(EPU_Index_Developed) ##Share_Index_Excess_Returns_Emerging Regression_SER_EMR_Data <- cbind(SER_Emerging, EPU_Emerging, SMB_Emerging, HML_Emerging, RMW_Emerging, CMA_Emerging) #create a single data frame for regression 2 Regression_2 <- lm(Brazil_SER+Chile_SER+China_SER+India_SER+Mexico_SER+Pakistan_SER+Russia_SER+Korea_SER #Run regression 2 ~ log10(Brazil_EPU+Chile_EPU+China_EPU+India_EPU+Mexico_EPU+Pakistan_EPU+Russia_EPU+Korea_EPU) + SMB_Emerging + HML_Emerging + RMW_Emerging + CMA_Emerging, data = Regression_SER_EMR_Data, na.action = na.omit) summary(Regression_2) #to have the summary of Regression_2 #CORRELATION MATRIX (EXPLANATORY VARIABLES) - REGRESSION 2 Corr_Mat_Regression_2_Data <- cbind(Numeric_data_2, Numeric_data_15, Numeric_data_16, Numeric_data_17, Numeric_data_18) #1 single data frame of Regression_1_Explanatory variables Corr_Matrix_Regression_2 <- cor(Corr_Mat_Regression_2_Data) #compute the correlation matrix View(Corr_Matrix_Regression_2) #Load the date-adjusted data for bond_excess_returns regressions EPU_Developed_Bond_Reg <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "EPU_Index_Developed_Short") EPU_Emerging_Bond_Reg <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "EPU_Index_Emerging_Short") SMB_Developed_Bond_Reg <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "SMB_Developed_Short") SMB_Emerging_Bond_Reg <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "SMB_Emerging_Short") HML_Developed_Bond_Reg <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "HML_Developed_Short") HML_Emerging_Bond_Reg <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "HML_Emerging_Short") RMW_Developed_Bond_Reg <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "RMW_Developed_Short") RMW_Emerging_Bond_Reg <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "RMW_Emerging_Short") CMA_Developed_Bond_Reg <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "CMA_Developed_Short") CMA_Emerging_Bond_Reg <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "CMA_Emerging_Short") ##Numeric conversion of date-adjusted data for bond_excess_returns ##EPU_Developed_Bond_Reg #Exclude columns "Year" & "Month" EPU_Developed_Bond_Reg_Excluded <- EPU_Developed_Bond_Reg[,!names(EPU_Developed_Bond_Reg) %in% c("Year", "Month")] #Convert list in vector data #as.numeric requires a vector of values Vector_data_19 <- unlist(EPU_Developed_Bond_Reg_Excluded) #Numeric data conversion #to convert the vector in numeric data Numeric_data_19 <- as.numeric(Vector_data_19) is.numeric(Numeric_data_19) ##EPU_Emerging_Bond_Reg #Exclude columns "Year" & "Month" EPU_Emerging_Bond_Reg_Excluded <- EPU_Emerging_Bond_Reg[,!names(EPU_Emerging_Bond_Reg) %in% c("Year", "Month")] #Convert list in vector data #as.numeric requires a vector of values Vector_data_20 <- unlist(EPU_Emerging_Bond_Reg_Excluded) #Numeric data conversion #to convert the vector in numeric data Numeric_data_20 <- as.numeric(Vector_data_20) is.numeric(Numeric_data_20) ##SMB_Developed_Bond_Reg #Exclude columns "Year" & "Month" SMB_Developed_Bond_Reg_Excluded <- SMB_Developed_Bond_Reg[,!names(SMB_Developed_Bond_Reg) %in% c("Year", "Month")] is.numeric(SMB_Developed_Bond_Reg_Excluded) ##SMB_Emerging_Bond_Reg #Exclude columns "Year" and "Month" SMB_Emerging_Bond_Reg_Excluded <- SMB_Emerging_Bond_Reg[,!names(SMB_Emerging_Bond_Reg) %in% c("Year", "Month")] is.numeric(SMB_Emerging_Bond_Reg_Excluded) ##HML_Developed_Bond_Reg #Exclude columns "Year" and "Month" HML_Developed_Bond_Reg_Excluded <- HML_Developed_Bond_Reg[,!names(HML_Developed_Bond_Reg) %in% c("Year", "Month")] is.numeric(HML_Developed_Bond_Reg_Excluded) ##HML_Emerging_Bond_Reg #Exclude columns "Year" and "Month" HML_Emerging_Bond_Reg_Excluded <- HML_Emerging_Bond_Reg[,!names(HML_Emerging_Bond_Reg) %in% c("Year", "Month")] is.numeric(HML_Emerging_Bond_Reg_Excluded) ##RMW_Developed_Bond_Reg #Exclude columns "Year" & "Month" RMW_Developed_Bond_Reg_Excluded <- RMW_Developed_Bond_Reg[,!names(RMW_Developed_Bond_Reg) %in% c("Year", "Month")] is.numeric(RMW_Developed_Bond_Reg_Excluded) ##RMW_Emerging_Bond_Reg #Exclude columns "Year" & "Month" RMW_Emerging_Bond_Reg_Excluded <- RMW_Emerging_Bond_Reg[,!names(RMW_Emerging_Bond_Reg) %in% c("Year", "Month")] is.numeric(RMW_Emerging_Bond_Reg_Excluded) ##CMA_Developed_Bond_Reg #Exclude columns "Year" & "Month" CMA_Developed_Bond_Reg_Excluded <- CMA_Developed_Bond_Reg[,!names(CMA_Developed_Bond_Reg) %in% c("Year", "Month")] is.numeric(CMA_Developed_Bond_Reg_Excluded) ##CMA_Emerging_Bond_Reg #Exclude columns "Year" & "Month" CMA_Emerging_Bond_Reg_Excluded <- CMA_Emerging_Bond_Reg[,!names(CMA_Emerging_Bond_Reg) %in% c("Year", "Month")] is.numeric(CMA_Emerging_Bond_Reg_Excluded) ##DATA STATIONARITY TESTS install.packages("tseries") #Install & update necessary package for ADF test library("tseries") update.packages("tseries") #EPU_Developed_Bond_Reg adf.test(Numeric_data_19) #EPU_Emerging_Bond_Reg adf.test(Numeric_data_20) #SMB_Developed_Bond_Reg adf.test(SMB_Developed_Bond_Reg_Excluded) #SMB_Emerging_Bond_Reg adf.test(SMB_Emerging_Bond_Reg_Excluded) #HML_Developed_Bond_Reg adf.test(HML_Developed_Bond_Reg_Excluded) #HML_Emerging_Bond_Reg adf.test(HML_Emerging_Bond_Reg_Excluded) #RMW_Developed_Bond_Reg adf.test(RMW_Developed_Bond_Reg_Excluded) #RMW_Emerging_Bond_Reg adf.test(RMW_Emerging_Bond_Reg_Excluded) #CMA_Developed_Bond_Reg adf.test(CMA_Developed_Bond_Reg_Excluded) #CMA_Emerging_Bond_Reg adf.test(CMA_Emerging_Bond_Reg_Excluded) ##FREQUENCY HISTOGRAMMS #EPU_Developed_Bond_Reg hist(Numeric_data_19) #EPU_Emerging_Bond_Reg hist(Numeric_data_20) #SMB_Developed_Bond_Reg hist(SMB_Developed_Bond_Reg_Excluded) #HML_Developed_Bond_Reg hist(HML_Developed_Bond_Reg_Excluded) #RMW_Developed_Bond_Reg hist(RMW_Developed_Bond_Reg_Excluded) #CMA_Developed_Bond_Reg hist(log(CMA_Developed_Bond_Reg_Excluded)) #SMB_Emerging_Bond_Reg hist(SMB_Emerging_Bond_Reg_Excluded) #HML_Emerging_Bond_Reg hist(HML_Emerging_Bond_Reg_Excluded) #RMW_Emerging_Bond_Reg hist(RMW_Emerging_Bond_Reg_Excluded) #CMA_Emerging_Bond_Reg hist(CMA_Emerging_Bond_Reg_Excluded) ##Bond_Index_Excess_Returns_Developed Regression_BER_DVP_Data <- cbind(BER_Developed,EPU_Developed_Bond_Reg,SMB_Developed_Bond_Reg,HML_Developed_Bond_Reg,RMW_Developed_Bond_Reg,CMA_Developed_Bond_Reg) #create a single data frame for regression 3 Regression_3 <- lm(Australia_BER+Canada_BER+Germany_BER+Spain_BER+France_BER+UK_BER+Greece_BER+Ireland_BER+Italy_BER+Japan_BER+Sweden_BER+Singapore_BER+US_BER #run regression 3 ~ log10(Australia_EPU+Canada_EPU+Germany_EPU+Spain_EPU+France_EPU+UK_EPU+Greece_EPU+Ireland_EPU+Italy_EPU+Japan_EPU+Sweden_EPU+Singapore_EPU+US_EPU) + SMB_Developed + HML_Developed + RMW_Developed + CMA_Developed, data = Regression_BER_DVP_Data, na.action = na.omit) summary(Regression_3) #to have the summary of Regression_3 #CORRELATION MATRIX (EXPLANATORY VARIABLES) - REGRESSION 3 Corr_Mat_Regression_3_Data <- cbind(Numeric_data_19, SMB_Developed_Bond_Reg_Excluded, HML_Developed_Bond_Reg_Excluded, RMW_Developed_Bond_Reg_Excluded, CMA_Developed_Bond_Reg_Excluded) #1 single data frame of Regression_1_Explanatory variables Corr_Matrix_Regression_3 <- cor(Corr_Mat_Regression_3_Data) #compute the correlation matrix View(Corr_Matrix_Regression_3) ##Bond_Index_Excess_Returns_Emerging Regression_BER_EMR_Data <- cbind(BER_Emerging,EPU_Emerging_Bond_Reg,SMB_Emerging_Bond_Reg,HML_Emerging_Bond_Reg,RMW_Emerging_Bond_Reg,CMA_Emerging_Bond_Reg) #create a single data frame for regression 4 Regression_4 <- lm(Brazil_BER+Chile_BER+China_BER+India_BER+Mexico_BER+Pakistan_BER+Russia_BER+Korea_BER #run regression 4 ~ log10(Brazil_EPU+Chile_EPU+China_EPU+India_EPU+Mexico_EPU+Pakistan_EPU+Russia_EPU+Korea_EPU) + SMB_Emerging + HML_Emerging + RMW_Emerging + CMA_Emerging, data = Regression_BER_EMR_Data, na.action = na.omit) summary(Regression_4) #to have the summary of Regression_4 #CORRELATION MATRIX (EXPLANATORY VARIABLES) - REGRESSION 4 Corr_Mat_Regression_4_Data <- cbind(Numeric_data_20, SMB_Emerging_Bond_Reg_Excluded, HML_Emerging_Bond_Reg_Excluded, RMW_Emerging_Bond_Reg_Excluded, CMA_Emerging_Bond_Reg_Excluded) #1 single data frame of Regression_1_Explanatory variables Corr_Matrix_Regression_4 <- cor(Corr_Mat_Regression_4_Data) #compute the correlation matrix View(Corr_Matrix_Regression_4) ##CORRELATION REGRESSIONS #Load Share-Bond Excess Returns Correlations for developed & emerging countries + EPU_DEV_FREQ_ADJ_CORR + EPU_EME_FREQ_ADJ_CORR Correlations_DVP <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "Correlations_DEV_2") Correlations_EME <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "Correlations_EME_2") Correlations_EME_LN <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "Correlations_EME_2_LN") EPU_Developed_FREQ_CORR <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "EPU_Index_Dev_Short_CORR_2") EPU_Developed_FREQ_CORR_DIFF <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "EPU_Dev_Short_CORR_2_DIF") EPU_Emerging_FREQ_CORR <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "EPU_Index_Eme_Short_CORR_2") EPU_Emerging_FREQ_CORR_DIFF <- read_excel("C:\\Users\\Yann Hanse\\Documents\\Master's thesis\\Working Directory\\Master's thesis - Spreadsheet.xlsx", sheet = "EPU_Index_Eme_Short_CORR_2_DIFF") #Exclude column "Year Ranges" Correlations_DVP_Excluded <- Correlations_DVP[,!names(Correlations_DVP) %in% c("Year Ranges")] Correlations_EME_Excluded <- Correlations_EME[,!names(Correlations_EME) %in% c("Years")] Correlations_EME_LN_Excluded <- Correlations_EME_LN[,!names(Correlations_EME_LN) %in% c("Years")] EPU_Developed_FREQ_CORR_Excluded <- EPU_Developed_FREQ_CORR[,!names(EPU_Developed_FREQ_CORR) %in% c("Year")] EPU_Developed_FREQ_CORR_DIFF_Excluded <- EPU_Developed_FREQ_CORR_DIFF[,!names(EPU_Developed_FREQ_CORR_DIFF) %in% c("Year")] EPU_Emerging_FREQ_CORR_Excluded <- EPU_Emerging_FREQ_CORR[,!names(EPU_Emerging_FREQ_CORR) %in% c("Years")] EPU_Emerging_FREQ_CORR_DIFF_Excluded <- EPU_Emerging_FREQ_CORR_DIFF[,!names(EPU_Emerging_FREQ_CORR_DIFF) %in% c("Years")] #Convert to numeric data #Convert list in vector data #as.numeric requires a vector of values Vector_data_21 <- unlist(Correlations_DVP_Excluded) Vector_data_22 <- unlist(Correlations_EME_Excluded) Vector_data_23 <- unlist(EPU_Developed_FREQ_CORR_Excluded) Vector_data_24 <- unlist(EPU_Emerging_FREQ_CORR_Excluded) Vector_data_25 <- unlist(Correlations_EME_LN_Excluded) Vector_data_27 <- unlist(EPU_Developed_FREQ_CORR_DIFF_Excluded) Vector_data_28 <- unlist(EPU_Emerging_FREQ_CORR_DIFF_Excluded) #Numeric data conversion #to convert the vector in numeric data Numeric_data_21 <- as.numeric(Vector_data_21) is.numeric(Numeric_data_21) Numeric_data_22 <- as.numeric(Vector_data_22) is.numeric(Numeric_data_22) Numeric_data_23 <- as.numeric(Vector_data_23) is.numeric(Numeric_data_23) Numeric_data_24 <- as.numeric(Vector_data_24) is.numeric(Numeric_data_24) Numeric_data_25 <- as.numeric(Vector_data_25) is.numeric(Numeric_data_25) Numeric_data_27 <- as.numeric(Vector_data_27) is.numeric(Numeric_data_27) Numeric_data_28 <- as.numeric(Vector_data_28) is.numeric(Numeric_data_28) #Remove "N/A values" Numeric_data_25_clean <- na.omit(Numeric_data_25) #DATA STATIONARITY TESTS #Correlations_DVP adf.test(Numeric_data_21) #Correlations_EMR adf.test(Numeric_data_22) adf.test(Numeric_data_25_clean) #LN transformation for stationarity #EPU_Developed_FREQ_CORR adf.test(Numeric_data_23) adf.test(Numeric_data_27) #differencing transformation for stationarity #EPU_Emerging_FREQ_CORR adf.test(Numeric_data_24) adf.test(Numeric_data_28) #differencing transformation for stationarity #FREQUENCY HISTOGRAMS #Correlations_DVP hist(Numeric_data_21) #Correlations_EMR hist(Numeric_data_22) #normal hist(Numeric_data_25_clean) #ln ##Regression_Correlations_DEV Regression_COR_DVP_Data <- cbind(Correlations_DVP, EPU_Developed_FREQ_CORR_DIFF) Regression_5 <- lm(Australia_CORR+Canada_CORR+Germany_CORR+Spain_CORR+France_CORR+UK_CORR+Greece_CORR+Ireland_CORR+Italy_CORR+Japan_CORR+Sweden_CORR+Singapore_CORR+US_CORR #run regression 5 ~ log10(Australia_EPU_Diff+Canada_EPU_Diff+Germany_EPU_Diff+Spain_EPU_Diff+France_EPU_Diff+UK_EPU_Diff+Greece_EPU_Diff+Ireland_EPU_Diff+Italy_EPU_Diff+Japan_EPU_Diff+Sweden_EPU_Diff+Singapore_EPU_Diff+US_EPU_Diff) , data = Regression_COR_DVP_Data, na.action = na.omit) summary(Regression_5) #to have the summary of Regression_5 ##Regression_Correlations_EMR Regression_CORR_EMR_Data <- cbind(Correlations_EME_LN, EPU_Emerging_FREQ_CORR_DIFF) #create a single data frame for regression 6 Regression_6 <- lm(Brazil_CORR+Chile_CORR+China_CORR+India_CORR+Mexico_CORR+Pakistan_CORR+Russia_CORR+Korea_CORR #run regression 6 ~ log10(Brazil_EPU_DIFF+Chile_EPU_DIFF+China_EPU_DIFF+India_EPU_DIFF+Mexico_EPU_DIFF+Pakistan_EPU_DIFF+Russia_EPU_DIFF+Korea_EPU_DIFF) , data = Regression_CORR_EMR_Data, na.action = na.omit) summary(Regression_6) #to have the summary of Regression_6 ##ASSUMPTIONS TESTS ##Regression_1: SER_Developed #MULTICOLLINEARITY - FARRAR-GLAUBER TEST install.packages("mctest") #Install and load necessary packages library("mctest") mctest(Regression_1) #HOMOSCEDASTIC VARIANCE - GOLDFELD-QUANDT TEST install.packages("lmtest") #Install and load necessary packages library("lmtest") gqtest(Regression_1) #NORMALITY OF THE RESIDUALS - JARQUE-BERA TEST install.packages("desk") #Install & load necessary packages library("desk") Resid_Reg_1 <- residuals(Regression_1) #Extract the residuals of Regression_1 jb.test(Resid_Reg_1) #Jarque-Bera test on residuals of Regression_1 #AUTO-CORRELATION OF THE RESIDUALS - DURBIN-WATSON TEST #install & load necessary packages install.packages("car") library(car) durbinWatsonTest(Resid_Reg_1) #Durbin-Watson test on residuals ##Regression_2: SER_Emerging #MULTICOLLINEARITY - FARRAR-GLAUBER TEST install.packages("mctest") #Install and load necessary packages library("mctest") mctest(Regression_2) #HOMOSCEDASTIC VARIANCE - GOLDFELD-QUANDT TEST install.packages("lmtest") #Install and load necessary packages library("lmtest") gqtest(Regression_2) #NORMALITY OF THE RESIDUALS - JARQUE-BERA TEST install.packages("desk") #Install & load necessary packages library("desk") Resid_Reg_2 <- residuals(Regression_2) #Extract the residuals of Regression 2 jb.test(Resid_Reg_2) #Jarque-Bera test on the residuals of Regression 2 #NON-NORMALITY DETECTED - TROUBLESHOOTING hist(Resid_Reg_2) #histogram of residuals qqplot(Resid_Reg_2, Resid_Reg_2) #qqplot #AUTO-CORRELATION OF THE RESIDUALS - DURBIN-WATSON TEST install.packages("car") library(car) durbinWatsonTest(Resid_Reg_2) #Durbin-Watson test on residuals ##Regression_3: BER_Developed #MULTICOLLINEARITY - FARRAR-GLAUBER TEST mctest(Regression_3) #HOMOSCEDASTIC VARIANCE - WHITE TEST install.packages("whitestrap") #Install & load necessary packages library("whitestrap") white_test(Regression_3) #NORMALITY OF THE RESIDUALS - JARQUE-BERA TEST Resid_Reg_3 <- residuals(Regression_3) #Extract the residuals of Regression 3 jb.test(Resid_Reg_3) #Jarque-Bera test on the residuals of Regression 3 #AUTO-CORRELATION OF THE RESIDUALS - DURBIN-WATSON TEST durbinWatsonTest(Resid_Reg_3) #Durbin-Watson test on the residuals ##Regression_4: BER_Emerging #MULTICOLLINEARITY - FARRAR-GLAUBER TEST mctest(Regression_4) #HOMOSCEDASTIC VARIANCE - WHITE TEST install.packages("whitestrap") #Install & load necessary packages library("whitestrap") white_test(Regression_4) #NORMALITY OF THE RESIDUALS - JARQUE-BERA TEST Resid_Reg_4 <- residuals(Regression_4) #Extract the residuals of Regression 4 jb.test(Resid_Reg_4) #Jarque-Bera test on the residuals of Regression 4 #AUTO-CORRELATION OF THE RESIDUALS - DURBIN-WATSON TEST durbinWatsonTest(Resid_Reg_4) #Durbin-Watson test on the residuals ##Regression 5: Correlations_Developed: Simple linear regression #LINEARITY - SCATTERPLOT WITH REGRESSION LINE plot(Numeric_data_23, Numeric_data_21, main = "Scatterplot with regression line - 2015-2024 for Developed Countries", xlab= "EPU Indexes", ylab="Share-Bond Excess Returns Correlations") #creation of the scatter plot with plot() function regression_line <- lm(Numeric_data_21 ~ Numeric_data_23) #creation of the regression line abline(regression_line, col = "green") #add the regression line on the scatter plot (add a straight line to the plot) #HOMOSCEDASTIC VARIANCE - WHITE TEST white_test(Regression_5) #NORMALITY OF THE RESIDUALS - JARQUE-BERA TEST install.packages("desk") #Install & load necessary packages library("desk") Resid_Reg_5 <- residuals(Regression_5) #Extract the residuals of Regression 5 jb.test(Resid_Reg_5) #Jarque-Bera test on the residuals of Regression 5 #AUTO-CORRELATION OF THE RESIDUALS - DURBIN-WATSON TEST install.packages("car") library(car) durbinWatsonTest(Resid_Reg_5) #Durbin-Watson test on the residuals ##Regression 6: Correlations_Emerging #LINEARITY - SCATTERPLOT WITH REGRESSION LINE plot(Numeric_data_24, Numeric_data_22, main = "Scatterplot with regression line - 2015-2024 for Emerging Countries", xlab= "EPU Indexes", ylab="Share-Bond Excess Returns Correlations") #creation of the scatter plot with plot() function regression_line <- lm(Numeric_data_22 ~ Numeric_data_24) #creation of the regression line abline(regression_line, col = "green") #HOMOSCEDASTIC VARIANCE - WHITE TEST library(whitestrap) white_test(Regression_6) #NORMALITY OF THE RESIDUALS - JARQUE-BERA TEST install.packages("desk") #Install & load necessary packages library("desk") Resid_Reg_6 <- residuals(Regression_6) #Extract the residuals of Regression 6 jb.test(Resid_Reg_6) #Jarque-Bera test on the residuals of Regression 6 #AUTO-CORRELATION OF THE RESIDUALS - DURBIN-WATSON TEST install.packages("car") library(car) durbinWatsonTest(Resid_Reg_6) #Durbin-Watson test on the residuals