Primeiro, importamos a base de dados com os retornos diários dos 5 fundos de investimento, do Ibovespa, da taxa livre de risco e dos 4 fatores do modelo Cahart.
Dados <- read_delim("Dados - Fundos de Investimento.csv",
";", escape_double = FALSE,
trim_ws = TRUE)
head(Dados)
## # A tibble: 6 x 12
## Data `Brasil Capital` `Dynamo Cougar` `IP Participaco~ Constellation Squadra
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 12/3~ 0.00773 0.00781 -0.00138 0.00561 0.00175
## 2 12/2~ 0.00225 0.00189 -0.00184 0.000810 -0.00174
## 3 12/2~ 0.0148 0.00574 0.0174 0.00967 0.0111
## 4 12/2~ 0.00502 0.00873 0.00270 0.00363 0.0108
## 5 12/2~ 0.00816 0.00332 -0.00302 0.00741 0.00549
## 6 12/2~ -0.0146 -0.0174 -0.00600 -0.00608 -0.0187
## # ... with 6 more variables: Ibovespa <dbl>, `Risk Free` <dbl>, `Market
## # Factor` <dbl>, `SMB Factor` <dbl>, `HML Factor` <dbl>, `WML Factor` <dbl>
Para evitar a repetição de códigos com o mesmo objetivo, criaremos uma função para cada estatítisca.
Vale ressaltar que a frequência dos retornos é diária. Assim, tentar utilizar essas funções com dados em uma frequência diferente (mensal, trimestral, anual, etc.), muito provavelmente, não irá retornar os resultados esperados.
media_arit_ano <- function(x){
mean(x)*252*100
}
media_geom_anual <- function(x){
(prod(x+1) ^ (252/length(x)) - 1)*100
}
desvpad_anual <- function(x){
sd(x)*sqrt(252)*100
}
coef_var <- function(x){
desvpad_anual(x)/media_geom_anual(x)
}
“x” é o vetor que contém os retornos diários do portfólio e “y” é o vetor que contém os retornos diários da carteira de mercado (Ibovespa).
coef_beta <- function(x,y){
cov(x,y)/var(y)
}
“x” é o vetor que contém os retornos diários do portfólio e “y” é o vetor que contém os retornos diários da carteira de mercado (Ibovespa).
grau_diversif <- function(x,y){
((coef_beta(x,y)^2 * var(y))/var(x))*100
}
“x” é o vetor que contém os retornos diários do portfólio e “z” é o vetor que contém os retornos diários da taxa livre de risco (Swap DI 30 dias).
indice_Sharpe <- function(x,z){
P_Rf <- media_geom_anual(x) - media_geom_anual(z)
P_Rf/desvpad_anual(x)
}
“x” é o vetor que contém os retornos diários do portfólio; “y” é o vetor que contém os retornos diários da carteira de mercado (Ibovespa); e “z” é o vetor que contém os retornos diários da taxa livre de risco (Swap DI 30 dias).
indice_Treynor <- function(x,y,z){
P_Rf <- media_geom_anual(x) - media_geom_anual(z)
P_Rf/coef_beta(x,y)
}
“x” é o vetor que contém os retornos diários do portfólio; “y” é o vetor que contém os retornos diários da carteira de mercado (Ibovespa); e “z” é o vetor que contém os retornos diários da taxa livre de risco (Swap DI 30 dias).
indice_M2 <- function(x,y,z){
P_Rf <- media_geom_anual(x) - media_geom_anual(z)
(P_Rf * desvpad_anual(y)/desvpad_anual(x)) -
(media_geom_anual(y) - media_geom_anual(z))
}
“x” é o vetor que contém os retornos diários do portfólio; “y” é o vetor que contém os retornos diários da carteira de mercado (Ibovespa); e “k” é o alfa da regressão dos retornos dos fundos contra os fatores de risco.
indice_informacao <- function(x,y,k){
k/sqrt((var(x) - (coef_beta(x,y)^2)*var(y)))
}
Primeiro, selecionamos as 5 primeiras colunas da base de dados “Dados”, visando facilitar o uso dos for loops.
Dados_Fundos <- Dados[,2:6]
Dados_Fundos
## # A tibble: 2,599 x 5
## `Brasil Capital` `Dynamo Cougar` `IP Participacoes` Constellation Squadra
## <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0.00773 0.00781 -0.00138 0.00561 0.00175
## 2 0.00225 0.00189 -0.00184 0.000810 -0.00174
## 3 0.0148 0.00574 0.0174 0.00967 0.0111
## 4 0.00502 0.00873 0.00270 0.00363 0.0108
## 5 0.00816 0.00332 -0.00302 0.00741 0.00549
## 6 -0.0146 -0.0174 -0.00600 -0.00608 -0.0187
## 7 -0.00123 0.00162 0.000316 -0.00213 -0.00323
## 8 0.00672 0.00361 0.00321 0.00857 0.00278
## 9 0.0137 0.0142 0.00471 0.0165 0.0153
## 10 0.0177 0.0176 0.00719 0.0125 0.0160
## # ... with 2,589 more rows
a <- vector("double", 5)
for (i in seq_along(Dados_Fundos)){
a[[i]] <- media_arit_ano(Dados_Fundos[[i]])
}
## [1] 22.99193 20.33945 15.75121 18.16196 20.58763
b <- vector("double", 5)
for (i in seq_along(Dados_Fundos)){
b[[i]] <- media_geom_anual(Dados_Fundos[[i]])
}
## [1] 23.04872 20.26916 16.10030 17.36908 20.06769
c <- vector("double", 5)
for (i in seq_along(Dados_Fundos)){
c[[i]] <- desvpad_anual(Dados_Fundos[[i]])
}
## [1] 20.95401 19.20066 12.75929 20.55271 21.24898
d <- vector("double", 5)
for (i in seq_along(Dados_Fundos)){
d[[i]] <- coef_var(Dados_Fundos[[i]])
}
## [1] 0.9091178 0.9472844 0.7924879 1.1832931 1.0588655
e <- vector("double", 5)
for (i in seq_along(Dados_Fundos)){
e[[i]] <- coef_beta(Dados_Fundos[[i]], Dados$Ibovespa)
}
## [1] 0.6841426 0.6577212 0.3768783 0.7202452 0.7511017
f <- vector("double", 5)
for (i in seq_along(Dados_Fundos)){
f[[i]] <- grau_diversif(Dados_Fundos[[i]], Dados$Ibovespa)
}
## [1] 68.20250 75.07456 55.82006 78.57128 79.93965
g <- vector("double", 5)
for (i in seq_along(Dados_Fundos)){
g[[i]] <- indice_Sharpe(Dados_Fundos[[i]], Dados$`Risk Free`)
}
## [1] 0.6631372 0.5789288 0.5444625 0.3997397 0.5136409
h <- vector("double", 5)
for (i in seq_along(Dados_Fundos)){
h[[i]] <- indice_Treynor(Dados_Fundos[[i]], Dados$Ibovespa, Dados$`Risk Free`)
}
## [1] 20.31065 16.90049 18.43289 11.40686 14.53112
ha <- vector("double", 5)
for (i in seq_along(Dados_Fundos)){
ha[[i]] <- indice_M2(Dados_Fundos[[i]], Dados$Ibovespa,
Dados$`Risk Free`)
}
## [1] 19.22059 17.09060 16.21881 12.55816 15.43920
Aproximando da conclusão do trabalho, apresentamos uma tabela parcial com as estatísticas já calculadas. O Alfa de Jensen e o Índice de Informação serão calculados em seguida.
tabela_parcial <- rbind.data.frame(a,b,c,d,e,f,g,h,ha)
## Brasil Capital Dynamo Cougar IP Participações
## Média Aritmética (%) 22.9919262 20.3394514 15.7512051
## Média Geométrica (%) 23.0487248 20.2691560 16.1002990
## Desvio-Padrão (%) 20.9540067 19.2006553 12.7592920
## Coeficiente de Variação 0.9091178 0.9472844 0.7924879
## Beta 0.6841426 0.6577212 0.3768783
## Grau de Diversificação (%) 68.2024967 75.0745562 55.8200638
## Índice Sharpe 0.6631372 0.5789288 0.5444625
## Índice Treynor 20.3106513 16.9004931 18.4328881
## Índice M^2 19.2205861 17.0906042 16.2188064
## Constellation Squadra
## Média Aritmética (%) 18.1619594 20.5876273
## Média Geométrica (%) 17.3690764 20.0676904
## Desvio-Padrão (%) 20.5527079 21.2489844
## Coeficiente de Variação 1.1832931 1.0588655
## Beta 0.7202452 0.7511017
## Grau de Diversificação (%) 78.5712840 79.9396524
## Índice Sharpe 0.3997397 0.5136409
## Índice Treynor 11.4068555 14.5311186
## Índice M^2 12.5581622 15.4391993
CAPM_BC <- lm(I(`Brasil Capital` - `Risk Free`) ~ `Market Factor`)
##
## Call:
## lm(formula = I(`Brasil Capital` - `Risk Free`) ~ `Market Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.065485 -0.003687 0.000042 0.003698 0.051288
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0004487 0.0001381 3.249 0.00117 **
## `Market Factor` 0.7854119 0.0097126 80.865 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.00704 on 2597 degrees of freedom
## Multiple R-squared: 0.7157, Adjusted R-squared: 0.7156
## F-statistic: 6539 on 1 and 2597 DF, p-value: < 2.2e-16
CAPM_DC <- lm(I(`Dynamo Cougar` - `Risk Free`) ~ `Market Factor`)
##
## Call:
## lm(formula = I(`Dynamo Cougar` - `Risk Free`) ~ `Market Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.060506 -0.002945 -0.000033 0.002975 0.036942
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0003482 0.0001104 3.153 0.00163 **
## `Market Factor` 0.7531410 0.0077656 96.984 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.005629 on 2597 degrees of freedom
## Multiple R-squared: 0.7836, Adjusted R-squared: 0.7836
## F-statistic: 9406 on 1 and 2597 DF, p-value: < 2.2e-16
CAPM_IP <- lm(I(`IP Participacoes` - `Risk Free`) ~ `Market Factor`)
##
## Call:
## lm(formula = I(`IP Participacoes` - `Risk Free`) ~ `Market Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.058684 -0.002647 0.000014 0.002557 0.045989
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0002143 0.0001035 2.072 0.0384 *
## `Market Factor` 0.4269212 0.0072755 58.679 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.005274 on 2597 degrees of freedom
## Multiple R-squared: 0.5701, Adjusted R-squared: 0.5699
## F-statistic: 3443 on 1 and 2597 DF, p-value: < 2.2e-16
CAPM_CL <- lm(I(Constellation - `Risk Free`) ~ `Market Factor`)
##
## Call:
## lm(formula = I(Constellation - `Risk Free`) ~ `Market Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.042295 -0.002853 0.000034 0.002989 0.041926
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0002509 0.0001065 2.357 0.0185 *
## `Market Factor` 0.8268976 0.0074866 110.450 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.005427 on 2597 degrees of freedom
## Multiple R-squared: 0.8245, Adjusted R-squared: 0.8244
## F-statistic: 1.22e+04 on 1 and 2597 DF, p-value: < 2.2e-16
CAPM_SD <- lm(I(Squadra - `Risk Free`) ~ `Market Factor`)
##
## Call:
## lm(formula = I(Squadra - `Risk Free`) ~ `Market Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.047801 -0.003253 -0.000053 0.003432 0.037114
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0003419 0.0001054 3.244 0.00119 **
## `Market Factor` 0.8623507 0.0074118 116.349 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.005373 on 2597 degrees of freedom
## Multiple R-squared: 0.839, Adjusted R-squared: 0.839
## F-statistic: 1.354e+04 on 1 and 2597 DF, p-value: < 2.2e-16
coef_CAPM_BC <- coef(CAPM_BC)
Alfa_Jansen_BC <- (((coef_CAPM_BC[1] + 1)^252)-1)*100
## (Intercept)
## 11.96795
coef_CAPM_DC <- coef(CAPM_DC)
Alfa_Jansen_DC <- (((coef_CAPM_DC[1] + 1)^252)-1)*100
## (Intercept)
## 9.169297
coef_CAPM_IP <- coef(CAPM_IP)
Alfa_Jansen_IP <- (((coef_CAPM_IP[1] + 1)^252)-1)*100
## (Intercept)
## 5.549086
coef_CAPM_CL <- coef(CAPM_CL)
Alfa_Jansen_CL <- (((coef_CAPM_CL[1] + 1)^252)-1)*100
## (Intercept)
## 6.525607
coef_CAPM_SD <- coef(CAPM_SD)
Alfa_Jansen_SD <- (((coef_CAPM_SD[1] + 1)^252)-1)*100
## (Intercept)
## 8.996407
Agora, com base nos dados dessas regressões, podemos calcular o Índice de Informação.
Observação: “f” refere-se ao vetor que contém os graus de diversificação e “c” ao vetor que contém os desvios-padrões dos fundos.
alfas_jensen <- c(Alfa_Jansen_BC, Alfa_Jansen_DC, Alfa_Jansen_IP, Alfa_Jansen_CL, Alfa_Jansen_SD)
## (Intercept) (Intercept) (Intercept) (Intercept) (Intercept)
## 11.967950 9.169297 5.549086 6.525607 8.996407
risco_nao_sistemico <- (1 - f/100)*c
indice_informacao <- alfas_jensen/risco_nao_sistemico
## (Intercept) (Intercept) (Intercept) (Intercept) (Intercept)
## 1.7962206 1.9159187 0.9843959 1.4816845 2.1105346
FF_BC <- lm(I(`Brasil Capital` - `Risk Free`) ~ `Market Factor` + `SMB Factor` + `HML Factor`)
##
## Call:
## lm(formula = I(`Brasil Capital` - `Risk Free`) ~ `Market Factor` +
## `SMB Factor` + `HML Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.051987 -0.003596 -0.000055 0.003608 0.031196
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0004994 0.0001262 3.958 7.76e-05 ***
## `Market Factor` 0.8430776 0.0092872 90.778 < 2e-16 ***
## `SMB Factor` 0.2932454 0.0159481 18.387 < 2e-16 ***
## `HML Factor` -0.3268327 0.0172445 -18.953 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.00643 on 2595 degrees of freedom
## Multiple R-squared: 0.763, Adjusted R-squared: 0.7628
## F-statistic: 2785 on 3 and 2595 DF, p-value: < 2.2e-16
FF_DC <- lm(I(`Dynamo Cougar` - `Risk Free`) ~ `Market Factor` + `SMB Factor` + `HML Factor`)
##
## Call:
## lm(formula = I(`Dynamo Cougar` - `Risk Free`) ~ `Market Factor` +
## `SMB Factor` + `HML Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.042742 -0.003026 -0.000040 0.003065 0.030313
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0003755 0.0001044 3.597 0.000328 ***
## `Market Factor` 0.7920933 0.0076850 103.070 < 2e-16 ***
## `SMB Factor` 0.1644952 0.0131969 12.465 < 2e-16 ***
## `HML Factor` -0.2287418 0.0142696 -16.030 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.005321 on 2595 degrees of freedom
## Multiple R-squared: 0.8068, Adjusted R-squared: 0.8066
## F-statistic: 3612 on 3 and 2595 DF, p-value: < 2.2e-16
FF_IP <- lm(I(`IP Participacoes` - `Risk Free`) ~ `Market Factor` + `SMB Factor` + `HML Factor`)
##
## Call:
## lm(formula = I(`IP Participacoes` - `Risk Free`) ~ `Market Factor` +
## `SMB Factor` + `HML Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.046970 -0.002628 -0.000050 0.002589 0.040488
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0002257 0.0001010 2.234 0.0256 *
## `Market Factor` 0.4518909 0.0074373 60.760 < 2e-16 ***
## `SMB Factor` 0.0756260 0.0127715 5.921 3.61e-09 ***
## `HML Factor` -0.1537075 0.0138096 -11.130 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.00515 on 2595 degrees of freedom
## Multiple R-squared: 0.5904, Adjusted R-squared: 0.5899
## F-statistic: 1247 on 3 and 2595 DF, p-value: < 2.2e-16
FF_CL <- lm(I(Constellation - `Risk Free`) ~ `Market Factor` + `SMB Factor` + `HML Factor`)
##
## Call:
## lm(formula = I(Constellation - `Risk Free`) ~ `Market Factor` +
## `SMB Factor` + `HML Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.036909 -0.002689 -0.000038 0.002921 0.026154
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.859e-04 9.684e-05 2.952 0.00319 **
## `Market Factor` 8.743e-01 7.128e-03 122.657 < 2e-16 ***
## `SMB Factor` 2.084e-01 1.224e-02 17.029 < 2e-16 ***
## `HML Factor` -2.763e-01 1.324e-02 -20.879 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.004935 on 2595 degrees of freedom
## Multiple R-squared: 0.8549, Adjusted R-squared: 0.8548
## F-statistic: 5098 on 3 and 2595 DF, p-value: < 2.2e-16
FF_SD <- lm(I(Squadra - `Risk Free`) ~ `Market Factor` + `SMB Factor` + `HML Factor`)
##
## Call:
## lm(formula = I(Squadra - `Risk Free`) ~ `Market Factor` + `SMB Factor` +
## `HML Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.032919 -0.003088 -0.000004 0.003194 0.036991
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0003716 0.0001002 3.707 0.000214 ***
## `Market Factor` 0.8957200 0.0073785 121.396 < 2e-16 ***
## `SMB Factor` 0.1715312 0.0126704 13.538 < 2e-16 ***
## `HML Factor` -0.1886913 0.0137003 -13.773 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.005109 on 2595 degrees of freedom
## Multiple R-squared: 0.8546, Adjusted R-squared: 0.8544
## F-statistic: 5082 on 3 and 2595 DF, p-value: < 2.2e-16
CHT_BC <- lm(I(`Brasil Capital` - `Risk Free`) ~ `Market Factor` + `SMB Factor` + `HML Factor` + `WML Factor`)
##
## Call:
## lm(formula = I(`Brasil Capital` - `Risk Free`) ~ `Market Factor` +
## `SMB Factor` + `HML Factor` + `WML Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.047028 -0.003627 -0.000113 0.003623 0.027960
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0004016 0.0001244 3.228 0.00126 **
## `Market Factor` 0.8437139 0.0091263 92.448 < 2e-16 ***
## `SMB Factor` 0.3079249 0.0157449 19.557 < 2e-16 ***
## `HML Factor` -0.2710100 0.0179024 -15.138 < 2e-16 ***
## `WML Factor` 0.1341858 0.0138821 9.666 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.006319 on 2594 degrees of freedom
## Multiple R-squared: 0.7713, Adjusted R-squared: 0.7709
## F-statistic: 2187 on 4 and 2594 DF, p-value: < 2.2e-16
CHT_DC <- lm(I(`Dynamo Cougar` - `Risk Free`) ~ `Market Factor` + `SMB Factor` + `HML Factor` + `WML Factor`)
##
## Call:
## lm(formula = I(`Dynamo Cougar` - `Risk Free`) ~ `Market Factor` +
## `SMB Factor` + `HML Factor` + `WML Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.041017 -0.003004 -0.000034 0.002886 0.028646
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0002866 0.0001026 2.795 0.00523 **
## `Market Factor` 0.7926717 0.0075238 105.355 < 2e-16 ***
## `SMB Factor` 0.1778362 0.0129802 13.701 < 2e-16 ***
## `HML Factor` -0.1780090 0.0147589 -12.061 < 2e-16 ***
## `WML Factor` 0.1219509 0.0114445 10.656 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.005209 on 2594 degrees of freedom
## Multiple R-squared: 0.8149, Adjusted R-squared: 0.8146
## F-statistic: 2855 on 4 and 2594 DF, p-value: < 2.2e-16
CHT_IP <- lm(I(`IP Participacoes` - `Risk Free`) ~ `Market Factor` + `SMB Factor` + `HML Factor` + `WML Factor`)
##
## Call:
## lm(formula = I(`IP Participacoes` - `Risk Free`) ~ `Market Factor` +
## `SMB Factor` + `HML Factor` + `WML Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.046700 -0.002606 -0.000042 0.002551 0.040069
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0002118 0.0001013 2.090 0.0367 *
## `Market Factor` 0.4519812 0.0074349 60.792 < 2e-16 ***
## `SMB Factor` 0.0777080 0.0128268 6.058 1.58e-09 ***
## `HML Factor` -0.1457900 0.0145844 -9.996 < 2e-16 ***
## `WML Factor` 0.0190318 0.0113092 1.683 0.0925 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.005148 on 2594 degrees of freedom
## Multiple R-squared: 0.5908, Adjusted R-squared: 0.5902
## F-statistic: 936.4 on 4 and 2594 DF, p-value: < 2.2e-16
CHT_CL <- lm(I(Constellation - `Risk Free`) ~ `Market Factor` + `SMB Factor` + `HML Factor` + `WML Factor`)
##
## Call:
## lm(formula = I(Constellation - `Risk Free`) ~ `Market Factor` +
## `SMB Factor` + `HML Factor` + `WML Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.025158 -0.002777 0.000025 0.002799 0.022202
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.0001468 0.0000912 1.61 0.108
## `Market Factor` 0.8751944 0.0066908 130.81 <2e-16 ***
## `SMB Factor` 0.2293100 0.0115430 19.87 <2e-16 ***
## `HML Factor` -0.1969757 0.0131247 -15.01 <2e-16 ***
## `WML Factor` 0.1907558 0.0101773 18.74 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.004633 on 2594 degrees of freedom
## Multiple R-squared: 0.8722, Adjusted R-squared: 0.872
## F-statistic: 4428 on 4 and 2594 DF, p-value: < 2.2e-16
CHT_SD <- lm(I(Squadra - `Risk Free`) ~ `Market Factor` + `SMB Factor` + `HML Factor` + `WML Factor`)
##
## Call:
## lm(formula = I(Squadra - `Risk Free`) ~ `Market Factor` + `SMB Factor` +
## `HML Factor` + `WML Factor`)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.030847 -0.003043 -0.000078 0.003079 0.038903
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.649e-04 9.724e-05 2.724 0.0065 **
## `Market Factor` 8.964e-01 7.134e-03 125.658 <2e-16 ***
## `SMB Factor` 1.876e-01 1.231e-02 15.240 <2e-16 ***
## `HML Factor` -1.278e-01 1.399e-02 -9.129 <2e-16 ***
## `WML Factor` 1.465e-01 1.085e-02 13.500 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.004939 on 2594 degrees of freedom
## Multiple R-squared: 0.8641, Adjusted R-squared: 0.8639
## F-statistic: 4124 on 4 and 2594 DF, p-value: < 2.2e-16