Question

What are the implications of predictability results in Part 2 and 3 for investment decisions?

Part 2

use log dividend-price ratio to predict the 5-year stock market excess log returns:

lm(formula = lnexret[2:t] ~ dp[1:t - 1])

Residuals:

     Min 1Q Median 3Q Max

-0.54389 -0.07305 0.01977 0.10712 0.34107

Coefficients:

            Estimate Std. Error t value

(Intercept) 0.58469 0.12768 4.579

dp[1:t - 1] 0.13510 0.03771 3.582

                 Pr(>|t|)    

(Intercept) 1.58e-05 ***

dp[1:t - 1] 0.000567 ***

---

Signif. codes:  

0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.1626 on 85 degrees of freedom

  (4 observations deleted due to missingness)

Multiple R-squared: 0.1312, Adjusted R-squared: 0.1209

F-statistic: 12.83 on 1 and 85 DF, p-value: 0.0005668

use log dividend-price ratio to predict the 5-year stock market excess simple returns

lm(formula = simexret[2:t] ~ dp[1:t - 1])

Residuals:

     Min 1Q Median 3Q Max

-1.29268 -0.32420 -0.05609 0.34175 1.85945

Coefficients:

            Estimate Std. Error t value Pr(>|t|)    

(Intercept) 2.2498 0.4400 5.113 1.93e-06 ***

dp[1:t - 1] 0.5142 0.1300 3.957 0.000157 ***

---

Signif. codes:  

0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.5603 on 85 degrees of freedom

  (4 observations deleted due to missingness)

Multiple R-squared: 0.1555, Adjusted R-squared: 0.1456

F-statistic: 15.66 on 1 and 85 DF, p-value: 0.000157

Response: simexret[2:t]

                  Df Sum Sq Mean Sq F value Pr(>F)    

dp[1:t - 1] 1 4.915 4.9150 15.656 0.000157 ***

Residuals 85 26.685 0.3139                     

---

Signif. codes:  

0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

> plot(x=dp[1:t-1],y=simexret[2:t])

> abline(lm(simexret[2:T]~dp[1:T-1]))

part 3:

use book-market ratio to predict the 5-year stock market excess log returns:

Call:

lm(formula = X5y_logexret[2:T] ~ bm[1:T - 1])

Residuals:

     Min 1Q Median 3Q Max

-0.47132 -0.10729 0.00696 0.10708 0.37486

Coefficients:

            Estimate Std. Error t value Pr(>|t|)   

(Intercept) 0.008525 0.042782 0.199 0.84253   

bm[1:T - 1] 0.214525 0.067897 3.160 0.00219 **

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.165 on 85 degrees of freedom

  (4 observations deleted due to missingness)

Multiple R-squared: 0.1051, Adjusted R-squared: 0.09457

F-statistic: 9.983 on 1 and 85 DF, p-value: 0.002189

Response: X5y_logexret[2:T]

                   Df Sum Sq Mean Sq F value Pr(>F)   

bm[1:T - 1] 1 0.27182 0.271825 9.983 0.002189 **

Residuals 85 2.31445 0.027229                    

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

use book-market ratio to predict the 5-year stock market excess simple returns:

Call:

lm(formula = X5y_exret[2:T] ~ bm[1:T - 1])

Residuals:

     Min 1Q Median 3Q Max

-1.04319 -0.39755 -0.06091 0.36066 1.95017

Coefficients:

            Estimate Std. Error t value Pr(>|t|)   

(Intercept) 0.1337 0.1510 0.885 0.37843   

bm[1:T - 1] 0.6822 0.2397 2.846 0.00555 **

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.5826 on 85 degrees of freedom

  (4 observations deleted due to missingness)

Multiple R-squared: 0.08699, Adjusted R-squared: 0.07625

F-statistic: 8.099 on 1 and 85 DF, p-value: 0.00555

Analysis of Variance Table

Response: X5y_exret[2:T]

                 Df Sum Sq Mean Sq F value Pr(>F)   

bm[1:T - 1] 1 2.749 2.74903 8.099 0.00555 **

Residuals 85 28.852 0.33943                   

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Answer 1

Before uploading the outcomes of R, first upload the base and details of the problem, without them just depending on the output no one can solve it. Only maximum you can expect in this case is that guessed solution which maybe right or maybe wrong.

Kindly upload the whole problem with complete details, not just R programme outputs.