hw05FamaMacbeth

library(broom)
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.2.0     ✔ readr     2.2.0
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.2     ✔ tibble    3.3.1
## ✔ lubridate 1.9.5     ✔ tidyr     1.3.2
## ✔ purrr     1.2.1     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

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

Estimate N Time series Regression

step0 <- data %>% 
  nest(data = c(date,ri,MKT,SMB,HML)) %>% 
  mutate(estimates = map(
    data,
    ~tidy(lm(ri ~ MKT + SMB + HML, data = .x))
  )) %>% 
  unnest(estimates) %>% 
  select(symbol, estimate, term) %>% 
  pivot_wider(names_from  = term,
              values_from = estimate) %>% 
  select(symbol, 
         b_MKT = MKT, 
         b_HML = HML, 
         b_SMB = SMB)

step0 <- data %>% 
  left_join(step0, by = "symbol")

Estimate T Cross-sectional regression

step1 <- step0 %>% 
    nest(data = c(symbol, ri, b_MKT, b_SMB, b_HML)) %>% 
  mutate(estimates = map(
    data,
    ~tidy(lm(ri ~ b_MKT + b_SMB + b_HML, data = .x))
  )) %>%
  unnest(estimates) %>% 
  select(date, estimate, term) %>% 
  pivot_wider(names_from  = term,
              values_from = estimate) %>% 
  select(date, b_MKT, b_HML, b_SMB)

Step2: Estimate time series averages

t.test(step1$b_MKT, mu=0)

## 
##  One Sample t-test
## 
## data:  step1$b_MKT
## t = -0.37879, df = 1256, p-value = 0.7049
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
##  -0.002546371  0.001722208
## sample estimates:
##     mean of x 
## -0.0004120813

t.test(step1$b_SMB, mu=0)

## 
##  One Sample t-test
## 
## data:  step1$b_SMB
## t = 0.97712, df = 1256, p-value = 0.3287
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
##  -0.003711466  0.011076953
## sample estimates:
##   mean of x 
## 0.003682744

t.test(step1$b_HML, mu=0)

## 
##  One Sample t-test
## 
## data:  step1$b_HML
## t = -0.18044, df = 1256, p-value = 0.8568
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
##  -0.005541205  0.004607776
## sample estimates:
##     mean of x 
## -0.0004667146