homework6

Set Up

#
remove(list = ls())

Importing

# importing package
library(stargazer)

Please cite as: 

 Hlavac, Marek (2022). stargazer: Well-Formatted Regression and Summary Statistics Tables.

 R package version 5.2.3. https://CRAN.R-project.org/package=stargazer 

library(help = "datasets")

# importing dataset
data(mtcars)
?stargazer
?mtcars

# summary stats for dataset
stargazer(mtcars,
          type = "text")

============================================
Statistic N   Mean   St. Dev.  Min     Max  
--------------------------------------------
mpg       32 20.091   6.027   10.400 33.900 
cyl       32  6.188   1.786     4       8   
disp      32 230.722 123.939  71.100 472.000
hp        32 146.688  68.563    52     335  
drat      32  3.597   0.535   2.760   4.930 
wt        32  3.217   0.978   1.513   5.424 
qsec      32 17.849   1.787   14.500 22.900 
vs        32  0.438   0.504     0       1   
am        32  0.406   0.499     0       1   
gear      32  3.688   0.738     3       5   
carb      32  2.812   1.615     1       8   
--------------------------------------------

Task 1: Bivariate Regression & Slope Calculation

# creating a bivariate regression for the data on the variables mpg & cyl
reg1 <- lm(data = mtcars,
           formula = mpg ~ cyl)

# printing the regression
reg1

Call:
lm(formula = mpg ~ cyl, data = mtcars)

Coefficients:
(Intercept)          cyl  
     37.885       -2.876  

# printing the summary stats for the regression (note the slope is -2.876)
summary(reg1)

Call:
lm(formula = mpg ~ cyl, data = mtcars)

Residuals:
    Min      1Q  Median      3Q     Max 
-4.9814 -2.1185  0.2217  1.0717  7.5186 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  37.8846     2.0738   18.27  < 2e-16 ***
cyl          -2.8758     0.3224   -8.92 6.11e-10 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 3.206 on 30 degrees of freedom
Multiple R-squared:  0.7262,    Adjusted R-squared:  0.7171 
F-statistic: 79.56 on 1 and 30 DF,  p-value: 6.113e-10

round(sum(reg1$residuals), 15)

[1] -4e-15

# calculating the slope using the formula to prove it is the same
beta1 <- cov(mtcars$mpg, mtcars$cyl)/var(mtcars$cyl)

# printing the slope (also -2.876)
beta1

[1] -2.87579

Creating Data to Import to Excel

# load packages
library(tidyquant)

Registered S3 method overwritten by 'quantmod':
  method            from
  as.zoo.data.frame zoo 

── Attaching core tidyquant packages ─────────────────────── tidyquant 1.0.11 ──
✔ PerformanceAnalytics 2.0.8      ✔ TTR                  0.24.4
✔ quantmod             0.4.28     ✔ xts                  0.14.1
── Conflicts ────────────────────────────────────────── tidyquant_conflicts() ──
✖ zoo::as.Date()                 masks base::as.Date()
✖ zoo::as.Date.numeric()         masks base::as.Date.numeric()
✖ PerformanceAnalytics::legend() masks graphics::legend()
✖ quantmod::summary()            masks base::summary()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(fpp3)

Registered S3 method overwritten by 'tsibble':
  method               from 
  as_tibble.grouped_df dplyr
── Attaching packages ──────────────────────────────────────────── fpp3 1.0.1 ──
✔ tibble      3.3.0     ✔ tsibble     1.1.6
✔ dplyr       1.1.4     ✔ tsibbledata 0.4.1
✔ tidyr       1.3.1     ✔ feasts      0.4.1
✔ lubridate   1.9.4     ✔ fable       0.4.1
✔ ggplot2     3.5.2     
── Conflicts ───────────────────────────────────────────────── fpp3_conflicts ──
✖ lubridate::date()    masks base::date()
✖ dplyr::filter()      masks stats::filter()
✖ dplyr::first()       masks xts::first()
✖ tsibble::index()     masks zoo::index()
✖ tsibble::intersect() masks base::intersect()
✖ tsibble::interval()  masks lubridate::interval()
✖ dplyr::lag()         masks stats::lag()
✖ dplyr::last()        masks xts::last()
✖ tsibble::setdiff()   masks base::setdiff()
✖ tsibble::union()     masks base::union()
✖ fable::VAR()         masks tidyquant::VAR()

Attaching package: 'fpp3'

The following object is masked from 'package:PerformanceAnalytics':

    prices

# assigning the stock prices data to an object
df_daily <- tq_get("META", 
       get = "stock.prices",
       from = "1992-01-01")

# aggregate to monthly
meta_data_monthly <- df_daily %>%
  mutate(month = yearmonth(date)
         ) %>%
  group_by(month) %>%
  summarise(adjusted = mean(adjusted)
            ) %>%
  as_tsibble(index = month)

# creating a file with the data
write.csv(x= meta_data_monthly, file= "meta_monthly_data.csv")

# assinging portions of the data to objects 
train <- meta_data_monthly[1:128,]   # 80% of og data
test <- meta_data_monthly[129:160,]  # 20% of og data

Task 2: Fitting Models

# fit models
models_meta <- model(
  train,
  ETS = ETS(adjusted),
  NAIVE = NAIVE(adjusted),
  SNAIVE = SNAIVE(adjusted),
)

# forecast
h <- nrow(test)
fc_meta <- forecast(models_meta, h = h)

# creating plot
autoplot(fc_meta, train) + labs(title = "My Forecast", xlab = "Time", ylab = "Adjusted Prices")

Note

Recommendations:

The fact that the adjusted stocks that we charted in Excel seems to be trending upwards, coupled with an positive (although small) slope and ETS model, makes me believe that investing in META could be a good idea.

However, although stock prices are accelerating upwards, the data also has trends of sharp downwards spikes such as in around 2023 and most recently in early 2025, so buying stock could come with a risk.