DataDiveWeek12

data <- read.csv("D:/2024-2025/FA24/Stats/mergedfile.csv")

Time Column Conversion

Task: Select a column in your dataset that encodes time (e.g., Date), and convert it to a proper date format in R.

library(lubridate)

## 
## Attaching package: 'lubridate'

## The following objects are masked from 'package:base':
## 
##     date, intersect, setdiff, union

data$Date <- as.Date(data$Date, format = "%Y-%m-%d")

Response Variable Selection

Task: Example filtering for a specific stock (e.g., Boeing):

boeing_data <- data[data$Symbol == "BA", ]

Create and Plot a Tsibble

Task: Create a tsibble object with the time and response variable, and generate time series plots for different time windows.

library(tsibble)

## Registered S3 method overwritten by 'tsibble':
##   method               from 
##   as_tibble.grouped_df dplyr

## 
## Attaching package: 'tsibble'

## The following object is masked from 'package:lubridate':
## 
##     interval

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, union

library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

# Example Data
data <- data.frame(
  Date = seq(as.Date("2020-01-01"), as.Date("2020-12-31"), by = "day"),
  Symbol = "BA",
  Adj.Close = runif(366, 100, 200)
)

# Ensure no issues
data <- data %>%
  arrange(Date) %>%
  distinct(Date, .keep_all = TRUE)

# Convert to tsibble
ts_data <- as_tsibble(data, index = Date)

library(ggplot2)

ggplot(ts_data, aes(x = Date, y = Adj.Close)) +
  geom_line() +
  ggtitle("Adjusted Close Price Over Time") +
  xlab("Date") +
  ylab("Adjusted Close Price")

Detect Trends Using Linear Regression

Task: Fit a linear regression model to identify trends

# Convert Date to numeric for regression
data$Date_numeric <- as.numeric(data$Date)

# Fit a linear regression model
lm_trend <- lm(Adj.Close ~ Date, data = ts_data)
summary(lm_trend)

## 
## Call:
## lm(formula = Adj.Close ~ Date, data = ts_data)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -53.168 -21.998  -1.241  20.708  50.103 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)  
## (Intercept) 433.55485  249.50056   1.738   0.0831 .
## Date         -0.01531    0.01353  -1.132   0.2584  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 27.34 on 364 degrees of freedom
## Multiple R-squared:  0.003508,   Adjusted R-squared:  0.0007703 
## F-statistic: 1.281 on 1 and 364 DF,  p-value: 0.2584

# Add trend line to plot
ggplot(ts_data, aes(x = Date, y = Adj.Close)) +
  geom_line() +
  geom_smooth(method = "lm", color = "blue") +
  ggtitle("Trend in Adjusted Close Prices") +
  xlab("Date") +
  ylab("Adjusted Close Price")

## `geom_smooth()` using formula = 'y ~ x'

Detecting Seasonality

Task: Apply smoothing techniques (e.g., moving averages) to identify seasonal patterns

library(fable)

## Warning: package 'fable' was built under R version 4.4.2

## Loading required package: fabletools

## Warning: package 'fabletools' was built under R version 4.4.2

smoothed <- ts_data %>%
  model(ETS(Adj.Close ~ season("A")))


library(forecast)

## Warning: package 'forecast' was built under R version 4.4.2

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

Acf(data$Adj.Close)

Pacf(data$Adj.Close)