Apply it to your data 10

# for Core packages
library(tidyverse)

## Warning: package 'tidyverse' was built under R version 4.2.3

## Warning: package 'ggplot2' was built under R version 4.2.3

## Warning: package 'tibble' was built under R version 4.2.3

## Warning: package 'tidyr' was built under R version 4.2.3

## Warning: package 'readr' was built under R version 4.2.3

## Warning: package 'purrr' was built under R version 4.2.3

## Warning: package 'dplyr' was built under R version 4.2.3

## Warning: package 'stringr' was built under R version 4.2.3

## Warning: package 'forcats' was built under R version 4.2.3

## Warning: package 'lubridate' was built under R version 4.2.3

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.2     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── 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

# for financial analysis
library(tidyquant)

## Loading required package: PerformanceAnalytics
## Loading required package: xts
## Loading required package: zoo
## 
## Attaching package: 'zoo'
## 
## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric
## 
## 
## Attaching package: 'xts'
## 
## The following objects are masked from 'package:dplyr':
## 
##     first, last
## 
## 
## Attaching package: 'PerformanceAnalytics'
## 
## The following object is masked from 'package:graphics':
## 
##     legend
## 
## Loading required package: quantmod
## Loading required package: TTR
## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo

# for times series
library(timetk)

## Warning: package 'timetk' was built under R version 4.2.3

Goal: Apply Matt Dancho’s tutorial to state unemployment initial claims of New England states.

The following is the replication of Matt Dancho’s tutorial on this page

start_date <- "1989-01-01"

symbols_txt <- c("CTICLAIMS", # Connecticut
                 "MEICLAIMS", # Maine
                 "MAICLAIMS", # Massachusetts
                 "NHICLAIMS", # New Hampshire
                 "RIICLAIMS", # Rhode Island
                 "VTICLAIMS") # Vermont

claims_tbl <- tq_get(symbols_txt, get = "economic.data", from = start_date) %>%
    mutate(symbol = fct_recode(symbol,
                               "Connecticut"   = "CTICLAIMS",
                               "Maine"         = "MEICLAIMS",
                               "Massachusetts" = "MAICLAIMS",
                               "New Hampshire" = "NHICLAIMS",
                               "Rhode Island"  = "RIICLAIMS",
                               "Vermont"       = "VTICLAIMS")) %>%
    rename(claims = price)

Plotting time series

claims_tbl %>%
  plot_time_series(.date_var = date, .value = claims)

Box plots

claims_tbl %>% count(symbol)

## # A tibble: 6 × 2
##   symbol            n
##   <fct>         <int>
## 1 Connecticut    1840
## 2 Massachusetts  1840
## 3 Maine          1840
## 4 New Hampshire  1840
## 5 Rhode Island   1840
## 6 Vermont        1840

claims_tbl %>%
  filter_by_time(.date_var = date, .end_date = "2021") %>%
  group_by(symbol) %>%
  plot_time_series_boxplot(.date_var = date,
                           .value    = claims,
                           .period   = "1 year",
                           .facet_ncol = 2)

Regression plots

claims_tbl %>%
  group_by(symbol) %>%
  plot_time_series_regression(.date_var = date,
                              .facet_ncol = 2,
                              .formula = log(claims) ~ as.numeric(date) + month(date, label = TRUE),
                              .show_summary = FALSE)

Plotting Seasonality and Correlation

Correlation Plots

Seasonality

claims_tbl %>% 
    plot_seasonal_diagnostics(date, claims)

STL Diagnostics

claims_tbl %>%
    group_by(symbol) %>%
    plot_stl_diagnostics(
        date, claims,
        .frequency = "auto", .trend = "auto",
        .feature_set = c("observed", "season", "trend", "remainder"))

## frequency = 13 observations per 1 quarter

## trend = 53 observations per 1 year

## frequency = 13 observations per 1 quarter

## trend = 53 observations per 1 year

## frequency = 13 observations per 1 quarter

## trend = 53 observations per 1 year

## frequency = 13 observations per 1 quarter

## trend = 53 observations per 1 year

## frequency = 13 observations per 1 quarter

## trend = 53 observations per 1 year

## frequency = 13 observations per 1 quarter

## trend = 53 observations per 1 year

Time Series Data Wrangling

Summarize by Time

Filter By Time

Padding Data

Sliding (Rolling) Calculations