𝔸 𝕊 𝕋 𝕊 𝔸 ⚡ applied statistical time series analysis

… more than just data … it’s a palindrome

… astsa includes data sets and scripts for analyzing time series in both the frequency and time domains including state space modeling as well as supporting the Springer text, Time Series Analysis and Its Applications: With R Examples and the Chapman & Hall text Time Series: A Data Analysis Approach using R.

Most scripts are designed to require minimal input to produce aesthetically pleasing output for ease of use in live demonstrations and course work.

We do not always push the latest version of the package to CRAN, but the latest working version of the package will always be at Github.

• The ROAD MAP is a good place to start to find all the links to the webpages for the texts and some help on using R for time series analysis.

• See the NEWS for further details about the state of the package, how to install the latest version, and the changelog.

• FUN WITH ASTSA has a list of data sets, scripts, and demonstrations of the capabilities of astsa … it’s more fun than high school. Also, the code for the examples are listed on GitHub:

  • The code for the graduate level text is here: TSA5.

  • The updated code for the data science text is here: TSDA2.

• Python

  • A python version of astsa may be found here.

  • The code in the first 3 chapters of the Springer text (ed 4) has been converted to Python here.

  • And a Python package that contains datasets from astsa is here.

⛔ WARNING: If loaded, the package dplyr may (and probably will) mask the base scripts filter and lag that a time series analyst uses often. An easy fix if you’re analyzing time series (or teaching a class) is to (tell students to) do the following if dplyr is going being used:

# [1] either detach it if it's loaded but no longer needed
detach(package:dplyr)  

# [2] or fix it yourself when loading dplyr 
# this is a great idea from https://stackoverflow.com/a/65186251
library(dplyr, exclude = c("filter", "lag"))   # load without the culprits
dlag    = dplyr::lag                           # then correct ... 
dfilter = dplyr::filter                        # ... the blunders
#  Now use `dlag` and `dfilter` in dplyr scripts and
# `lag` and `filter` can be use as originally intended

# [3] or just take back the commands
filter = stats::filter
lag    = stats::lag
# in this case, you can still use these for dplyr
dlag    = dplyr::lag     
dfilter = dplyr::filter 

😎 Also, consider that dplyr is a MUCH SLOWER version of data.table. So try data.table if you have to do data manipulation. AND, when you load data.table, there are ZERO masked warnings!!!