Simple Linear Regression

How to run

Install the TAF package from CRAN. Then open R in the taf-demo directory and run:

library(TAF)
taf.boot()
source.all()

Explore results

After running the analysis, we get plots and formatted tables in the final report folder, to paste into a report. The entire analysis is scripted and the results can be traced back to the initial data and through the analytical steps in the TAF scripts.

---

Quick intro to TAF

The initial data are declared in DATA.bib, which is processed by the taf.boot() function. During this boot procedure, each metadata entry is processed and the TAF system then makes the data available in the boot/data folder, where the data.R script will read it.

After the boot procedure, the data.R, model.R, output.R, and report.R scripts are run sequentially, each picking up files from previous steps. See the general TAF flow diagram.

The purpose of each script is indicated in the header comments:

Script	Purpose
data.R	Preprocess data
model.R	Run analysis
output.R	Extract results
report.R	Plots and tables

TAF provides a way to divide any analysis into these four main steps. In addition to supporting reproducibility, the standardized structure makes analyses more manageable and reviewable.

See also

• ICES TAF landing page
• ICES TAF documentation
• Tutorial video and annotated transcript
• TAF package help pages
• ICES TAF stock assessment examples:
  • 2015 Spotted ray in the Eastern Channel
  • 2015 Haddock in Icelandic waters
  • 2016 Plaice in the Eastern Channel
  • 2016 Cod in the North Sea
  • 2019 Sandeel in Area 6