Overview

This is the central collostructional analysis website for performing collostructional analyses with the open source software tool and programming language R . I have just revised the script considerably; in particular, I now made *p*_FYE results available again at at a much higher speed than before; als KL-divergence output has now been added to every module. Information about what this function does and what its results mean can be found in my books Quantitative Corpus Linguistics with R: […]², Statistics for Linguistics with R: […]³, and Frequency, dispersion, association, and keyness: [...], but also many published collostructional analaysis.

And, at this point in time, I feel compelled to say that, while I am always happy to address questions/concerns about potential mistakes in the script, I cannot provide the kind of free research consulting that many people seem to think the existence of such a script promises. If your question is not about some technical aspect of the script, it is a question for your supervisor, your peers/colleagues, etc.

Background information

Stefanowitsch & Gries (2003 and 2005), Gries & Stefanowitsch (2004a and 2004b), Gries, Hampe, & Schönefeld (2005 and 2010), Gries (2015a, 2015b, 2019, 2022, and 2023, and my 2024 book)

My script Coll.analysis 4.2

Coll.analysis 4.2
readme.txt for Coll.analysis 4.2 (make sure you read this before you use it!)

Collexeme analysis

input file(s): 1.csv
output file(s): 1_out.csv

(Multiple) distinctive collexeme analysis

input file(s): 2a.csv, 2b.csv, 2c.csv
output file(s): 2a_out.csv, 2b_out.csv, 2c_out.csv

Covarying collexeme analysis

input file(s): 3.csv
output file(s): 3_out.csv