I also enjoy reading and learning new things. Recently, I have expanded into quantitiative research methods whilst also learning the basics of the programming language R.

While the field of theoretical linguistics is definitely moving in the direction of quantitiative methods, there is still much resistance from generative linguists to adopt these methods. Consider me a recent convert who believes that the traditional way of doing theoretical linguistics and this relatively new way complement each other.

I am currently conducting an experiment which investigates the effects of different types of modifiers on indefinite specificational clause subjects. Follow this space as I provide updates on my findings as they come in.

There are many textbooks available for the linguist who wants to learn how to conduct experiments. In my own research, I have been studying quite a few of them, and in alphabetical order, I present them below with a brief review that I hope you will find useful.

This is a very comprehensive introduction to using R to analyze linguistic data. Requires you to have R running alongside while you are reading so that you can follow along. This book has a good chapter on mixed models which are all the rage now in quantitative linguistic research. I would not suggest starting with this book if you are a complete novice to statistics and R.

This book takes you through step-by-step on how to conduct a syntax experiment from formulating a good research question to creating a valid experiment design to analyzing the data that you get. Also has many sample questionnaires to look at. This book also provides a good discussion on how to create magnitude estimation questionnaires which are argued to be better way of extracting acceptability judgments. This book does not discuss R but uses an older version of Excel in order to do the statistical analysis. I would suggest this as one of the first books to read if you are just starting out.

I would recommend reading this general statistics book which teaches you how to use R before reading any of the other books here that have R as a primary focus. If you have never done statistics or used R before, this book is an excellent primer.

This book is comprehensive in terms of the types of descriptive and analytical statistics tools that are available out there. Gries does not deal too much with mixed models as he appears skeptical about their actual usefulness to linguistics research. Nonetheless, this book discusses a wide range of experiment designs and a particularly good feature of this book is that the author discusses how you would write up specific findings in a paper. However, I would not recommend starting with this book but it is something that you should get to if you want a good overview of the various analytical tools that are at the disposal of linguists.

This book is similar to Cowart (1997) is that it does not focus on the use of R to do the statistics although there are demarcated sections where the R code is discussed. The advantage this book has over Cowart's is that this book does not focus just on Syntax. There are also sections on how to do a phonetic, sociolinguistic, psycholinguistic, historical linguistic experiments. This book teaches the various analytical statistics methods (such as t-tests and ANOVA) by using actual linguistic experiment data which makes it easier for non-statistically minded linguists to follow along.

This is not so much a textbook but rather a collection of essays that discuss various aspects of quantitiative research in linguistics. I include this book in this list because this is one of the few books that I know that contains essays on data-collection methods which are not done through a questionnaire or survey. One of the essays in this book (Edley & Litosseliti) disucsses the strengths and weaknesses of using interviews and focus groups to collect data. While this is not a method I envision theoretical linguists to be too keen on, this is nonetheless a good discussion of the method.

This is a collection of essays that discuss experimental results. As such I would save this book for when you are comfortable with the various statistical tests such as ANOVAs and Chi-Square Tests. This book is good for when you are ready to start reading actual research findings on certain pragmatic-semantic phenomena. This book will acculturate you to reading these types of papers which can be very different from how general theoretical linguistics papers are structured. This can also give you an idea of how to write your own paper based on quantitative research when you are ready to..

This is a contemporary treatment that does not use R, but rather Excel. So one could consider this an updated version of Cowart (1997). Rasinger goes through experiment design and data analysis with detailed discussion of basic statistics as well as advanced statistical tools. This book also discusses simple and multiple regression but does not include a discussion of mixed models. If you are not interested in mixed models or R, you will find this book very useful.

I would save reading this for last alongside Meibauer and Steinbach (2011), for the same reasons. However, this book focuses on island effects and as such has a decidedly syntactic bent if you are so inclined.

This is an excellent document from Jon Sprouse that discusses data collection methods and includes a very comprehensive bibliography of the various issues that arise in quantitative linguistic research. A must read.

You can download R by following this link: https://cran.r-project.org/

For people new to statistics and programming (like me!), I would recommend

Powered by