[PLing] Invitation to Book Launch "Statistics in Corpus Linguistics Research" by Sean Wallis
Mathilde Eveline Keizer
evelien.keizer at univie.ac.at
Thu Feb 24 10:12:30 CET 2022
**Apologies for double posting**
**
Dear colleagues,
You are cordially invited to a presentation by Sean Wallis (Survey of
English Usage, UCL), in which he will talk about his *book/Statistics in
Corpus Linguistics Research: a New Approach/ *(Routledge 2021).
The presentation will be on *17 March 2022, 15:00* and will take place
online. A link will be sent around a few days before the event.
Below you will find the abstract of the talk, as well as some
information about the book.
Best wishes,
Evelien Keizer (University of Vienna) & Gunther Kaltenböck (University
of Graz)
**
*Book Launch: /Statistics in Corpus Linguistics Research/ (Routledge
2021) - Sean Wallis, Survey of English Usage*
*Abstract:*
Why do people find 'statistics' difficult, and what can we do about
this? What are the best methods to use in linguistics, and are there
specific problems we must address when we apply statistical methods to
corpora?
In his new book, Sean Wallis argues there are several reasons why we
find statistical reasoning counter-intuitive. Probably the most
fundamental is that we do not "see" sampling uncertainty, we have to
count many events, which is often an impossible task. But with a
computer we can calculate and visualise uncertainty on the same scale as
an observed factor, which is what /confidence intervals/ do. Whereas
traditional approaches to confidence intervals were inconsistent with
statistical testing and sometimes obtained improbable events, modern
methods do not suffer these defects, and may be extended into a wide
range of testing environments.
Applying these methods to corpus linguistics requires us to address a
number of challenges and traditions. For example, conventionally, many
statistical approaches accepted linguistic variables with per (million)
word baselines. Yet these are clearly suboptimal, as most phenomena can
only occur in specific locations in a text. This is fundamentally a
linguistic analysis problem, which must be addressed through good
research design, well-considered queries and a careful review of data.
Other problems tackled in the book include questions of semasiological
analysis, learning how to engage in statistical argument to reduce
research workload and how to compensate for the fact that corpora are
random samples of texts, rather than random samples of independent
utterances, clauses or phrases.
*From the jacket:*
Traditional approaches to statistics focused on significance tests have
often been difficult for linguistics researchers to visualise.
/Statistics in Corpus Linguistics Research: A New Approach/ breaks these
significance tests down for researchers in corpus linguistics and
linguistic analysis, promoting a visual approach to understanding the
performance of tests with real data, and demonstrating how to derive new
intervals and tests.
Accessibly written for those with little to no mathematical or
statistical background, this book explains the mathematical fundamentals
of simple significance tests by relating them to confidence intervals.
With sample datasets and easy- to- read visuals, this book focuses on
practical issues, such as how to:
• pose research questions in terms of choice and constraint;
• employ confidence intervals correctly (including in graph plots);
• select optimal significance tests (and what results mean);
• measure the size of the effect of one variable on another;
• estimate the similarity of distribution patterns; and
• evaluate whether the results of two experiments significantly differ.
Appropriate for anyone from the student just beginning their career to
the seasoned researcher, this book is both a practical overview and
valuable resource.
--
Univ.-Prof. Dr. Evelien Keizer
Institut für Anglistik und Amerikanistik / Department of English
Universität Wien Campus d. Universität Wien
Spitalgasse 2-4/Hof 8.3
1090 Wien
Austria
Homepage:https://anglistik.univie.ac.at/staff/staff/keizer/
-------------- n�chster Teil --------------
Ein Dateianhang mit HTML-Daten wurde abgetrennt...
URL: <https://lists.univie.ac.at/pipermail/pling/attachments/20220224/e7519011/attachment.html>
More information about the PLing
mailing list