About

Suzanna Linn is a Professor of Political Science and a Graduate Faculty member at Pennsylvania State University. She is also a Social Data Analytics C-SoDA Faculty Affiliate. Her research focuses on social data analytics within the context of political science, contributing to the understanding of social data through her academic work. She is affiliated with the Department of Political Science and the Social Data Analytics program, working at the 302 Pond Laboratory in University Park, PA. Her professional profile can be found on the university's website, and she is connected through her email sld8@psu.edu.

Research topics

• Computer science
• Information retrieval
• Environmental science
• Natural language processing
• Mathematics

Selected publications

• The Exogeneity Question(s)

  Oxford University Press eBooks · 2023-12-18

  book-chapter1st authorCorresponding

  Abstract Exogeneity assumptions are critical to applied time series analysis, but the topic is under-discussed and under-explained in econometric texts and often assumed away in applied work. The central misunderstanding is that there is not an exogeneity assumption; there are many exogeneity assumptions. Weak exogeneity, strong exogeneity, and super exogeneity are more or less likely to hold in different applications and the type of exogeneity that can be assumed tells us what we can learn from a given model. This chapter explains the importance of exogeneity in applied time series analysis, defines the different exogeneity concepts, highlights the different forms of time series analysis they are relevant for, and provides a strategy for evaluating the different exogeneity assumptions. Theory and data must support the exogeneity assumption necessary given the purpose of an analysis and analysts must be transparent in the claims they make about exogeneity.

  PublisherDOI

• The Distinctness of Social and Economic Identities

  SSRN Electronic Journal · 2022-01-01

  articleOpen accessSenior author
  PublisherDOI

• PPS volume 19 issue 3 Cover and Front matter

  Perspectives on Politics · 2021-09-01

  articleOpen access

  Founded in 1903, the American Political Science Association (APSA) is the leading professional organization for the study of political science and serves more than 11,000 members in over 100 countries. With a range of programs and services for individuals, departments, and institutions, APSA brings together political scientists from all fields of inquiry, regions, and occupational endeavors within and outside academe in order to deepen our understanding of politics, democracy, and citizenship throughout the world. The direct advancement of knowledge is at the core of APSA activities. We promote scholarly communication in political science through a variety of initiatives including publishing four distinguished

  PublisherOA PDFDOI

• figure7-appendix.tab

  Harvard Dataverse · 2020-01-01

  datasetOpen access
  PublisherDOI

• sentence_article_feature_space.py

  Harvard Dataverse · 2020-01-01

  datasetOpen access
  PublisherDOI

• LICENSE

  Harvard Dataverse · 2020-01-01

  datasetOpen access
  PublisherDOI

• 10-binning-analysis.R

  Harvard Dataverse · 2020-01-01

  datasetOpen access
  PublisherDOI

• Beyond the Unit Root Question: Uncertainty and Inference

  American Journal of Political Science · 2020-02-09 · 26 citations

  article

  Abstract A fundamental challenge facing applied time‐series analysts is how to draw inferences about long‐run relationships (LRR) when we are uncertain whether the data contain unit roots. Unit root tests are notoriously unreliable and often leave analysts uncertain, but popular extant methods hinge on correct classification. Webb, Linn, and Lebo (WLL; 2019) develop a framework for inference based on critical value bounds for hypothesis tests on the long‐run multiplier (LRM) that eschews unit root tests and incorporates the uncertainty inherent in identifying the dynamic properties of the data into inferences about LRRs. We show how the WLL bounds procedure can be applied to any fully specified regression model to solve this fundamental challenge, extend the results of WLL by presenting a general set of critical value bounds to be used in applied work, and demonstrate the empirical relevance of the LRM bounds procedure in two applications.

  PublisherDOI

• appendix-table3.html

  Harvard Dataverse · 2020-01-01

  datasetOpen access
  PublisherDOI

• data-1AC.tab

  Harvard Dataverse · 2020-01-01

  datasetOpen access
  PublisherDOI

Frequent coauthors

• Janet M. Box‐Steffensmeier

  The Ohio State University

  3618 shared

• Erik Bleich

  Friedrich-Alexander-Universität Erlangen-Nürnberg

  3607 shared

• Ben W. Ansell

  University of Oxford

  3606 shared

• Catherine Guisan

  University of Minnesota

  3605 shared

• Alexandra Filindra

  3604 shared

• Tamara Metz

  Reed College

  3604 shared

• John Ishiyama

  University of North Texas

  3603 shared

• David Lublin

  American University

  3602 shared

Labs

• Social Data AnalyticsPI