@book{MunzertRubbaMeissneretal., author = {Munzert, Simon and Rubba, Christian and Meißner, Peter and Nyhuis, Dominic}, title = {Automated Data Collection with R: A Practical Guide to Web Scraping and Text Mining}, publisher = {John Wiley \& Sons}, address = {Chichester}, isbn = {978-1-118-83481-7}, doi = {10.1002/9781118834732}, publisher = {Hertie School}, pages = {474}, abstract = {A hands on guide to web scraping and text mining for both beginners and experienced users of R Introduces fundamental concepts of the main architecture of the web and databases and covers HTTP, HTML, XML, JSON, SQL. Provides basic techniques to query web documents and data sets (XPath and regular expressions). An extensive set of exercises are presented to guide the reader through each technique. Explores both supervised and unsupervised techniques as well as advanced techniques such as data scraping and text management. Case studies are featured throughout along with examples for each technique presented. R code and solutions to exercises featured in the book are provided on a supporting website.}, language = {en} } @article{MunzertJankinal, author = {Munzert, Simon and Jankin, Slava and al., et}, title = {The 2019 report of The Lancet Countdown on health and climate change: ensuring that the health of a child born today is not defined by a changing climate}, series = {The Lancet}, volume = {394}, journal = {The Lancet}, number = {10211}, doi = {10.1016/S0140-6736(19)32596-6}, pages = {1836 -- 1878}, abstract = {The Lancet Countdown is an international, multidisciplinary collaboration, dedicated to monitoring the evolving health profile of climate change, and providing an independent assessment of the delivery of commitments made by governments worldwide under the Paris Agreement.}, language = {en} } @article{StoetzerNeunhoefferGschwendetal., author = {St{\"o}tzer, Lukas F. and Neunhoeffer, Marcel and Gschwend, Thomas and Munzert, Simon and Sternberg, Sebastian}, title = {Forecasting Elections in Multiparty Systems: A Bayesian Approach Combining Polls and Fundamentals}, series = {Political Analysis}, volume = {27}, journal = {Political Analysis}, number = {2}, doi = {10.1017/pan.2018.49}, pages = {255 -- 262}, abstract = {We offer a dynamic Bayesian forecasting model for multiparty elections. It combines data from published pre-election public opinion polls with information from fundamentals-based forecasting models. The model takes care of the multiparty nature of the setting and allows making statements about the probability of other quantities of interest, such as the probability of a plurality of votes for a party or the majority for certain coalitions in parliament. We present results from two ex ante forecasts of elections that took place in 2017 and are able to show that the model outperforms fundamentals-based forecasting models in terms of accuracy and the calibration of uncertainty. Provided that historical and current polling data are available, the model can be applied to any multiparty setting.}, language = {en} } @article{SelbMunzert, author = {Selb, Peter and Munzert, Simon}, title = {Examining a Most Likely Case for Strong Campaign Effects: Hitler's Speeches and the Rise of the Nazi Party, 1927-1933}, series = {American Political Science Review}, volume = {112}, journal = {American Political Science Review}, number = {4}, doi = {10.1017/S0003055418000424}, pages = {1050 -- 1066}, abstract = {Hitler's rise to power amidst an unprecedented propaganda campaign initiated scholarly interest in campaign effects. To the surprise of many, empirical studies often found minimal effects. The predominant focus of early work was on U.S. elections, though. Nazi propaganda as the archetypal and, in many ways, most likely case for strong effects has rarely been studied. We collect extensive data about Hitler's speeches and gauge their impact on voter support at five national elections preceding the dictatorship. We use a semi-parametric difference-in-differences approach to estimate effects in the face of potential confounding due to the deliberate scheduling of events. Our findings suggest that Hitler's speeches, while rationally targeted, had a negligible impact on the Nazis' electoral fortunes. Only the 1932 presidential runoff, an election preceded by an extraordinarily short, intense, and one-sided campaign, yielded positive effects. This study questions the importance of charismatic leaders for the success of populist movements.}, language = {en} } @article{GoebelMunzert, author = {G{\"o}bel, Sascha and Munzert, Simon}, title = {Political Advertising on the Wikipedia Marketplace of Information}, series = {Social Science Computer Review}, volume = {36}, journal = {Social Science Computer Review}, number = {2}, doi = {10.1177/0894439317703579}, pages = {157 -- 175}, abstract = {We point to a popular yet underresearched platform of political information, the online encyclopedia Wikipedia. Considering the supply side of the marketplace, we argue that personal biographies on the platform are an attractive medium for politicians to enhance their appearance. We trace changes to biographies coming from the parliament using data that cover the entire edit histories for biographies on all German members of parliament for the three last legislative periods. Our findings show editing of personal biographies to be a persistent phenomenon. Moreover, type, timing, and driving factors of editing behavior highlight the importance politicians' attribute to Wikipedia for pursuing reelection. Our results speak to the domains of political professionalization, voting behavior, and the general measurement of communicative patterns.}, language = {en} } @article{MunzertStoetzerGschwendetal., author = {Munzert, Simon and St{\"o}tzer, Lukas F. and Gschwend, Thomas and Neunhoeffer, Marcel and Sternberg, Sebastian}, title = {Zweitstimme.org. Ein strukturell-dynamisches Vorhersagemodell f{\"u}r Bundestagswahlen.}, series = {Politische Vierteljahresschrift}, volume = {58}, journal = {Politische Vierteljahresschrift}, number = {3}, issn = {0032-3470 (print); 1862-2860 (online)}, doi = {10.5771/0032-3470-2017-3-418}, pages = {418 -- 441}, abstract = {We present results of an ex-ante forecast of party-specific vote shares at the German Federal Election 2017. To that end, we combine data from published trial heat polls with structural information. The model takes care of the multi-party nature of the setting and allows making statements about the probability of certain events, such as the plurality of votes for a party or the majority for coalition options in parliament. The forecasts of our model are continuously being updated on the platform zweitstimme.org. The value of our approach goes beyond the realms of academia: We equip journalists, political pundits, and ordinary citizens with information that can help make sense of the parties' latent support and ultimately make voting decisions better informed.}, language = {de} } @article{Munzert, author = {Munzert, Simon}, title = {Forecasting elections at the constituency level: A correction-combination procedure}, series = {International Journal of Forecasting}, volume = {33}, journal = {International Journal of Forecasting}, number = {2}, doi = {10.1016/j.ijforecast.2016.12.001}, pages = {467 -- 481}, abstract = {Scholarly efforts to forecast parliamentary elections have targeted the national level predominantly, disregarding the outcomes of constituency races. In doing so, they have frequently failed to account for systematic bias in the seats-votes curve, and been unable to provide candidates and campaign strategists with constituency-level information. On the other hand, existing accounts of constituency-level election forecasting suffer from data sparsity, leading to a lack of precision. This paper proposes a correction-combination procedure that allows for the correction of individual constituency-level forecast models for election-invariant bias, then combines these models based on their past performances. I demonstrate the use of this procedure through out-of-sample forecasts of 299 district races at the 2013 German federal election.}, language = {en} } @article{MunzertSelb, author = {Munzert, Simon and Selb, Peter}, title = {Measuring Political Knowledge in Web-Based Surveys: An Experimental Validation of Visual Versus Verbal Instruments}, series = {Social Science Computer Review}, volume = {25}, journal = {Social Science Computer Review}, number = {2}, doi = {10.1177/0894439315616325}, pages = {167 -- 183}, abstract = {Does the opportunity to deliver visual instead of verbal stimuli of political knowledge to respondents in web-based surveys make a difference in terms of data quality? For instance, does the presentation of visual knowledge items reduce cheating, that is, looking up the answer via the Web? And do visual and verbal stimuli capture the same underlying construct? To test whether the use of visuals to measure political knowledge effectively makes a difference, we administer a question form experiment in an online survey of the German Longitudinal Election Study. Respondents are randomly assigned to one of two question formats—visual or verbal—and are asked to solve a set of eight questions on political leaders and their offices. The instruments are validated based on nonparametric item response theory and analyses of response latency. While there is no clear evidence for cheating behavior under either of the conditions, both instruments form strong knowledge scales. Results from a regression analysis indicate that the scales provide measures of closely related but not identical concepts.}, language = {en} } @article{SelbMunzert, author = {Selb, Peter and Munzert, Simon}, title = {Forecasting the 2013 German Bundestag Election Using Many Polls and Historical Election Results}, series = {German Politics}, volume = {25}, journal = {German Politics}, number = {1}, doi = {10.1080/09644008.2015.1121454}, pages = {73 -- 83}, abstract = {This article reports on an attempt to forecast the outcome of the 2013 election to the German Bundestag. In contrast to the predominant academic approach to forecast incumbent vote shares from measures of government popularity, economic conditions and other fundamental variables, we entirely relied on data from published trial heat polls. Opposite to common practice in the news media, we did not take isolated polls as election forecasts in their own right. Instead, we used historical data to assess empirically the relationship between polls and election outcomes, and combined extrapolations from current polls in a Bayesian manner. The forecast was published one month ahead of the election. The retrospective evaluation of our method was added after the election. While our method is parsimonious and provides a large lead time, the performance at the 2013 election was underwhelming. We offer additional suggestions how the approach can be improved in future scenarios.}, language = {en} } @article{HerrmannMunzertSelb, author = {Herrmann, Michael and Munzert, Simon and Selb, Peter}, title = {Determining the effect of strategic voting on election results}, series = {Journal of the Royal Statistical Society (Series A)}, volume = {179}, journal = {Journal of the Royal Statistical Society (Series A)}, number = {2}, doi = {10.1111/rssa.12130}, pages = {583 -- 605}, abstract = {Speculations about whether strategic voting made a difference to the outcome of an election regularly whip up the passions of pundits, party strategists, electoral reformers and scholars alike. Yet, research on strategic voting's political effect has been hampered by the scarcity of data on district level party preferences. We propose the use of Bayesian small area estimation to predict district level preferences from just a handful of survey responses per district and comparing these predictions against election results to estimate how many voters switched sides in each district. We apply the approach to estimate how many seats changed hands as a result of strategic voting at the 1997 and 2001 UK general elections. Despite similar rates of strategic voting in both elections, the number of seats that were affected was markedly greater in 1997. Interestingly, the Liberal Democrats turn out to win the most seats because of strategic voting. We also estimate how many votes went in the 'wrong' direction—away from otherwise viable candidates. We validate our results by using journalistic sources and compare them with previous published estimates.}, language = {en} } @article{BernauerMunzert, author = {Bernauer, Julian and Munzert, Simon}, title = {Loyal to the Game? Strategic Policy Representation in Mixed Electoral Systems}, series = {Representation. Journal of Representative Democracy}, volume = {50}, journal = {Representation. Journal of Representative Democracy}, number = {1}, doi = {10.1080/00344893.2014.902221}, pages = {83 -- 97}, abstract = {In Germany's compensatory mixed electoral system, alternative electoral routes lead into parliament. We study the relationship between candidates' electoral situations across both tiers and policy representation, fully accounting for candidate, party and district preferences in a multi-actor constellation and the exact electoral incentives for candidates to represent either the party or the district. The results (2009 Bundestag election data) yield evidence of an interactive effect of closeness of the district race and list safety on candidates' positioning between their party and constituency.}, language = {en} } @article{MunzertBauer, author = {Munzert, Simon and Bauer, Paul}, title = {Political Depolarization in German Public Opinion, 1980-2010}, series = {Political Science Research and Methods}, volume = {1}, journal = {Political Science Research and Methods}, number = {1}, doi = {10.1017/psrm.2013.7}, pages = {67 -- 89}, abstract = {Little is known about political polarization in German public opinion. This article offers an issue-based perspective and explores trends of opinion polarization in Germany. Public opinion polarization is conceptualized and measured as alignment of attitudes. Data from the German General Social Survey (1980 to 2010) comprise attitudes towards manifold issues, which are classified into several dimensions. This study estimates multilevel models that reveal general and issue- as well as dimension-specific levels and trends in attitude alignment for both the whole German population and sub-groups. It finds that public opinion polarization has decreased over the last three decades in Germany. In particular, highly educated and more politically interested people have become less polarized over time. However, polarization seems to have increased in attitudes regarding gender issues. These findings provide interesting contrasts to existing research on the American public.}, language = {en} } @article{SelbHerrmannMunzertetal., author = {Selb, Peter and Herrmann, Michael and Munzert, Simon and Sch{\"u}bel, Thomas and Shikano, Susumu}, title = {Forecasting runoff elections using candidate evaluations from first round exit polls}, series = {International Journal of Forecasting}, volume = {29}, journal = {International Journal of Forecasting}, number = {4}, doi = {10.1016/j.ijforecast.2013.02.001}, pages = {541 -- 547}, abstract = {We draw attention to a simple yet underappreciated way of forecasting the outcomes of elections involving two rounds of voting: surveying the voters' candidate evaluations in first round exit polls, poststratifying the sample proportions of reported votes to official first round election returns, and redistributing the votes for eliminated competitors according to their supporters' lower-order preferences among the viable alternatives in round two. We argue that the approach is likely to outperform standard pre-election surveys, due to its better coverage and reduced measurement error, and the possibility of correcting for sample selection. We set out the practical details of the method and demonstrate its usefulness by employing a recent German mayoral election as an empirical case. Thirteen candidates were competing in the first round, while there were six candidates in the decisive second round. The runoff result was forecast two weeks in advance with an average absolute error of less than one percentage point.}, language = {en} } @article{SelbMunzert, author = {Selb, Peter and Munzert, Simon}, title = {Voter overrepresentation, vote misreporting, and turnout bias in postelection surveys}, series = {Electoral Studies}, volume = {32}, journal = {Electoral Studies}, number = {1}, doi = {10.1016/j.electstud.2012.11.004}, pages = {186 -- 196}, abstract = {Figures from postelection surveys often grossly overestimate election turnout. Two distinct phenomena are responsible for this gap: overrepresentation of actual voters and vote misreporting by actual nonvoters among survey respondents. Previous accounts of turnout bias are inconclusive in that they either focus on a single component, or fail to separate between the two. In this paper, we formally decompose turnout bias in election surveys into its constituent parts, assess their empirical prevalence and heterogeneity using an extensive collection of 49 vote validation studies from six countries, and employ Bayesian meta regression techniques to account for cross-study differences. Our results indicate that both election and survey characteristics such as actual voter turnout and survey response rates differentially affect the components of turnout bias. We conclude with a discussion of the threats and potentials of our findings for survey-based comparative electoral research.}, language = {en} } @article{SelbMunzert, author = {Selb, Peter and Munzert, Simon}, title = {Estimating Constituency Preferences from Sparse Survey Data Using Auxiliary Geographic Information}, series = {Political Analysis}, volume = {19}, journal = {Political Analysis}, number = {4}, doi = {10.1093/pan/mpr034}, pages = {455 -- 470}, abstract = {Measures of constituency preferences are of vital importance for the study of political representation and other research areas. Yet, such measures are often difficult to obtain. Previous survey-based estimates frequently lack precision and coverage due to small samples, rely on questionable assumptions or require detailed auxiliary information about the constituencies' population characteristics. We propose an alternative Bayesian hierarchical approach that exploits minimal geographic information readily available from digitalized constituency maps. If at hand, social background data are easily integrated. To validate the method, we use national polls and district-level results from the 2009 German Bundestag election, an empirical case for which detailed structural information is missing.}, language = {en} } @article{Munzert, author = {Munzert, Simon}, title = {Big Data in der Forschung! Big Data in der Lehre? Ein Vorschlag zur Erweiterung der bestehenden Methodenausbildung}, series = {Zeitschrift f{\"u}r Politikwissenschaft}, volume = {24}, journal = {Zeitschrift f{\"u}r Politikwissenschaft}, number = {1-2}, issn = {1430-6387}, doi = {10.5771/1430-6387-2014-1-2-205}, pages = {207 -- 222}, language = {de} } @incollection{MunzertNyhuis, author = {Munzert, Simon and Nyhuis, Dominic}, title = {Die Nutzung von Webdaten in den Sozialwissenschaften}, series = {Handbuch Methoden der Politikwissenschaft}, booktitle = {Handbuch Methoden der Politikwissenschaft}, editor = {Wagemann, Claudius and Goerres, Achim and Siewert, Markus}, publisher = {Springer}, address = {Heidelberg}, isbn = {978-3-658-16937-4}, doi = {10.1007/978-3-658-16937-4_22-1}, publisher = {Hertie School}, abstract = {Das Kapitel bietet einen {\"U}berblick der Webdatensammlung f{\"u}r die sozialwissenschaftliche Forschung. Zu diesem Zweck wird nach einem praktischen Beispiel eine {\"U}bersicht der grundlegenden Webtechnologien geboten, um in einem zweiten Schritt einen vertiefenden Blick auf das Web Scraping einerseits und Programmierschnittstellen andererseits zu werfen. Die praktische Umsetzung der Webdatensammlung wird mit Code-Beispielen in der Programmiersprache R illustriert. Nach der praktischen Einf{\"u}hrung werden Potenziale und Herausforderungen der webbasierten Sozialwissenschaft am Beispiel ausgew{\"a}hlter Anwendungen aus der aktuellen Forschungsliteratur diskutiert. Abschließend werden verschiedene technische und konzeptionelle Problemstellungen der Webdatensammlung dargelegt und einige weiterf{\"u}hrende Literaturhinweise f{\"u}r die vertiefte Auseinandersetzung mit den Themen des Kapitels geboten.}, language = {de} } @incollection{Munzert, author = {Munzert, Simon}, title = {Auf dem Weg zu einer fundierten Softwareausbildung in der Politikwissenschaft}, series = {Computational Social Science. Die Analyse von Big Data}, booktitle = {Computational Social Science. Die Analyse von Big Data}, editor = {Bl{\"a}tte (et al.), Adreas}, publisher = {Nomos}, address = {Baden-Baden}, isbn = {ISBN print: 978-3-8487-4393-3, ISBN online: 978-3-8452-8655-6}, doi = {10.5771/9783845286556-379}, publisher = {Hertie School}, pages = {379 -- 402}, language = {de} } @incollection{ShikanoMunzertSchuebeletal., author = {Shikano, Susumu and Munzert, Simon and Sch{\"u}bel, Thomas and Herrmann, Michael and Selb, Peter}, title = {Eine empirische Sch{\"a}tzmethode f{\"u}r Valenz-Issues auf der Basis der Kandidatenbeurteilung am Beispiel der Konstanzer Oberb{\"u}rgermeisterwahl 2012}, series = {Jahrbuch f{\"u}r Handlungs- und Entscheidungstheorie}, booktitle = {Jahrbuch f{\"u}r Handlungs- und Entscheidungstheorie}, editor = {Linhart, Eric and Kittel, Bernhard and B{\"a}chtiger, Andr{\´e}}, publisher = {Springer}, address = {Wiesbaden}, isbn = {978-3-658-05007-8}, doi = {10.1007/978-3-658-05008-5_4}, publisher = {Hertie School}, pages = {113 -- 131}, abstract = {Bei der Entwicklung der r{\"a}umlichen Modelle des Parteienwettbewerbs spielt die Valenz eine wichtige Rolle. Trotz der theoretischen Relevanz bleibt die Mess- und Sch{\"a}tzmethode der Valenz unterentwickelt. Angesichts dieser Forschungsl{\"u}cke schl{\"a}gt dieser Beitrag ein statistisches Modell vor, das die gleichzeitige Sch{\"a}tzung der Kandidatenpositionen und der Valenz erm{\"o}glicht. Ein wichtiger Vorzug dieses Modells liegt darin, dass man nur die Kandidatenbeurteilungen per Skalometer ben{\"o}tigt, der in den meisten Umfragedaten verf{\"u}gbar ist. Dieses Modell wird auf Daten angewendet, die in Rahmen der Konstanzer Oberb{\"u}rgermeisterwahl 2012 erhoben wurden.}, language = {de} } @misc{Munzert, author = {Munzert, Simon}, title = {XML and Web Technologies for Data Sciences with R}, series = {Journal of Statistical Software}, volume = {81}, journal = {Journal of Statistical Software}, doi = {10.18637/jss.v061.b01}, language = {de} } @techreport{MunzertPapoutsiNowak, type = {Working Paper}, author = {Munzert, Simon and Papoutsi, Myrto and Nowak, Holger}, title = {Ein Jahr digitale Kontaktpersonennachverfolgung mit der Corona-Warn-App}, doi = {10.48462/opus4-3999}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:b1570-opus4-39994}, pages = {16}, abstract = {Nachdem es zwischenzeitlich ruhig um die Corona-Warn-App geworden war, nahm die Diskussion um digitale Kontaktpersonennachverfolgung im Fr{\"u}hjahr 2021 wieder Fahrt auf. Die Corona-Warn-App wurde mit lange erwarteten Zusatzfeatures zur Eventregistrierung und Erfassung von Schnelltestergebnissen ausgestattet, w{\"a}hrend die Luca-App aufgrund von Sicherheitsl{\"u}cken und Datenschutzm{\"a}ngeln zunehmend in die Kritik geriet. In unserem Bericht dokumentieren wir, wie popul{\"a}r diese Apps mittlerweile in der deutschen Bev{\"o}lkerung sind. Nach wie vor gilt: F{\"u}r die Wirksamkeit dieser Technologien ist die breitfl{\"a}chige Nutzung in der Bev{\"o}lkerung entscheidend. In unserer Erhebung, einem Smartphone-basierten Nutzertracking, das zwischen dem 19. Mai und 01. Juni 2021 durchgef{\"u}hrt wurde, zeigt sich nach wie vor deutliche Unterschiede in der Nutzung der beiden bekanntesten Apps - Corona-Warn-App und Luca-App. Im Vergleich zur vorherigen Befragung (M{\"a}rz/April 2021) sind jedoch einige Verschiebungen beobachtbar: Die Luca-App ist bekannter geworden, gleichzeitig steigt die Sorge um den Datenschutz der App allenfalls leicht an. Bei vielen Befragten besteht nach wie vor große Unklarheit {\"u}ber die Unterschiede in Funktionsweise und Zweck dieser Apps.}, language = {de} }