Bayesian Analysis

2009 ◽  
Author(s):  
Andrew D. Martin
Keyword(s):  
Social Sciences ◽  
Monte Carlo ◽  
Political Science ◽  
Bayesian Methods ◽  
Change Point ◽  
Prior Information ◽  
Mcmc Methods ◽  
The Social ◽  
Change Point Models ◽  
The Bayesian Approach

This article surveys modern Bayesian methods of estimating statistical models. It first provides an introduction to the Bayesian approach for statistical inference, contrasting it with more conventional approaches. It then explains the Monte Carlo principle and reviews commonly used Markov Chain Monte Carlo (MCMC) methods. This is followed by a practical justification for the use of Bayesian methods in the social sciences, and a number of examples from the literature where Bayesian methods have proven useful are shown. The article finally provides a review of modern software for Bayesian inference, and a discussion of the future of Bayesian methods in political science. One area ripe for research is the use of prior information in statistical analyses. Mixture models and those with discrete parameters (such as change point models in the time-series context) are completely underutilized in political science.

A Note on “Public Policy”

1973 ◽  
Vol 6 (4) ◽  
pp. 661-664 ◽  
Author(s):  
Robert Vaison
Keyword(s):  
Social Sciences ◽  
Public Policy ◽  
Political Science ◽  
Public Administration ◽  
Government Policy ◽  
Policy Making ◽  
The Social ◽  
Political Studies ◽  
Policy Analysts ◽  
Government Body

Normally in political studies the term public policy is construed to encompass the societally binding directives issued by a society's legitimate government. We usually consider government, and only government, as being able to “authoritatively allocate values.” This common conception pervades the literature on government policy-making, so much so that it is hardly questioned by students and practitioners of political science. As this note attempts to demonstrate, some re-thinking seems to be in order. For purposes of analysis in the social sciences, this conceptualization of public policy tends to obscure important realities of modern corporate society and to restrict unnecessarily the study of policy-making. Public policy is held to be public simply and solely because it originates from a duly legitimated government, which in turn is held to have the authority (within specified limits) of formulating and implementing such policy. Public policy is public then, our usual thinking goes, because it is made by a body defined somewhat arbitrarily as “public”: a government or some branch of government. All other policy-making is seen as private; it is not public (and hence to lie essentially beyond the scope of the disciplines of poliitcal science and public administration) because it is duly arrived at by non-governmental bodies. Thus policy analysts lead us to believe that public policy is made only when a government body acts to consider some subject of concern, and that other organizations are not relevant to the study of public policy.

Political Science and Public Administration: A Note on the State of the Union

1952 ◽  
Vol 46 (3) ◽  
pp. 660-676 ◽  
Author(s):  
Roscoe C. Martin
Keyword(s):  
Social Sciences ◽  
Political Science ◽  
Public Administration ◽  
Russell Sage Foundation ◽  
Special Study ◽  
Woodrow Wilson ◽  
State Of The Union ◽  
The Social ◽  
Original Essay ◽  
The Subject

By tradition public administration is regarded as a division of political science. Woodrow Wilson set the stage for this concept in his original essay identifying public administration as a subject worthy of special study, and spokesmen for both political science and public administration have accepted it since. Thus Leonard White, in his 1930 article on the subject in the Encyclopedia of the Social Sciences, recognizes public administration as “a branch of the field of political science.” Luther Gulick follows suit, observing in 1937 that “Public administration is thus a division of political science ….” So generally has this word got around that it has come to the notice of the sociologists, as is indicated in a 1950 report of the Russell Sage Foundation which refers to “political science, including public administration….” “Pure” political scientists and political scientists with a public administration slant therefore are not alone in accepting this doctrine, which obviously enjoys a wide and authoritative currency.But if public administration is reckoned generally to be a child of political science, it is in some respects a strange and unnatural child; for there is a feeling among political scientists, substantial still if mayhap not so widespread as formerly, that academicians who profess public administration spend their time fooling with trifles. It was a sad day when the first professor of political science learned what a manhole cover is! On their part, those who work in public administration are likely to find themselves vaguely resentful of the lack of cordiality in the house of their youth.

scholarly journals Bayesian Metric Multidimensional Scaling

2013 ◽  
Vol 21 (1) ◽  
pp. 125-140 ◽  
Author(s):  
Ryan Bakker ◽  
Keith T. Poole
Keyword(s):  
Monte Carlo ◽  
Markov Chain ◽  
Bayesian Methods ◽  
Optimal Solution ◽  
Full Rank ◽  
Mcmc Methods ◽  
Ratio Scale ◽  
Posterior Distributions ◽  
Point Estimates ◽  
Inflection Points

In this article, we show how to apply Bayesian methods to noisy ratio scale distances for both the classical similarities problem as well as the unfolding problem. Bayesian methods produce essentially the same point estimates as the classical methods, but are superior in that they provide more accurate measures of uncertainty in the data. Identification is nontrivial for this class of problems because a configuration of points that reproduces the distances is identified only up to a choice of origin, angles of rotation, and sign flips on the dimensions. We prove that fixing the origin and rotation is sufficient to identify a configuration in the sense that the corresponding maxima/minima are inflection points with full-rank Hessians. However, an unavoidable result is multiple posterior distributions that are mirror images of one another. This poses a problem for Markov chain Monte Carlo (MCMC) methods. The approach we take is to find the optimal solution using standard optimizers. The configuration of points from the optimizers is then used to isolate a single Bayesian posterior that can then be easily analyzed with standard MCMC methods.

Agency, Structure and Causality in Political Science: A Comment on Sibeon

Politics ◽  
2002 ◽  
Vol 22 (1) ◽  
pp. 17-23 ◽  
Author(s):  
Paul A. Lewis
Keyword(s):  
Social Sciences ◽  
Social Structure ◽  
Political Science ◽  
Critical Realism ◽  
Explanatory Power ◽  
Recent Contribution ◽  
Ontological Commitments ◽  
Political Analysis ◽  
The Social ◽  
Ontological Turn

Researchers in political science are devoting increasing attention to the ontological commitments of their theories – that is, to what those theories presuppose about the nature of the political world. This article focuses on a recent contribution to this ‘ontological turn’ in political science ( Sibeon, 1999 ). Tensions are identified in Sibeon's account of the causal interplay between agency and social structure. It is argued that these tensions can be resolved by reflecting explicitly on ontological issues, in particular the causal efficacy of social structure, using a particular approach to the philosophy of the social sciences known as critical realism. The value of such reflection for the explanatory power of political analysis is highlighted.

Political Science as a Discipline: A Statement by the Committee on Standards of Instruction of the American Political Science Association

1962 ◽  
Vol 56 (2) ◽  
pp. 417-421 ◽  
Author(s):  
Gabriel A. Almond ◽  
Eric C. Bellquist ◽  
Joseph M. Ray ◽  
John P. Roche ◽  
Irvin Stewart ◽  
...  
Keyword(s):  
Social Sciences ◽  
Social Psychology ◽  
Political Science ◽  
Human Experience ◽  
American Political Science Association ◽  
Conceptual Schemes ◽  
The Social ◽  
American Political Science ◽  
Factual Data ◽  
Science Association

Political science is a basic discipline in the social sciences. Although it must necessarily maintain close scholarly association with the disciplines of history, economics, sociology, anthropology, geography, and social psychology, political science cannot be considered a part of any of these other social sciences. Political science has its own area of human experience to analyze, its own body of descriptive and factual data to gather, its own conceptual schemes to formulate and test for truth.

Area Studies and the Disciplines: A Rejoinder

1997 ◽  
Vol 25 (1) ◽  
pp. 29-31
Author(s):  
John W. Harbeson
Keyword(s):  
Social Sciences ◽  
Political Science ◽  
Comparative Politics ◽  
Scientific Knowledge ◽  
American Political Science Association ◽  
Important Work ◽  
Area Studies ◽  
The Social ◽  
American Political Science ◽  
Science Association

Robert Bates’ letter entitled “Area Studies and the Discipline” (American Political Science Association, Comparative Politics 1, Winter 1996, pp. 1-2) uses the occasion of the SSRC’s abolishing of area committees to announce that “within the academy, the consensus has formed that area studies has failed to generate scientific knowledge.” As someone who has done some of his most important work on African development issues, Bates deplores declining investment in area studies as a “loss to the social sciences, as well as to the academy,” at an inopportune moment, “just when our [political science] discipline is becoming equipped to handle area knowledge in a rigorous fashion.”

: Nations and Nationalism in British Political Studies

2003 ◽  
Author(s):  
Charles King
Keyword(s):  
Social Sciences ◽  
Political Science ◽  
British Politics ◽  
Future Directions ◽  
The Social ◽  
Political Studies ◽  
Historical Phenomenon ◽  
Methodological Eclecticism ◽  
British Study

This chapter attempts to provide a ‘reader’s guide’ to nationalism in British politics. It explores some of the major trends in the British study of nationalism and relates these to broader substantive and methodological concerns within the social sciences. The chapter focuses on most important comparative and conceptual studies of nationalism as a general political and historical phenomenon, rather than research limited to particular countries or periods. The defining features of British political studies, including a respect for methodological eclecticism and historically grounded research, have made British writers uniquely attuned to the importance of nationalism at times when many of their American colleagues dismissed it as the residuum of retarded modernization. The chapter concludes with some reflections on possible future directions for research and modest proposals for thinking about the study of nationalism and its relationship to broader debates within political science.

The Political Science Discipline in Argentina: The Political Scientist's National Association's Role

2009 ◽  
Vol 42 (03) ◽  
pp. 616-618
Author(s):  
Diego Mazzoccone ◽  
Mariano Mosquera ◽  
Silvana Espejo ◽  
Mariana Fancio ◽  
Gabriela Gonzalez ◽  
...  
Keyword(s):  
Social Sciences ◽  
Nineteenth Century ◽  
Political Science ◽  
Political Thought ◽  
Scientific Method ◽  
The Political ◽  
Nation State ◽  
Science Discipline ◽  
The Social ◽  
The One

It is very difficult to date the birth of political science in Argentina. Unlike other discipline of the social sciences, in Argentina the first distinction can be made between political thought on the one hand, and political science in another. The debate over political thought—as the reflection of different political questions—emerged in our country in the nineteenth century, especially during the process of constructing the Argentine nation-state. Conversely, political science is defined in a general way as the application of the scientific method to the studies on the power of the state (Fernández 2001).

scholarly journals Teach a Student to Fish? International Relations Scholars in the Classroom

2017 ◽  
Vol 50 (01) ◽  
pp. 214-220
Author(s):  
Nina Srinivasan Rathbun ◽  
Brian C. Rathbun
Keyword(s):  
Social Sciences ◽  
Higher Education ◽  
International Relations ◽  
Political Science ◽  
Undergraduate Students ◽  
Theoretical Work ◽  
Practical Skills ◽  
Relevant Research ◽  
American Higher Education ◽  
The Social

ABSTRACT American higher-education institutions are under increasing pressure to prepare their students with practical skills for the workplace, and the social sciences—including political science—are not immune. Political figures have suggested—sometimes seconded by academics themselves—that research distracts academics from imparting practical skills to undergraduate students. Using a survey of international relations (IR) scholars, this article shows that this is not the case. Those who spend more time on research actually devote more time to policy-relevant research in their courses than more abstract and theoretical work, and they incorporate more contemporary issues. Research seems to encourage academics to teach their students to fish.

Sign in / Sign up

Export Citation Format

Share Document