Citation

Not-So-Standard Errors: A New and Robust Method for Calculating Standard Errors in Time-Series Cross-Sectional Studies

Abstract | Word Stems | Keywords | Association | Citation | Get this Document | Similar Titles



Abstract:

For years social scientists in general and IR researchers
in particular who utilized time-series cross-sectional (TSCS) data
produced overly optimistic findings because the methods they used
failed to account for the manner in which their observations were
interrelated. Observations in TSCS datasets are generally correlated
over time and space. Failure to take these correlations into account
leads to inconsistent standard errors and hypothesis tests. Beck and
Katz 1995 (BK) offer a corrective that has been widely used but has two
limiting features. The BK correction requires the analyst to specify a
precise time-series structure, and it requires that the cross-sectional
correlation structure not change over time. Both of these features
imply substantive assumptions that are undesirable in IR research. For
example, while research on institutions suggests that correlations
among policy outputs across states both exist and may change over time,
the BK solution does not permit the cross-sectional correlation
structure to change over time. Similarly, while the precise form of
serial correlation is typically difficult to establish and may vary
across countries, the BK solution requires an explicit specification of
a common AR structure. We offer a method of calculating consistent TSCS
standard errors that is robust to arbitrary cross-sectional correlation
that changes over time and to arbitrary serial correlation that changes
across units. We offer Monte Carlo simulations and reanalyses of
published work in IR to demonstrate its utility.
Convention
All Academic Convention can solve the abstract management needs for any association's annual meeting.
Submission - Custom fields, multiple submission types, tracks, audio visual, multiple upload formats, automatic conversion to pdf.Review - Peer Review, Bulk reviewer assignment, bulk emails, ranking, z-score statistics, and multiple worksheets!
Reports - Many standard and custom reports generated while you wait. Print programs with participant indexes, event grids, and more!Scheduling - Flexible and convenient grid scheduling within rooms and buildings. Conflict checking and advanced filtering.
Communication - Bulk email tools to help your administrators send reminders and responses. Use form letters, a message center, and much more!Management - Search tools, duplicate people management, editing tools, submission transfers, many tools to manage a variety of conference management headaches!
Click here for more information.

Association:
Name: The Midwest Political Science Association
URL:
http://www.indiana.edu/~mpsa/


Citation:
URL: http://www.allacademic.com/meta/p84255_index.html
Direct Link:
HTML Code:

MLA Citation:

Braumoeller, Bear. and Sekhon, Jasjeet. "Not-So-Standard Errors: A New and Robust Method for Calculating Standard Errors in Time-Series Cross-Sectional Studies" Paper presented at the annual meeting of the The Midwest Political Science Association, Palmer House Hilton, Chicago, Illinois, Apr 15, 2004 <Not Available>. 2009-05-26 <http://www.allacademic.com/meta/p84255_index.html>

APA Citation:

Braumoeller, B. F. and Sekhon, J. , 2004-04-15 "Not-So-Standard Errors: A New and Robust Method for Calculating Standard Errors in Time-Series Cross-Sectional Studies" Paper presented at the annual meeting of the The Midwest Political Science Association, Palmer House Hilton, Chicago, Illinois <Not Available>. 2009-05-26 from http://www.allacademic.com/meta/p84255_index.html

Publication Type: Conference Paper/Unpublished Manuscript
Review Method: Peer Reviewed
Abstract: For years social scientists in general and IR researchers
in particular who utilized time-series cross-sectional (TSCS) data
produced overly optimistic findings because the methods they used
failed to account for the manner in which their observations were
interrelated. Observations in TSCS datasets are generally correlated
over time and space. Failure to take these correlations into account
leads to inconsistent standard errors and hypothesis tests. Beck and
Katz 1995 (BK) offer a corrective that has been widely used but has two
limiting features. The BK correction requires the analyst to specify a
precise time-series structure, and it requires that the cross-sectional
correlation structure not change over time. Both of these features
imply substantive assumptions that are undesirable in IR research. For
example, while research on institutions suggests that correlations
among policy outputs across states both exist and may change over time,
the BK solution does not permit the cross-sectional correlation
structure to change over time. Similarly, while the precise form of
serial correlation is typically difficult to establish and may vary
across countries, the BK solution requires an explicit specification of
a common AR structure. We offer a method of calculating consistent TSCS
standard errors that is robust to arbitrary cross-sectional correlation
that changes over time and to arbitrary serial correlation that changes
across units. We offer Monte Carlo simulations and reanalyses of
published work in IR to demonstrate its utility.

Get this Document:

Find this citation or document at one or all of these locations below. The links below may have the citation or the entire document for free or you may purchase access to the document. Clicking on these links will change the site you're on and empty your shopping cart.

Abstract Only All Academic Inc.
Associated Document Available The Midwest Political Science Association
Associated Document Available Political Research Online


Similar Titles:
Determinants of Social MovementMobilization: A Pooled Cross-Section Time-Series Analysis for aComparative Study in Four Western European Countries in1975-89

State Capacity and Democracy: A Theoretical Argument with a Burmese Case Study and a Time-Series Cross-Section Analysis


 
All Academic, Inc. is your premier source for research and conference management. Visit our website, www.allacademic.com, to see how we can help you today.