A Comparative Distributional Method for Public Administration Illustrated Using Public Budget Data

TY - JOUR

T1 - A Comparative Distributional Method for Public Administration Illustrated Using Public Budget Data

AU - Jensen, Jens Ledet

AU - Mortensen, Peter Bjerre

AU - Serritzlew, Søren

PY - 2019/6/7

Y1 - 2019/6/7

N2 - Many outputs and outcomes of relevance to public administration research are distributed in a way that escapes simple statistical descriptives. The field of public administration has generally been slow to acknowledge this fact, but in recent years the research field of public budgeting has experienced what we term a “distributional turn” reflected in a massive increase in publications studying distributions of changes in public budgets. Yet, distributional budget studies still rely on inadequate statistical methods. In this article, we introduce a comparative distributional method (CDM), which allows for inferential statistics and statistical modeling of distributions. It also allows for specification of parameter values that precisely characterize the empirical distribution. All this is important for systematic comparisons of empirical distributions. We illustrate the usefulness of the CDM approach by analyzing budget data from seven countries and conclude with a discussion of how this new method can be extended to other areas of public administration than public budgeting.

AB - Many outputs and outcomes of relevance to public administration research are distributed in a way that escapes simple statistical descriptives. The field of public administration has generally been slow to acknowledge this fact, but in recent years the research field of public budgeting has experienced what we term a “distributional turn” reflected in a massive increase in publications studying distributions of changes in public budgets. Yet, distributional budget studies still rely on inadequate statistical methods. In this article, we introduce a comparative distributional method (CDM), which allows for inferential statistics and statistical modeling of distributions. It also allows for specification of parameter values that precisely characterize the empirical distribution. All this is important for systematic comparisons of empirical distributions. We illustrate the usefulness of the CDM approach by analyzing budget data from seven countries and conclude with a discussion of how this new method can be extended to other areas of public administration than public budgeting.

UR - http://www.scopus.com/inward/record.url?scp=85064124785&partnerID=8YFLogxK

U2 - 10.1093/jopart/muy056

DO - 10.1093/jopart/muy056

M3 - Journal article

SN - 1053-1858

VL - 29

SP - 460

EP - 473

JO - Journal of Public Administration Research and Theory

JF - Journal of Public Administration Research and Theory

IS - 3

ER -