Time-series Cross-sectional Models Research Articles

DSRIP’s innovation and collaboration in population health management: A cross-sectional segmented time series model

Texas Medicaid Section 1115 waiver approved Delivery System Reform Incentive Payment (DSRIP) program has four categories, namely infrastructure development, program innovation and redesign, reporting of quality improvement outcomes, and population health improvement. A metric of the fourth category, preventable hospitalization rate, was analyzed for a set of eight diagnostic conditions to assess the impact of DSRIP on participating- and non-participating hospitals over two time periods, pre-DSRIP and post-DSRIP, with the help of a cross-sectional segmented time series regression model. Texas Healthcare Information Collection database was leveraged to obtain preventable hospitalization rate data. The dependent variables were preventable hospitalization rates of eight program-specified conditions and the independent variables were time, intervention, and post-implementation intervention. The overall combined preventable hospitalization rate for DSRIP hospitals was observed to decrease by 25.73%, whereas the overall combined preventable hospitalization rate for non-DSRIP hospitals was observed to increase by 37.57%. DSRIP hospitals had invested in coordinating healthcare projects and were subsequently reimbursed by the state for healthcare improvements. The implementation of DSRIP may have had the capacity to decrease preventable hospitalization rates in regions wherein its adoption may have improved the health of the population.

Immigrants in the EU5 labour markets: what happened during the economic crisis?

PurposeThe purpose of this paper is to understand: whether the changes that have occurred in migrants’ conditions over time are smaller than the differences in their conditions existing across countries; and whether the comparison between immigrants and native-born conditions allows the verification of the levels of disparities between them and, therefore, the relative disadvantage suffered by migrant. After a general overview of the 28 European Union countries, this paper analyses the changes that have occurred from 2006 to 2017 in the conditions of migrants in the labour market in the big five European countries (Italy, Spain, France, Germany and the UK).Design/methodology/approachVarious statistical methodologies were used. First, to gain an overall picture, taking into account both the spatial and the temporal dimensions, dynamic factor analysis (DFA) was applied. Second, time-dependent and cross-sectional time-series models were estimated to better understand the DFA results.FindingsThe results highlight very different scenarios in terms of labour market vulnerabilities, both affecting immigrants and native-born workers. The results also highlight the existence of a very complex framework, due to the high heterogeneity of immigrants’ characteristics and labour market capacities to integrate migrants and also to promote good conditions for the native-born population.Originality/valueThe picture emerging from this study and the evaluation of the policies and legislation in force to cope with migration and to promote integration suggests some reflections on the most efficacious actions to take in order to improve migrants’ integration, counteracting social exclusion and promoting economic growth.

Pork, parties, and priorities: Partisan politics and overseas military deployments

Since the end of World War II, the USA has maintained a sizable military presence around the world. As one of the main mechanisms that the USA uses to exercise its military power abroad, it is a defining characteristic of the international order. Using time-series cross-sectional models and case evidence, I show that, in addition to strategic considerations, the President’s party strength in Congress and the proportion of moderates in the Senate are key determinants of US deployment outcomes. This finding adds to the literature on causes of US troop deployments by examining the incentives for deployments within US politics.

Is social investment inimical to the poor?

AbstractIn the last two decades, the social investment strategy has been the main approach to welfare state reform. Concretely, two spending programs have dominated the agenda: the expansion of active labor market programs and the development of childcare services. Many authors have suspected, however, that these social investments were realized at the expense of income protection for the poor. This article assesses this potential trade-off with time-series cross-sectional models of the determinants of active labor market policies expenditures, childcare spending and the adequacy of minimum income protection (MIP), for 18 OECD countries between 1990 and 2009. It turns out that social investments are rather akin to traditional welfare state programs, and are explained by similar institutional, political and economic factors. More importantly, they do not develop at the expense of income protection. Social investment initiatives are consistent with the usual politics of the welfare state and, overall, they are not inimical to the poor.

Changing the transmission belt: the programme-to-policy link in Italy between the First and Second Republic

AbstractThis article analyses the transmission of policy priorities from electoral campaigns to legislative outputs under different institutional configurations. Taking an agenda-setting approach, the article tests whether a mandate effect exists, if incumbents also uptake the priorities of their competitors, and whether and how the introduction of alternation in government impacts on these dynamics. The analysis relies on data sets of the Italian Agendas Project recording the issue content of party manifestos and laws and covering the period 1983–2012. The results of time series cross-sectional models lend support to the presence of a mandate effect in Italy, a mechanism which was strengthened after the introduction of alternation in government. Opposition priorities may have an impact on the legislative agenda, but mostly when considering the legislation initiated in Parliament. Our findings have important implications for the understanding of the impact of government alternation, an institutional feature underlying – with varying intensity – most democracies, on the functioning of democratic representation.

Corporate governance and audit features: SMEs evidence

Purpose The purpose of this paper is to investigate the effect of corporate governance factors on audit features, namely, audit fees and the selection of Big 4 audit firms within the UK SMEs context. Design/methodology/approach The author uses different regression models to investigate the impact of corporate governance characteristics on audit features, and employs cross-sectional time series models as well as two-stage least squares technique. In addition, the author has used logit analysis to examine the effect of corporate governance factors on the selection of Big 4 audit firms. Findings The author provides new evidence that governance mechanisms in SMEs affect different audit features. The results show that corporate governance mechanisms are important in determining audit fees. The author detects a positive impact of board independence, audit meeting and board size on audit fees. The author also reports evidence that governance factors determine the selection of Big 4 audit firms. In particular, the author reports that independent directors and audit diligence positively affect the decision to select Big 4 audit firms. Originality/value This paper investigates the under-researched relationship between audit features and corporate governance using UK SMEs. In so doing, the author aims to provide new insights into this relationship within the SMEs context.

Immigration, socio-economic conditions and crime: a cross-sectional versus cross-sectional time-series perspective

This study purpose is to verify if there is an association between foreign immigration and crime. In doing this, the study investigates also some satellite aspects revolving around this possible association: the range of offences affected by immigration, the relationship between immigrant and native crime, and whether the immigration impact on crime is direct or indirect. The present study has addressed these issues by both a cross-sectional and a longitudinal analysis, the latter including an instrument. The study is based on data of the Italian provinces. Italy represents a critical case for studying the migration–crime relationship, because in this country the rise in foreign immigration has been sudden and its pace feverish. The cross-sectional analysis findings show that crime intensities are affected by time-invariant factors and marginally by immigration. On the contrary, the longitudinal analysis shows that variations in immigration had a positive impact on both the most serious and the most common offences, on property crimes as well as on crimes of violence. There is no evidence of indirect effects of immigration on crime or of a link with native crime. In contrast to previous literature regarding the U.S., Canada, and Australia, these results suggest that a spiralling immigration can affect crime. In terms of methods, these findings show that the standard synchronic analysis models can be biased by non-observed factors and that therefore cross-sectional time-series models can offer significant advantages.

Revisiting Environmental Kuznets Curve in Sub-Sahara Africa

PurposeThe purpose of this paper is to revisit the Environmental Kuznets Curve (EKC) model in Sub-Saharan Africa (SSA) countries by focusing on two indicators of environmental change (EC), namely rate of deforestation (RD) and all greenhouse gas emissions from agriculture (Agric_GHG) with aim of addressing two key objectives in the study. First, to investigate whether the EKC hypothesis exists for both indicators considered in the region. Second, to examine the effects of macroeconomic and institutional variables on both indicators in the study.Design/methodology/approachThe authors employ a balanced panel data covering 43 countries from 1990-2009 in the study. Subsequently, the study uses serial correlation/autoregressive order one corrected cross-section time series model based on Feasible Generalized Least Square method.FindingsThe empirical results show that the EKC exists (i.e. as inverted U-shaped) only for all GHG emissions from agriculture. Agricultural production and trade openness increase significantly both indicators of EC considered in the study. Other results show that, population growth reduces significantly Agric_GHG, while economic growth increases significantly RD in SSA.Originality/valueThis is the very first study to investigate the applicability of EKC hypothesis to emissions from non-oil sector such as agriculture (i.e. all GHG emissions from agriculture) in the region.

Revisiting Diversification and Performance Relationship: Does Product Diversification Hurt Firm's Performance?

The diversification-performance relationship has been the hot subject of extensive studies for past 30 years. But the studies about the product diversification and performance relationship produced mixed results. In this paper, we integrate the transaction cost theory with the resource-based view together to explain this relationship for the firms from developed countries in past 15 years. Using cross-sectional time-series regression model to analyze a sample of 19,890 firm-years data from firms in Europe, US and Japan during the period from 1991 and 2004, we found that product diversification is negatively related to firm’s performance. The result also shows that different industries and different countries have no statistically significant effects on this relationship but some years have effects on this relationship.

The Paradox of Power Asymmetry: When and Why Do Weaker States Challenge US Hegemony?

Little is known about how, among weaker states, incentives to challenge the status quo are related to the expected response of the US as the system’s hegemon. In contrast to conventional wisdom that suggests militarized punishment can deter potential challengers, it is argued that weak but strongly motivated challengers can interpret the hegemon’s military intervention against adversaries as a window of opportunity to launch their own actions. Empirical results using Generalized Estimating Equations (GEE) and binary time-series cross-section (BTSCS) models reveal that weaker states possess incentives to challenge the international status quo when the hegemon is preoccupied with prior foreign policy commitments, most notably war. In other words, weaker states dissatisfied with the status quo are more likely to challenge the hegemon when it is preoccupied with prior military commitments. They do so because war involvement distracts the hegemon, drains its capabilities and resolve, and opens up a window of opportunity for weaker states to issue challenges. In addition, weaker states that have an alliance portfolio dissimilar to that of the hegemon are more likely than others to initiate Militarized Interstate Disputes. Theoretically, this paper provides microfoundations to answer the question of why weaker parties instigate asymmetric conflicts when it might seem irrational to do so.

Party mandates and the politics of attention

This article develops an attention-based model of party mandates and policy agendas, where parties and governments are faced with an abundance of issues and must divide their scarce attention across them. In government, parties must balance their desire to deliver on their electoral mandate (i.e. the ‘promissory agenda’) with a need to continuously adapt their policy priorities in response to changes in public concerns and to deal with unexpected events and the emergence of new problems (i.e. the ‘anticipatory agenda’). Parties elected to office also have incentives to respond to issues prioritized by the platforms of their rivals. To test this theory, time series cross-sectional models are used to investigate how the policy content of the legislative program of British government responds to governing and opposition party platforms, the executive agenda, issue priorities of the public and mass media.

Drivers of cross-national variation in advertising spending: A longitudinal analysis of the effects of freedom and foreign direct investment

We examine the effects of freedom and foreign direct investment on ad spending. We also assess possible differential effects of foreign direct investment (FDI) on ad spending across economies with different income levels. We employed random effect time-series cross-sectional (TSCS) models linear in parameters for fifty economies using annual data from Euromonitor and other sources for the 2000–2013 period. We found that freedom and FDI have significant effects on ad spending. A theoretical contribution of this study to the literature consists in showing that macro-level environmental factors such as political freedom and FDI are crucial for understanding how firms allocate their ad spending to national markets. It also shows that the effect of FDI on ad spending is more salient in low income economies than in high income economies.

Democracy, political partisanship, and state capacity in Latin America

Social scientists have often neglected, or not sufficiently explored, the role of political factors in shaping state capacity. When they did, they mostly focused on key institutional features of political regimes, especially democracy. In this paper, we broaden this approach: besides the institutional traits of democracy, we analyze how governments and their ideologies influence state capacity. In particular, we assess the impact of democracy and executives’ partisanship on a composite index of state capacity, based on political order, administrative ability, and extractive capacity. To this end, we apply a pooled cross-sectional time-series model to 18 Latin American countries between 1995 and 2009. Our findings suggest that, in recent years, state capacity in the region was significantly affected by both democratic features and the ideological bearing of elected governments.

Strategy of Spatial Panel Estimation: Spatial Spillovers Between Taxation and Economic Growth

Spatial panels are a powerful econometric tool for the estimation of space-dependent cross-sectional time-series models of economic phenomena. A plethora of parameters and possible specifications require a systematic approach to estimation. This paper presents a strategy of estimation to be considered in applied research on economic policy, including the concept of spatial spillovers and its local and global effects, direct and indirect impacts, as well as the role of different spatial weighting schemes. The paper presents fiscal factors affecting GDP between the years 2002–2015 in a number of European economies.

A Panel Analysis of Legal Culture, Political Economics, and Punishment Among 15 Western Countries, 1960–2010

I extend Sutton’s political economy of punishment thesis by including a composite measure of legal and criminal justice practices that are hypothesized to be related to incarceration rates. I test the association between a punishment regime–type variable composed of the nature of prosecutorial discretion, judicial power, and the nature of lay participation with incarceration rates in 15 Western countries between 1960 and 2010. The effects of the punishment regime variable are tested in several time series cross-section models that correct for autocorrelation and heteroscedasticity and include the effects of the leading political–economic correlates of punishment and homicide rates. The results show consistent significant findings for the punishment regime–type variable, union power, and corporatist bargaining, with mixed support for political party power, inflation, and unemployment rates. These findings provide evidence for the existence of multiple cultures of Western punishment. In the end, I suggest that multidisciplinary cross-national partnerships incorporating researchers and governmental entities are needed to develop large comparative criminal justice databases to enhance understanding of comparative crime and justice.

Indigenous Identity, Natural Resources, and Contentious Politics in Bolivia

How do natural resources and ethnic identity interact to incite or to mitigate social conflict? This article argues that high-value natural resources can act as an important catalyst for the politicization of ethnic, specifically indigenous identity, and contribute to social conflict as they limit the malleability of identity frames and raise the stakes of confrontations. We test this argument using unique sub-national data from Bolivian provinces. Drawing on Bolivian newspaper reports, we code conflict events for all of the 112 provinces from 2000 to 2011. We join this conflict data with information on local ethnic composition from the census, the political representation of ethnic groups at the national level, as well as geo-spatial information on gas deposits. Using time-series cross-sectional count models, we show a significant conflict-promoting effect of the share of indigenous people in provinces with gas reserves, but not without.

Prediction of energy expenditure and physical activity in preschoolers.

Accurate, nonintrusive, and feasible methods are needed to predict energy expenditure (EE) and physical activity (PA) levels in preschoolers. Herein, we validated cross-sectional time series (CSTS) and multivariate adaptive regression splines (MARS) models based on accelerometry and heart rate (HR) for the prediction of EE using room calorimetry and doubly labeled water (DLW) and established accelerometry cut points for PA levels. Fifty preschoolers, mean ± SD age of 4.5 ± 0.8 yr, participated in room calorimetry for minute-by-minute measurements of EE, accelerometer counts (AC) (Actiheart and ActiGraph GT3X+), and HR (Actiheart). Free-living 105 children, ages 4.6 ± 0.9 yr, completed the 7-d DLW procedure while wearing the devices. AC cut points for PA levels were established using smoothing splines and receiver operating characteristic curves. On the basis of calorimetry, mean percent errors for EE were -2.9% ± 10.8% and -1.1% ± 7.4% for CSTS models and -1.9% ± 9.6% and 1.3% ± 8.1% for MARS models using the Actiheart and ActiGraph+HR devices, respectively. On the basis of DLW, mean percent errors were -0.5% ± 9.7% and 4.1% ± 8.5% for CSTS models and 3.2% ± 10.1% and 7.5% ± 10.0% for MARS models using the Actiheart and ActiGraph+HR devices, respectively. Applying activity EE thresholds, final accelerometer cut points were determined: 41, 449, and 1297 cpm for Actiheart x-axis; 820, 3908, and 6112 cpm for ActiGraph vector magnitude; and 240, 2120, and 4450 cpm for ActiGraph x-axis for sedentary/light, light/moderate, and moderate/vigorous PA (MVPA), respectively. On the basis of confusion matrices, correctly classified rates were 81%-83% for sedentary PA, 58%-64% for light PA, and 62%-73% for MVPA. The lack of bias and acceptable limits of agreement affirms the validity of the CSTS and MARS models for the prediction of EE in preschool-aged children. Accelerometer cut points are satisfactory for the classification of sedentary, light, and moderate/vigorous levels of PA in preschoolers.

Explaining the Variation in Gender Composition of Personnel Contributions to UN Peacekeeping Operations

How do we account for the dearth of female contributions to UN peace operations (UNPOs)? For answers, this study examines conditions that led the United Nations to move to reduce the gender imbalance in UNPO personnel and provides descriptive evidence that points to the continuing underrepresentation of women in these operations. To interpret this evidence, the study presents theoretical explanations for the varying contributions of personnel to UNPOs—including the political and socioeconomic character of the contributing states, international reputations and norms, and various demand-side influences exerted by missions—and then tests these explanations with a cross-sectional time-series model that accounts for female personnel contributions to each mission in the 2010–2011 period. Although offering significant support for domestic political explanations, the findings indicate that gender diversity is not a primary goal of most contributors and is largely a by-product of force sizes.

Active transportation: Do current traffic safety policies protect non-motorists?

ObjectiveThis study investigated the impact that state traffic safety regulations have on non-motorist fatality rates. MethodsData obtained from the National Highway Traffic Safety Administration (NHTSA), the Federal Highway Administration (FHWA), and the National Institute on Alcohol Abuse and Alcoholism (NIAAA) were analyzed through a pooled time series cross-sectional model using fixed effects regression for all 50 states from 1999 to 2009. Two dependent variables were used in separate models measuring annual state non-motorist fatalities per million population, and the natural log of state non-motorist fatalities. Independent variables measuring traffic policies included state expenditures for highway law enforcement and safety per capita; driver cell phone use regulations; graduated driver license regulations; driver blood alcohol concentration regulations; bike helmet regulations; and seat belt regulations. Other control variables included percent of all vehicle miles driven that are urban and mean per capita alcohol consumption per year. ResultsNon-motorist traffic safety was positively impacted by state highway law enforcement and safety expenditures per capita, with a decrease in non-motorist fatalities occurring with increased spending. Per capita consumption of alcohol also influenced non-motorist fatalities, with higher non-motorist fatalities occurring with higher per capita consumption of alcohol. Other traffic safety covariates did not appear to have a significant impact on non-motorist fatality rates in the models. ConclusionOur research suggests that increased expenditures on state highway and traffic safety and the initiation/expansion of programs targeted at curbing both driver and non-motorist intoxication are a starting point for the implementation of traffic safety policies that reduce risks for non-motorists.

Where Do Women Run? A Case for the Study of “Women Friendly Districts” in State Legislative Primaries

This study explores the political, institutional, and socio-demographic factors that contribute to the entry of women candidates in state legislative primaries. Using a dataset constructed from 49 partisan state legislative primary elections from 20012010, a binary time series cross-sectional logistic model is used to determine which factors are independently related to the probability of a woman candidate running for office. Women candidates run in districts that have a higher income, more professional people, are typically in cities with a higher urban population. Women candidates typically do not run in states with more professionalized legislatures, but are more likely to run in districts that are in session longer. Women are more likely to be present in districts where there is a lot of competition for a seat, i.e. multimember districts. The electoral environment that women face is different than men.