Nonresponse in dynamic panel data models

To verify whether data are missing at random (MAR) we need to observe the missing data. There are only two exceptions: when the relationship between the probability of responding and the missing variables is either imposed by introducing untestable assumptions or recovered using additional data sources. In this paper, we briefly review the estimation and test procedures for selectivity in panel data. Furthermore, by extending the MAR definition from a static setting to the case of dynamic panel data models, we prove that some tests for selectivity are not verifying the MAR condition.     

The impact of a Hausman pretest on the size of a hypothesis test: The panel data case

The size properties of a two-stage test in a panel data model are investigated where in the first stage a Hausman (1978) specification test is used as a pretest of the random effects specification and in the second stage, a simple hypothesis about a component of the parameter vector is tested, using a t$t$-statistic that is based on either the random effects or the fixed effects estimator depending on the outcome of the Hausman pretest. It is shown that the asymptotic size of the two-stage test equals 1 for empirically relevant specifications of the parameter space. The size distortion is caused mainly by the poor power properties of the pretest. Given these results, we recommend using a t$t$-statistic based on the fixed effects estimator instead of the two-stage procedure.     

Empirical analysis of the impact of cigarette excise taxes on cigarette consumption: estimates from recent state-level data

The adverse health effects from cigarette smoking account for an estimated 443,000 deaths annually in the U.S. Given this circumstance, this study has two objectives. First, it uses a state-level panel data set for a recent time frame to investigate the impact of federal plus state cigarette excise taxes (along with a variety of other factors) on the aggregate consumption of cigarettes. The study adopts a state-level panel data series spanning the period 2002 through 2007, which is the most recent panel for which data for all of the variables are available. Consistent with a number of previous studies, the PLS estimates in this study find that the higher the cigarette excise tax, the lower the aggregate volume of cigarettes consumed. Of course, this outcome does not address the practical problem of the substitution of high nicotine cigarettes for low nicotine cigarettes in the presence of a significant cigarette tax hike. This circumstance leads to the second objective of this study, namely, to propose a general template for a different kind of cigarette excise tax, one that is tied directly to each cigarette brand’s nicotine and tar content.     

The impact of institutional quality on manufacturing sectors: A panel data analysis

We use data on Russian regions to examine the effect of institutional quality on institutionally dependent manufacturing sectors in terms of both output levels and growth rates. Unlike the existing literature on this topic, which mostly uses cross-sectional or pooled specifications for either country-level or regional data, we use panel data. This approach allows us to distinguish between short-term and long-term impacts and mitigates endogeneity concerns. As an additional contribution to the literature, we estimate the full marginal effects of institutions on manufacturing sectors with different degrees of institutional dependence. In terms of policy recommendations, our results imply that significant institutional improvements would be needed for the Russian economy to diversify away from heavy reliance on oil and natural gas.     

The role of fixed capital depreciations for TFP growth: evidence from firm level panel data estimates

The role of accounting depreciation rates and the stocks of fixed capital has been well established in the literature. By exploring available evidence on the value of fixed assets in certain countries, this paper makes use of firm level data on fixed capital depreciations over the period 1990–2008 from a group of OECD countries along with panel data estimations to investigate their role for total factor productivity (TFP) as it is defined through growth accounting, since different capital depreciation profiles imply different rates of capital accumulation and, therefore, different estimates of TFP. The empirical results indicate a positive relationship between the two variables under study.     

The optimal consumption function in a Brownian model of accumulation Part A: The consumption function as solution of a boundary value problem

We consider a neo-classical model of optimal economic growth with c.r.r.a. utility in which the traditional deterministic trends representing population growth, technological progress, depreciation and impatience are replaced by Brownian motions with drift. When transformed to ‘intensive’ units, this is equivalent to a stochastic model of optimal saving with diminishing returns to capital. For the intensive model, we give sufficient conditions for optimality of a consumption plan (open-loop control) comprising a finite welfare condition, a martingale condition for shadow prices and a transversality condition as t→∞. We then replace these by conditions for optimality of a plan generated by a consumption function (closed-loop control), i.e. a function expressing log-consumption as a time-invariant, deterministic function of log-capital . Making use of the exponential martingale formula we replace the martingale condition by a non-linear, non-autonomous second-order o.d.e. which an optimal consumption function must satisfy; this has the form , where . Economic considerations suggest certain limiting values which and should satisfy as , thus defining a two-point boundary value problem (b.v.p.) — or rather, a family of problems, depending on the values of parameters. We prove two theorems showing that a consumption function which solves the appropriate b.v.p. generates an optimal plan. Proofs that a unique solution of each b.v.p. exists are given in a separate paper (Part B).     

Business strategy for sustainable development: Impact of life cycle inventory and life cycle impact assessment steps in supply chain design and planning

Sustainability reporting has become a central instrument in displaying a company's strategy and engagement with a more sustainable society. Life cycle assessment (LCA) is an important tool in this context as it is aimed to analyze the entire life cycle of the product/service, instead of focusing on one focal firm. However, the lack of standardized guidelines in its application raises questions regarding the usefulness and validity of results. This study contributes to the improvement of sustainability reporting through the identification of the uncertainty sources in life cycle methodologies that have the biggest impact in the definition of business and environmental strategies, exploring a supply chain‐oriented analysis. The focus is on life cycle inventory (LCI) and life cycle impact assessment (LCIA). A multiobjective optimization‐based methodology is applied to a supply chain case study in the pulp and paper industry. Environmental and economic objectives are considered. Results show that different LCIA methods and different normalization data sets result in significantly different business and environmental strategies. However, different system models and cultural perspectives at the LCI step and variations in the characterization factors tend to lead to the same decisions. Important insights are gained regarding the impact of nonstandardized analysis of the application of LCA in supply chain design and planning decisions and consequently on business strategy definition and sustainability reporting. Furthermore, the importance of operations research methods to improve LCA‐based studies and of bridging the gap between LCA and supply chain management bodies of knowledge is highlighted in this work.     

Habits and heterogeneity in demands: a panel data analysis

We examine demand behaviour for intertemporal dependencies, using Spanish panel data. We present evidence that there is both state dependence and correlated heterogeneity in demand behaviour. Our specific findings are that food outside the home, alcohol and tobacco are habit forming, whereas clothing and small durables exhibit durability. We conclude that demand analyses using cross‐section data that ignore these effects may be seriously biased. On the other hand, the degree of intertemporal dependence is not sufficiently strong to make composite ‘consumption’ significantly habit forming, as has been suggested in some recent analyses. Copyright © 2007 John Wiley & Sons, Ltd.     

The impact of site characteristics on housing cost estimates

Hedonic housing regressions using micro data for owners and renters from the 1972–1973 Consumer Expenditure Survey are presented. By including tract characteristics and public goods in these regressions, evidence is presented which indicates sensitivity of the physical housing variable coefficients to the choice of included site-related characteristics. Furthermore, omission of public good variables can result in misleading, and possibly perverse, coefficients on access. Intermetropolitan housing cost estimates, however, are shown to be relatively insensitive to the choice of site-related characteristics.     

The heterogeneous impact of taxation on economic development: New insights from a panel cointegration approach

In this paper, we study the role of taxation on long-run income performance. In the theoretical part of the study, we develop a stylized model based on Barro (1990), in which income taxation has two contradictory roles in the standard Solow (1956) setup: on the one hand, taxation appropriates resources that would otherwise be used for physical capital accumulation, and on the other, it is the source of government spending, which is used to support private production. In the empirical part of the study, the impact of consumption tax, personal income tax, corporate profit tax and property tax on income is estimated using the common correlated effects (CCE) panel cointegration approach, which allows for cross-sectional dependencies and provides both panel- and country-specific results. The panel findings for 30 OECD countries for the period of 1995–2016 indicate that only consumption tax has a statistically significant negative effect on long-run income. However, because the type and sign of the tax coefficients are heterogeneous for the country-specific results, we conclude that taxation has heterogeneous effects on income.     

Does the expansionary government spending crowd out the private consumption?: Cointegration analysis in panel data

That whether expansionary government spending crowds out private consumption is examined by evaluating the intra-temporal elasticity of substitution between them. Using annual data (1981–2000) of 23 OECD countries, a linear deterministic cointegration relation between private consumption, government spending and their relative price is supported. We have two findings: first, the panel estimators plausibly compute the parameter estimates in general. Second, when cross-sectional correlation is considered by using a SUR estimator, the statistical significance of panel cointegration is improved. Thirdly, the intra-temporal elasticity of substitution indicates that government and private consumption are found to be complements, which shows that expansionary government spending does not crowd out private consumption.     

An evaluation of financial institutions: Impact on consumption and investment using panel data and the theory of risk-bearing

The theory of the optimal allocation of risk and the Townsend Thai panel data on financial transactions are used to assess the impact of the major formal and informal financial institutions of an emerging market economy. We link financial institution assessment to the actual impact on clients, rather than ratios and non-performing loans. We derive both consumption and investment equations from a common core theory with both risk and productive activities. The empirical specification follows closely from this theory and allows both OLS and IV estimation. We thus quantify the consumption and investment smoothing impact of financial institutions on households including those running farms and small businesses. A government development bank (BAAC) is shown to be particularly helpful in smoothing consumption and investment, in no small part through credit, consistent with its own operating system, which embeds an implicit insurance operation. Commercial banks are smoothing investment, largely through formal savings accounts. Other institutions seem ineffective by these metrics.     

Beyond death: The impact of a population-wide health shock on life insurance

Population-wide health shocks, for example, pandemics, affect life insurance owners beyond their health impact. This paper considers joint impacts of their surrender behavior adaptions and mortality rise following a population-wide health shock on insurance pricing. We build a model that captures both more surrenders of contracts to meet unexpected liquidity needs and less financially beneficial surrenders to keep insurance protection after the shock. Unlike the systemic mortality rise impact that turns out to be negligible, we find that policyholders’ surrender behavior adaptions substantially devalue policies with increasing emergency surrenders being the main driver. Regulatory solvency protection partly restrains the devaluation.     

Measuring the impact of nonignorability in panel data with non‐monotone nonresponse

The analysis of panel data with non‐monotone nonresponse often relies on the critical and untestable assumption of ignorable missingness. It is important to assess the consequences of departures from the ignorability assumption. Non‐monotone nonresponse, however, can often make such sensitivity analysis infeasible because the likelihood functions for alternative models involve high‐dimensional and difficult‐to‐evaluate integrals with respect to missing outcomes. We develop an extension of the local sensitivity method that overcomes computational difficulty and completely avoids fitting alternative models and evaluating these high‐dimensional integrals. The proposed method is applicable to a wide range of panel outcomes. We apply the method to a Smoking Trend dataset where we relax the standard ignorability assumption and evaluate how smoking‐trend estimates in different groups of US young adults are affected by alternative assumptions about the missing‐data mechanism. The main finding is that the standard estimate in the black male group is sensitive to nonignorable missingness but those in other groups are reasonably robust. Copyright © 2010 John Wiley & Sons, Ltd.     

Organized crime and public spending: a panel data analysis

The aim of this paper is to investigate, empirically, what components of public spending imply a decreasing effect on organized crime and what components create opportunities for organized crime, discussing also the role of government efficiency. Using a panel data analysis, the results show a strikingly consistent pattern for the EU Member States. Organized crime mainly operates in the distribution of government spending for local public goods and public provision of private services. There is a decreasing effect on organized crime of the public expenditure devoted to education and social policy. Government efficiency in public spending is beneficial to limit the opportunities of the organized crime.     

The major determinants of logistic performance in a global perspective: evidence from panel data analysis

The global logistics industry has grown significantly and logistics has become an important sector of the business economic system and a major global economic activity in recent years. Logistics activities accelerate economic and productivity growth. Efficient logistics is also important to a country’s competitiveness and source of employment. The purpose of this paper is to uncover and understand the major determinants of logistics performance (LP) to further lift the LP of countries. Using unbalanced panel data of 93 selected countries from 2007 to 2014, the present research attempts to critically investigate the major determinants of LP. In estimating the model, this study prefers to use static panel data approach owing to limited data. The findings of the present study reveal that (a) countries with low level of corruption and stable political environment are likely to yield a high level of LP; (b) improvement in resources supply such as infrastructure, technology, labour, and education also have a significant positive effect on LP. Therefore, institutional reforms and upgrading resources will effectively accelerate LP.