Unit root testing

Summary The occurrence of unit roots in economic time series has far reaching consequences for univariate as well as multivariate econometric modelling. Therefore, unit root tests are nowadays the starting point of most empirical time series studies. The oldest and most widely used test is due to Dickey and Fuller (1979). Reviewing this test and variants thereof we focus on the importance of modelling the deterministic component. In particular, we survey the growing literature on tests accounting for structural shifts. Finally, further applied aspects are addressed, for instance, how to get the size correct and obtain good power at the same time. We thank Mu-Chun Wang for producing the figures, and an anonymous referee for comments improving the presentation.     

Autoregressive distributed lag models and cointegration

Summary This paper considers cointegration analysis within an autoregressive distributed lag (ADL) framework. First, different reparameterizations and interpretations are reviewed. Then we show that the estimation of a cointegrating vector from an ADL specification is equivalent to that from an error-correction (EC) model. Therefore, asymptotic normality available in the ADL model under exogeneity carries over to the EC estimator. Next, we review cointegration tests based on EC regressions. Special attention is paid to the effect of linear time trends in case of regressions without detrending. Finally, the relevance of our asymptotic results in finite samples is investigated by means of computer experiments. In particular, it turns out that the conditional EC model is superior to the unconditional one. We thank Vladimir Kuzin for excellent research assistance and Surayyo Kabilova for skillful word processing. Moreover, we are grateful to an anonymous referee for clarifying comments.     

Optimal Taxes on Fossil Fuel in General Equilibrium

We analyze a dynamic stochastic general‐equilibrium (DSGE) model with an externality—through climate change—from using fossil energy. Our central result is a simple formula for the marginal externality damage of emissions (or, equivalently, for the optimal carbon tax). This formula, which holds under quite plausible assumptions, reveals that the damage is proportional to current GDP, with the proportion depending only on three factors: (i) discounting, (ii) the expected damage elasticity (how many percent of the output flow is lost from an extra unit of carbon in the atmosphere), and (iii) the structure of carbon depreciation in the atmosphere. Thus, the stochastic values of future output, consumption, and the atmospheric CO₂ concentration, as well as the paths of technology (whether endogenous or exogenous) and population, and so on, all disappear from the formula. We find that the optimal tax should be a bit higher than the median, or most well‐known, estimates in the literature. We also formulate a parsimonious yet comprehensive and easily solved model allowing us to compute the optimal and market paths for the use of different sources of energy and the corresponding climate change. We find coal—rather than oil—to be the main threat to economic welfare, largely due to its abundance. We also find that the costs of inaction are particularly sensitive to the assumptions regarding the substitutability of different energy sources and technological progress.     

Comparing the efficacy of electronic-tablet to paper-based surveys for on-site survey administration

This study compares cost, completion times, and percent completion of electronic tablet (n = 244) to paper-based (n = 398) questionnaires administered to participants of scenic raft trips on the Snake River, Grand Teton National Park. We hypothesized e-tablet questionnaires would (1) cost less (2) be completed faster and (3) be completely filled more frequently than paper-based questionnaires. Our survey resulted in a greater per unit cost of e-tablet compared to paper-based questionnaires ($4.17 and $1.80, respectively). Although e-tablets were completed faster (230 [±66] s) than paper questionnaires (235 [±57] s), the difference was not significant (t₍₆₄₁₎ = 1.97, p = 0.39). E-tablets were filled completely more frequently than paper questionnaires (80% vs. 51%, respectively; χ² = 3.84, p < 0.01). We suggest that for multi-year projects with a sample size target of ≥100, and length ≥ 5 pages, e-tablets are more cost effective and efficient than paper-based surveys.     

Effect of neglected deterministic seasonality on unit root tests

Whenever deterministic seasonality is ignored, the distribution of the Dickey-Fuller test is shifted to the left, with lower dispersion at the same time. When accounting for serial correlation, the distortions become less predictable. A Monte Carlo study confirms that the (augmented) Dickey-Fuller test without seasonal dummies is oversized and has little power at the same time, due to the need of lag augmentation. The effect of neglecting seasonal deterministics on the KPSS test for stationarity depends on the way the long-run variance is estimated. This is a shorter version of a working paper containing additional experimental evidence and the proofs of the propositions. The working paper is available online under http://www.wiwi.uni-frankfurt.de/~deme/ends_urt.pdf.     

ECONOMICS AND CLIMATE CHANGE: INTEGRATED ASSESSMENT IN A MULTI‐REGION WORLD

This paper develops a model that integrates the climate and the global economy—an integrated assessment model—with which different policy scenarios can be analyzed and compared. The model is a dynamic stochastic general‐equilibrium setup with a continuum of regions. Thus, it is a full stochastic general‐equilibrium version of RICE, Nordhaus’s pioneering multi‐region integrated assessment model. Like RICE, our model features traded fossil fuel but otherwise has no markets across regions—there is no insurance nor any intertemporal trade across them. The extreme form of market incompleteness is not fully realistic but arguably not a bad approximation of reality. Its major advantage is that, along with a set of reasonable assumptions on preferences, technology, and nature, it allows a closed‐form model solution. We use the model to assess the welfare consequences of carbon taxes that differ across as well as within oil‐consuming and ‐producing regions. We show that, surprisingly, only taxes on oil producers can improve the climate: taxes on oil consumers have no effect at all. The calibrated model suggests large differences in views on climate policy across regions.     

Inbreeding in Social Work Education: An Empirical Examination

Academic inbreeding frequently has been asserted to be detrimental to the quality of educational institutions. Prior empirical studies, however, have been equivocal in supporting this position and sizeable proportions of inbreeding have been noted in high-prestige institutions. This study found inbreeding to be quite prevalent in graduate schools of social work, but not related to an institution's ranking on measures of prestige, scholarly and professional productivity, and teaching quality. Similarly, the academic nativity of individual faculty members across schools was not related to their scholarly productivity. It was concluded that inbreeding alone is not predictive of institutional or individual calibre.