Oxford Bulletin of Economics and Statistics最新文献

We evaluate the impact of real-time macroeconomic data and data revisions on the forecasting performance of DSGE models in the US and the euro area. We identify significant differences in data revisions between the two world regions: Negative revisions (due to overestimation in early data releases) are prevalent in the US, while the euro area data tends to be dominated by positive revisions. These biases are most significant in consumption growth, output growth, and hours worked. Parameter estimates in small-sized DSGE models are not strongly affected by the use of real-time data, while larger models exhibit substantial differences depending on the data used, especially during large economic downturns. Revisions significantly affect the predictive accuracy of the DSGE model for output growth in the US and for inflation and interest rates in the euro area. Our findings highlight the central role of data revisions as a determinant of predictive accuracy in macroeconomic models and thus of the quality of such specifications as an instrument to inform evidence-based policy-making.

Stochastic and deterministic trends always coexist in data generating processes, which causes the nonstationarity and non-standard distributions of statistics used in inference. It is known that the presence of the deterministic trend leads to asymptotic normality of the t-statistics. This article goes further and points out that the convergence rate depends on the share of the deterministic trend in the data generating process, which can be assessed from the estimator derived in the article. This finding is of significance for empirical research, because it shows that in the case of two samples of the same relatively small size, the one with dominance of the deterministic trend may satisfy asymptotic properties, enabling the use of standard approach, whereas the other one requires different strategy of statistical inference.

How does the implementation of a new technology affect workers? Using detailed worker-level data for Germany, we analyse the impact of new technologies on non-monetary working conditions such as overtime, training and perceived labour intensity. We show that the strongest effects arise in the first year of their implementation. These effects diminish after the introduction period. We further provide evidence that the impact of technology adoption varies across diverse occupational and industrial contexts. Workers in occupations with a higher task substitution potential show stronger increases in overtime, training measures and labour intensity. Analysing industry characteristics, we find that employees exposed to a new technology react more strongly in industries with higher business dynamics in terms of organisational capital and R&D investment. Extending these considerations to information and communication technology (ICT) usage, we show that new technologies exert stronger effects in industries with high investment in ICT equipment or low investment in software.

Housing is an important asset for many households in the United States. Nevertheless, our understanding of the relationships between housing markets and election outcomes remains somewhat limited. Examining the influence of local housing markets on U.S. presidential elections in the past three decades, this paper presents evidence that a faster rise in county-level house prices increases the share of the county's vote that goes to the incumbent party. That is, greater support for the incumbent party in counties where housing prices outpaced the national average. This effect, however, exhibits significant variation among counties and becomes more pronounced in regions where a larger proportion of homeowners with mortgage debts. These results support the “collateral effect” channel as the primary mechanism through which local housing markets affect U.S. national elections.

We consider the estimation of the location parameter $��\theta �$ in the normal location model and study the sampling properties of shrinkage estimators derived from a non-standard Bayesian approach that places the prior on a scaled version of $��\theta �$, interpreted as the “population $��t�$-ratio.” We show that the finite-sample distribution of these estimators is not centred at $��\theta �$ and is generally non-normal. In the asymptotic theory, we prove uniform $��\sqrt{��n��}�$-consistency of our estimators and obtain their asymptotic distribution under a general moving-parameter setup that includes both the fixed-parameter and the local-parameter settings as special cases.

This article considers the issue of testing for an explosive bubble in financial time series in the presence of deterministic level shifts. We demonstrate that the sign-based variants of the Phillips-Shi-Yu test retain their asymptotic validity in the presence of level shifts under a weak restriction on the number of shifts that occur. This is in contrast to the original Phillips-Shi-Yu test which only remains valid under a joint restriction involving both the number and magnitudes of the level shifts. We find, through Monte Carlo simulation, that the original test can display substantial over-size in the presence of level shifts, without a corresponding increase in power, while the sign-based variants are largely unaffected in both regards. The sign-based tests therefore offer robust and powerful methods for detecting an explosive autoregressive regime in a financial time series that potentially contains level shifts. Empirical applications of the different tests are provided using intraday Bitcoin log price data and daily Nasdaq price data.