No abstract

A univariate nonlinear model is estimated for US GNP that on many criteria outperforms standard linear models. The estimated model is of the threshold autoregressive type and contains evidence of asymmetric effects of shocks over the business cycle. In particular the nonlinear model suggests that the post‐1945 US economy is significantly more stable than the pre‐1945 US economy.

This paper develops a new approach to change-point modelling that allows the number of change-points in the observed sample to be unknown. The model we develop assumes that regime durations have a Poisson distribution. It approximately nests the two most common approaches: the time-varying parameter (TVP) model with a change-point every period and the change-point model with a small number of regimes. We focus considerable attention on the construction of reasonable hierarchical priors both for regime durations and for the parameters that characterize each regime. A Markov chain Monte Carlo posterior sampler is constructed to estimate a version of our model, which allows for change in conditional means and variances. We show how real-time forecasting can be done in an efficient manner using sequential importance sampling. Our techniques are found to work well in an empirical exercise involving U.S. GDP growth and inflation. Empirical results suggest that the number of change-points is larger than previously estimated in these series and the implied model is similar to a TVP (with stochastic volatility) model. Copyright 2007 The Review of Economic Studies Limited.

The labor force participation rate in the United States increased almost continuously for two-and-a-half decades after the mid-1960s, pausing only briefly during economic downturns, as shown in Figure 1, where the shaded regions signify recessions. The pace of growth slowed considerably during the 1990s, however, and after reaching a record high of 67.3 percent in the first quarter of 2000, participation had declined by 1.5 percentage points by 2005. This paper reviews the social and demographic trends that contributed to the movements in the labor force participation rate in the second half of the twentieth century. It also examines the manner in which developments in the 2000s reflect a break from past trends.Understanding changes in the labor force participation rate is important for a number of reasons. The share of the adult population that participates in the labor force-either by working or by looking for work-determines the size of the labor force, which in turn is central to constructing a measure of potential GDP and for making projections of future GDP growth. In the 1970s and the 1980s, for example, the entry of married women greatly expanded the labor force and potential GDP. As the "baby boom" generation-people born between 1946 and 1964 -approach retirement age, how will the size of the U.S. labor force evolve? Will labor market participation of married women continue to grow over the next several decades? Will older workers continue in the labor force until later ages? As a related issue, much of the discussion regarding the solvency of Social Security hinges on projections of the labor force participation rate. The Social Security Trustees are projecting that the participation rate of older people will increase and that the overall

This paper introduces a new model of trend (or underlying) in ‡ation. In contrast to many earlier approaches, which allow for trend in ‡ation to evolve according to a random walk, ours is a bounded model which ensures that trend in ‡ation is constrained to lie in an interval. The bounds of this interval can either be …xed or estimated from the data. Our model also allows for a time-varying degree of persistence in the transitory component of in ‡ation. The bounds placed on trend in ‡ation mean that standard econometric methods for estimating linear Gaussian state space models cannot be used and we develop a posterior simulation algorithm for estimating the bounded trend in ‡ation model. In an empirical exercise with CPI in ‡ation we …nd the model to work well, yielding more sensible measures of trend in ‡ation and forecasting better than popular alternatives such as the unobserved components stochastic volatility model.