Christine Amsler

An LM Test for a Unit Root in the Presence of a Structural Change

In this paper, we examine a suitably modified version of the unit root test proposed by Schmidt and Phillips (1992). A one-time structural break in the intercept does not affect its asymptotic distribution under the null hypothesis, and this is true whether the break is allowed for in the model or not. This implies that the asymptotic validity of this test statistic under the null is not affected by the incorrect placement of the structural break, by the allowance for a break when there is no break, or by no allowance for a break when there is a break.

A Monte Carlo investigation of the accuracy of multivariate CAPM tests

Abstract In a multivariate regression model relating individual returns to the market return, CAPM implies non-linear restrictions on the parameters. Several asymptotically valid tests of these restrictions have been suggested. The existing Monte Carlo evidence shows that some of these tests are unreliable for reasonable sample sizes, but does not indicate well which tests are reliable. This paper reports the results of an extensive Monte Carlo experiment. Shankens CSR test and Jobson and Korkies corrected likelihood ratio test are quite accurate in all cases we consider.

Consistency of the KPSS unit root test against fractionally integrated alternative

Abstract We derive the asymptotic distribution of the Kwiatkowski et al. (1992) statistic under nonstationary long memory (1/2

Thoughts of Some British Economists on Early Limited Liability and Corporate Legislation

The debate over the economic and social merits of limited liability corporations has fascinated American social scientists for most of this century. Yet virtually all of the combatants in this controversy have believed that the issues raised by limited liability and by the legal status of incorporated firms were problems new to this century, problems with little or no intellectual history before the 1890s or 1920s. Despite some passing awareness that Smith and his successors would find these issues of interest if faced with modern conditions, the consensus of opinion is that the eighteenth and nineteenth centuries were times quite significantly alien to our own.’ Somewhere near the end of the last century, we are told, the beast of corporatism was spawned as a necessary offspring of ‘mature capitalism.’ Although ‘necessary,’ this development was unanticipated. The nature of the creature is still not fully understood by incredulous scholars today, though they have spent much effort in attempts to examine and exorcise it. Probably the only agreed-upon characteristics of the corporate form of organization are large-scale production and some, vaguely associated, notions of pervasive monopoly. Much of

Using copulas to model time dependence in stochastic frontier models

We consider stochastic frontier models in a panel data setting where there is dependence over time. Current methods of modeling time dependence in this setting are either unduly restrictive or computationally infeasible. Some impose restrictive assumptions on the nature of dependence such as the “scaling” property. Others involve T-dimensional integration, where T is the number of cross-sections, which may be large. Moreover, no known multivariate distribution has the property of having commonly used, convenient marginals such as normal/half-normal. We show how to use copulas to resolve these issues. The range of dependence we allow for is unrestricted and the computational task involved is easy compared to the alternatives. Also, the resulting estimators are more efficient than those that assume independence over time. We propose two alternative specifications. One applies a copula function to the distribution of the composed error term. This permits the use of maximum likelyhood estimate (MLE) and generalized method moments (GMM). The other applies a copula to the distribution of the one-sided error term. This allows for a simulated MLE and improved estimation of inefficiencies. An application demonstrates the usefulness of our approach.

Tests of Short Memory With Thick-Tailed Errors

In this article, we consider the robustness to fat tails of four stationarity tests. We also consider their sensitivity to the number of lags used in long-run variance estimation, and the power of the tests. Los modified rescaled range (MR/S) test is not very robust. Chois Lagrange multiplier (LM) test has excellent robustness properties but is not generally as powerful as the Kwiatkowski–Phillips–Schmidt–Shin (KPSS) test. As an analytical framework for fat tails, we suggest local-to-finite variance asymptotics, based on a representation of the process as a weighted sum of a finite variance process and an infinite variance process, where the weights depend on the sample size and a constant. The sensitivity of the asymptotic distribution of a test to the weighting constant is a good indicator of its robustness to fat tails. This article has supplementary material online.

Term structure variance bounds and time varying liquidity premia

Abstract Including a time varying liquidity premium in Shillers variance bound does not reverse Shillers conclusion that long-term interest rates are too volatile relative to short-term rates to be explained by the rational expectations model of the term structure.

A "Pure" long-term interest rate and the demand for money

Abstract This article presents the appropriate rate by which to discount a constant, certain, infinite stream of future payments: that is, the yield on a noncallable perpetuity or consol. The American consol series is a daily risk-free “pure” long term interest rate which is undistorted by tax effects, call premiums, and varying duration and reinvestment assumptions. If Hamburger had used the American consol series instead of the U.S. Government Long Term Bond Rate in his money demand function, he would have found more of the “missing money.” His average error (actual minus predicted money demand) as a percentage of actual money demand would have been reduced from 1.43% to 0.93% a 35% error reduction.

A joint test for a unit root and common factor restrictions in the presence of a structural break

Abstract This paper provides evidence that the common factor restrictions (CFR) play an important role in testing for a unit root in the presence of a structural break. We first show that the CFR should not be ignored in the unit root testing procedure when a structural break is allowed for. Then we provide a Wald test statistic for the joint hypothesis of a unit root and the CFR. The empirical finding suggests that the missing common factor restrictions may result in a quite different and perhaps misleading inference.

Size and power: lower tail KPSS tests and anti-persistent alternatives

Evidence is presented on the size and power of the lower tail Kwiatkowski-Phillips-Schmidt-Shin stationarity test for testing the null hypothesis of short memory against the alternative hypothesis of anti-persistence.