U.S. money demand instability A flexible least squares approach

Tesfatsion, Leigh; Veitch, John M.

doi:10.1016/0165-1889(90)90010-e

Cited by 39 publications

(16 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TESFATSION and VEITCH, 1990 propose to specify D to be diagonal with elements d rr ¼ 1=T P T t¼1 x 2 rt for r = 1, . .…”

Section: Flexible Least Squaresmentioning

confidence: 99%

See 1 more Smart Citation

Time-Varying Betas of German Stock Returns

Ebner¹,

Neumann²

2005

Fin Mkts Portfolio Mgmt

View full text Add to dashboard Cite

The market model assumes stock returns to be a linear function of the market return. However, there is considerable evidence that the beta stability assumption commonly used when estimating the market model is invalid. In this paper we account for beta instability in German stock returns by allowing the coefficients to vary over time in estimation. For time-varying beta estimation we rely on the Flexible Least Squares approach, the Random Walk Model and Moving Window Least Squares. Due to our results time-varying estimation fits the data considerably better than time-invariant estimation and, hence, increases the efficiency of beta based risk measurement. Copyright Swiss Society for Financial Market Research 2005

show abstract

“…TESFATSION and VEITCH, 1990 propose to specify D to be diagonal with elements d rr ¼ 1=T P T t¼1 x 2 rt for r = 1, . .…”

Section: Flexible Least Squaresmentioning

confidence: 99%

“…Applications are given in TESFATSION and VEITCH (1990), LÜ TKEPOHL (1993), LÜ TKEPOHL et al, (1995) and NEUMANN (2003) among others.…”

Section: Endnotesmentioning

confidence: 99%

Time-Varying Betas of German Stock Returns

Ebner¹,

Neumann²

2005

Fin Mkts Portfolio Mgmt

View full text Add to dashboard Cite

show abstract

“…The strength of the method is that it can be used as a purely descriptive tool without any stochastic assumptions (Lütkepohl and Herwartz 1996). Importantly, FLS resolves problems of nonstationarity in the original time series as discussed by Tesfatsion and Veitch (1990). Unlike ordinary least squares (OLS), which seeks to find the average coefficient vector over all observations, FLS seeks to find the particular coefficient vector that obtained at a point of time t, considering all time T. This contrasts with recursive least squares, which generates coefficient time paths from subsamples of increasing length.…”

Section: Model Of the Relationship Between Log Grade Prices For Lumbementioning

confidence: 99%

Testing for variation in the western Oregon softwood log price structure

Størdal¹,

Adams²

2005

Can. J. For. Res.

View full text Add to dashboard Cite

Timber owners in western Oregon have been concerned about the erosion of price premiums for higher quality grades of Douglas-fir (Pseudotsuga menziesii (Mirb.) Franco) sawlogs over the past decade. Time series tests indicate that the ratio of 3Saw (lower quality) to 2Saw (higher quality) sawlog prices did rise over the 1990-2000 period, suggesting convergence between the prices. To identify causes of this trend, we estimate reduced form equations for Douglas-fir sawlog prices with time-varying coefficients using flexible least squares. Log grade prices were related to prices of lumber by grade, prices of chipped residues, labor wage rates, and volumes of public timber supplied. Changes in the relation of log grade prices are reflected through changes in both reduced form coefficients and levels of the exogenous variables. Changes in the coefficients, in turn, may derive from shifts in the distribution of log qualities within grade categories and from grade-specific changes in sawing and log production technologies. Coefficient trends showed that higher quality lumber grades became more important for 3Saw logs during the sample period, while lower quality lumber grades and chips became more important for 2Saw, moving the log grade prices closer together. Comparison of simulated 2Saw and 3Saw prices with and without historical time patterns in the exogenous variables had little impact on their relationship, suggesting that factors shifting the coefficients may have been the primary drivers of price convergence.Résumé : Les propriétaires forestiers de l'ouest de l'Oregon sont préoccupés par l'érosion de la valeur des billes de sciage de douglas (Pseudotsuga menziesii (Mirb.) Franco) de qualité supérieure qui est survenue au cours de la dernière décennie. Des tests de séries chronologiques indiquent que le rapport du prix des billes de qualité 3Sciage (qualité inférieure) sur celui des billes de qualité 2Sciage (qualité supérieure) a connu une augmentation durant la période allant de 1990 à 2000, ce qui laisse croire à une convergence des prix. Dans le but d'identifier les causes de cette tendance, nous estimons la forme réduite des équations du prix des billes de sciage de douglas en fonction de coefficients variables dans le temps, en utilisant des moindres carrés flexibles. Le prix des différentes qualités de billes est relié au prix des différentes qualités de bois d'oeuvre, au prix des résidus transformés en copeaux, au coût de la main d'oeuvre et au volume de bois provenant de la forêt publique. Des changements dans la relation entre le prix des différentes qualités de billes se reflètent dans des changements tant des coefficients de la forme réduite que dans le niveau des variables exogènes. Les changements dans les coefficients peuvent en retour découler de changements dans la distribution de la qualité des billes dans chaque classe de qualité et de changements spécifiques aux classes elles-mêmes résultant des technologies de sciage et de production des billes. Les tendances dans les coefficients indiquent qu...

show abstract

“…This issue arose in the FLS money demand study 40], for the focus of the study concerned possible step-function breaks in money demand regression coe cients. Various simulation experiments were therefore conducted in which the components of the true regression coe cients were shifted idiosyncratically at various points in time.…”

Section: Insert Figure 2 About Here|mentioning

confidence: 99%

A multicriteria approach to model specification and estimation

Kalaba

Tesfatsion

1996

Computational Statistics & Data Analysis

Self Cite

View full text Add to dashboard Cite

In decision theory, incommensurabilities among con icting decision criteria are typically handled by m ulticriteria optimization methods such a s P areto e ciency and meanvariance analysis. In econometrics and statistics, where con icting model criteria replace con icting decision criteria, probability assessments are routinely used to transform disparate model discrepancy terms into apparently commensurable quantities. This tactic has both strengths and weaknesses. On the plus side, it permits the construction of a single real-valued measure of theory and data incompatibility in the form of a likelihood function or a posterior probability distribution. On the minus side, the amalgamation of conceptually distinct model discrepancy terms into a single real-valued incompatibility measure can make it di cult to untangle the true source of any diagnosed model speci cation problem. This paper discusses recent theoretical and empirical work on a multicriteria \ exible least squares" (FLS) approach to model speci cation and estimation. The basic FLS objective is to determine the \cost-e cient frontier," that is, the set of estimates that are minimally incompatible with a speci ed set of model criteria. The relation of this work to previous work in econometrics, statistics, and systems science is also clari ed.

show abstract

U.S. money demand instability A flexible least squares approach

Cited by 39 publications

References 11 publications

Time-Varying Betas of German Stock Returns

Time-Varying Betas of German Stock Returns

Testing for variation in the western Oregon softwood log price structure

A multicriteria approach to model specification and estimation

Contact Info

Product

Resources

About