Home  About us  Contact
 

Threshold Estimation (threshold + estimation)

Distribution by Scientific Domains
Business, Economics, Finance and Accounting75%

Selected Abstracts

Sample Splitting and Threshold Estimation

ECONOMETRICA, Issue 3 2000
Bruce E. Hansen
Threshold models have a wide variety of applications in economics. Direct applications include models of separating and multiple equilibria. Other applications include empirical sample splitting when the sample split is based on a continuously-distributed variable such as firm size. In addition, threshold models may be used as a parsimonious strategy for nonparametric function estimation. For example, the threshold autoregressive model (TAR) is popular in the nonlinear time series literature. Threshold models also emerge as special cases of more complex statistical frameworks, such as mixture models, switching models, Markov switching models, and smooth transition threshold models. It may be important to understand the statistical properties of threshold models as a preliminary step in the development of statistical tools to handle these more complicated structures. Despite the large number of potential applications, the statistical theory of threshold estimation is undeveloped. It is known that threshold estimates are super-consistent, but a distribution theory useful for testing and inference has yet to be provided. This paper develops a statistical theory for threshold estimation in the regression context. We allow for either cross-section or time series observations. Least squares estimation of the regression parameters is considered. An asymptotic distribution theory for the regression estimates (the threshold and the regression slopes) is developed. It is found that the distribution of the threshold estimate is nonstandard. A method to construct asymptotic confidence intervals is developed by inverting the likelihood ratio statistic. It is shown that this yields asymptotically conservative confidence regions. Monte Carlo simulations are presented to assess the accuracy of the asymptotic approximations. The empirical relevance of the theory is illustrated through an application to the multiple equilibria growth model of Durlauf and Johnson (1995). [source]

A joint test of market power, menu costs, and currency invoicing

AGRICULTURAL ECONOMICS, Issue 1 2009
Jean-Philippe Gervais
Exchange rate pass-through; Currency invoicing; Menu costs; Threshold estimation Abstract This article investigates exchange rate pass-through (ERPT) and currency invoicing decisions of Canadian pork exporters in the presence of menu costs. It is shown that when export prices are negotiated in the exporter's currency, menu costs cause threshold effects in the sense that there are bounds within (outside of) which price adjustments are not (are) observed. Conversely, the pass-through is not interrupted by menu costs when export prices are denominated in the importer's currency. The empirical model focuses on pork meat exports from two Canadian provinces to the U.S. and Japan. Hansen's (2000) threshold estimation procedure is used to jointly test for currency invoicing and incomplete pass-through in the presence of menu costs. Inference is conducted using the bootstrap with pre-pivoting methods to deal with nuisance parameters. The existence of menu cost is supported by the data in three of the four cases. It also appears that Quebec pork exporters have some market power and invoice in Japanese yen their exports to Japan. Manitoba exporters also seem to follow the same invoicing strategy, but their ability to increase their profit margin in response to large enough own-currency devaluations is questionable. Our currency invoicing results for sales to the U.S. are consistent with subsets of Canadian firms using either the Canadian or U.S. currency. [source]

Sample Splitting and Threshold Estimation

ECONOMETRICA, Issue 3 2000
Bruce E. Hansen
Threshold models have a wide variety of applications in economics. Direct applications include models of separating and multiple equilibria. Other applications include empirical sample splitting when the sample split is based on a continuously-distributed variable such as firm size. In addition, threshold models may be used as a parsimonious strategy for nonparametric function estimation. For example, the threshold autoregressive model (TAR) is popular in the nonlinear time series literature. Threshold models also emerge as special cases of more complex statistical frameworks, such as mixture models, switching models, Markov switching models, and smooth transition threshold models. It may be important to understand the statistical properties of threshold models as a preliminary step in the development of statistical tools to handle these more complicated structures. Despite the large number of potential applications, the statistical theory of threshold estimation is undeveloped. It is known that threshold estimates are super-consistent, but a distribution theory useful for testing and inference has yet to be provided. This paper develops a statistical theory for threshold estimation in the regression context. We allow for either cross-section or time series observations. Least squares estimation of the regression parameters is considered. An asymptotic distribution theory for the regression estimates (the threshold and the regression slopes) is developed. It is found that the distribution of the threshold estimate is nonstandard. A method to construct asymptotic confidence intervals is developed by inverting the likelihood ratio statistic. It is shown that this yields asymptotically conservative confidence regions. Monte Carlo simulations are presented to assess the accuracy of the asymptotic approximations. The empirical relevance of the theory is illustrated through an application to the multiple equilibria growth model of Durlauf and Johnson (1995). [source]

A SIMPLE ALTERNATIVE ANALYSIS FOR THRESHOLD DATA DETERMINED BY ASCENDING FORCED-CHOICE METHODS OF LIMITS

JOURNAL OF SENSORY STUDIES, Issue 3 2010
HARRY T. LAWLESS
ABSTRACT An alternative analysis of forced-choice threshold data sets such as the type generated by ASTM method E-679 involves a simple interpolation of chance-corrected 50% detection. This analysis has several potential advantages. The analysis does not require the ad hoc heuristics for estimating individual thresholds above and below the series. It takes into account the possibility of guessing correctly, which is not considered in the ASTM calculations and produces a downward bias to the estimates. It does not discount correct responses early in the series which may be legitimate detections, but which are discounted by the ASTM method if followed by any incorrect response. Comparisons of the two methods in a large consumer study of odor detection threshold study data set gave comparable values. The interpolation can also be done to determine other levels of detection (e.g. 10, 25%). These values other than 50% can be potentially useful in setting regulatory standards for water or air pollution limits or to food manufacturers who wish to avoid detection of taints by more sensitive individuals. PRACTICAL APPLICATIONS The forced choice methods for threshold estimation have proven practically useful in comparing the potency of various flavor materials and in comparing the sensitivities of individuals. The ASTM method E-679 is one such method. The alternative analysis of results from this procedure which is outlined here provides additional information and does not exhibit the downward bias because of correct guessing. [source]