Rekursive oder nicht-rekursive Modelle? / Testing for non-recursiveness in causal modelling

1975 ◽  
Vol 4 (3) ◽  
Author(s):  
Christof Ammermann ◽  
Peter Gluchowski ◽  
Peter Schmidt
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Error Term ◽  
Causal Model ◽  
Identification Problem ◽  
Testing Procedure ◽  
Small Samples ◽  
Theory Construction ◽  
Causal Modelling ◽  
Oder Nicht

AbstractThe paper discusses a stubborn problem of theory construction: deciding between recursive and non- recursive variants of a causal model by testing them against empirical data. After pointing out the consequences of a correlation between an exogeneous variable and the error term of an endogeneous variable as well as certain aspects of the identification problem we show for the asymptotic case (n → ∞) that a test is possible if the correlation between the exogeneous and the error term is in fact zero. Following this we present the results of a Monte-Carlo simulation investigating the robustness of the proposed test when applied to small samples. Finally we suggest conclusions of this testing procedure for empirical research.

Testing for bubbles in housing markets: some evidence for Brazil

2018 ◽  
Vol 11 (5) ◽  
pp. 754-770 ◽  
Author(s):  
Cássio da Nóbrega Besarria ◽  
Nelson Leitão Paes ◽  
Marcelo Eduardo Alves Silva
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Housing Prices ◽  
Market Price ◽  
Housing Markets ◽  
Cointegration Analysis ◽  
Small Samples ◽  
Content Type ◽  
Long Run ◽  
Cointegration Tests

Purpose Housing prices in Brazil have displayed an impressive growth in recent years, raising some concerns about the existence of a bubble in housing markets. In this paper, the authors implement an empirical methodology to identify whether or not there is a bubble in housing markets in Brazil. Design/methodology/approach Based on a theoretical model that establish that, in the absence of a bubble, a long-run equilibrium relationship should be observed between the market price of an asset and its dividends. The authors implement two methodologies. First, the authors assess whether there is a cointegration relationship between housing prices and housing rental prices. Second, the authors test whether the price-to-rent ratio is stationary. Findings The authors’ results show that there is evidence of a bubble in housing prices in Brazil. However, given the short span of the data, the authors perform a Monte Carlo simulation and show that the cointegration tests may be biased in small samples. Therefore, the authors should be caution when assessing the results. Research limitations/implications The results obtained from the cointegration analysis can be biased for small samples. Practical implications The information on the excessive increase of the prices of the properties in relation to their fundamental value can help in the decision-making on investment of the economic agents. Social implications These results corroborate the hypothesis that Brazil has an excessive appreciation in housing prices, and, as Silva and Besarria (2018) have suggested, this behavior explains, in part, the fact that the central bank has taken this issue into account when deciding about the stance of monetary policy of Brazil. Originality/value The originality is linked to the use of the Gregory-Hansen method of cointegration in the identification of bubbles and discussion of the limitations of the research through Monte Carlo simulation.

scholarly journals Efficiency calibration of a well-type HPGe detector using experimental and Monte Carlo simulation techniques

2020 ◽  
Vol 35 (2) ◽  
pp. 121-129
Author(s):  
Ekaterini Dalaka ◽  
Georgios Kuburas ◽  
Konstantinos Eleftheriadis ◽  
Marios Anagnostakis
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Background Radiation ◽  
Detection Efficiency ◽  
Environmental Radioactivity ◽  
Efficiency Calibration ◽  
Small Samples ◽  
Experimental Calibration ◽  
Simulation Techniques ◽  
Radioactivity Laboratory

Well-type high-purity germanium detectors are well suited for the analysis of small samples, as they combine high detection efficiency with low background radiation. The well geometry however makes efficiency calibration more difficult than that of ordinary HPGe detectors, due to intense true coincidence and possibly random summing effects. Such a detector has been installed at the Environmental Radioactivity Laboratory of the National Centre for Scientific Research "Demokritos". For the calibration of this detector, experimental and Monte Carlo simulation techniques were applied. To this end, calibration sources were produced from the radionuclides available at the Environmental Radioactivity Laboratory. Starting from the geometrical characteristics of the detector as provided by the manufacturer, using the calibration sources and applying Monte Carlo simulation techniques, the detector was characterized and peak efficiency, as well as total-to-peak calibration curves were produced. The results of the calibration finally obtained by simulation are found to be in good agreement with the respective experimental calibration results.

scholarly journals Stock Price Simulation Using Bootstrap and Monte Carlo

2017 ◽  
Vol 64 (2) ◽  
pp. 155-170 ◽  
Author(s):  
Martin Pažický
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Stock Price ◽  
Error Term ◽  
Monte Carlo Experiment ◽  
Asian Option ◽  
Heteroscedastic Error ◽  
Maturity Date ◽  
The Future ◽  
The Difference

Abstract In this paper, an attempt is made to assessment and comparison of bootstrap experiment and Monte Carlo experiment for stock price simulation. Since the stock price evolution in the future is extremely important for the investors, there is the attempt to find the best method how to determine the future stock price of BNP Paribas′ bank. The aim of the paper is define the value of the European and Asian option on BNP Paribas′ stock at the maturity date. There are employed four different methods for the simulation. First method is bootstrap experiment with homoscedastic error term, second method is blocked bootstrap experiment with heteroscedastic error term, third method is Monte Carlo simulation with heteroscedastic error term and the last method is Monte Carlo simulation with homoscedastic error term. In the last method there is necessary to model the volatility using econometric GARCH model. The main purpose of the paper is to compare the mentioned methods and select the most reliable. The difference between classical European option and exotic Asian option based on the experiment results is the next aim of tis paper.

scholarly journals A Shrinkage Instrumental Variable Estimator for Large Datasets

2016 ◽  
Vol 91 (1-2) ◽  
pp. 67-87
Author(s):  
Andrea Carriero ◽  
George Kapetanios ◽  
Massilimiano Marcellino
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Recent Work ◽  
Instrumental Variable ◽  
Large Datasets ◽  
Small Samples ◽  
Many Instruments ◽  
Good Potential ◽  
Instrumental Variable Estimator ◽  
General Conditions

This paper proposes and discusses an instrumental variable estimator that can be of particular relevance when many instruments are available and/or the number of instruments is large relative to the total number of observations. Intuition and recent work (see, e.g., Hahn, 2002) suggest that parsimonious devices used in the construction of the final instruments may provide effective estimation strategies. Shrinkage is a well known approach that promotes parsimony. We consider a new shrinkage 2SLS estimator. We derive a consistency result for this estimator under general conditions, and via Monte Carlo simulation show that this estimator has good potential for inference in small samples.

Effects of filtering data on testing asymmetry in threshold autoregressive models

2016 ◽  
Vol 20 (5) ◽  
Author(s):  
Jing Li
Keyword(s):  
Time Series ◽  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Business Cycle ◽  
Error Term ◽  
Economic Time Series ◽  
Threshold Autoregressive ◽  
Threshold Autoregression ◽  
Power Of The Test ◽  
Economic Time

AbstractEmpirical macroeconomic research on business cycle typically filters economic time series in order to obtain cyclical components. This paper examines the effects of filtering data on the test for a linear autoregression against a threshold autoregression. Monte Carlo simulation shows that (1) filtering data in general reduces the power of the test, (2) the power is sensitive to the choice of filters and the specification of the trend and cyclical components, (3) regime-varying variance of the error term can affect the rejection frequency. Empirical evidences for cyclical asymmetry are provided for the quarterly US real GNP.

Electron Scattering in Solids

1990 ◽  
Vol 48 (2) ◽  
pp. 4-5
Author(s):  
Ryuichi Shimizu ◽  
Ze-Jun Ding
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Angular Distribution ◽  
Elastic Scattering ◽  
Electron Scattering ◽  
Cross Sections ◽  
Expansion Method ◽  
Electron Excitation ◽  
Partial Wave Expansion ◽  
Backscattered Electrons

Monte Carlo simulation has been becoming most powerful tool to describe the electron scattering in solids, leading to more comprehensive understanding of the complicated mechanism of generation of various types of signals for microbeam analysis.The present paper proposes a practical model for the Monte Carlo simulation of scattering processes of a penetrating electron and the generation of the slow secondaries in solids. The model is based on the combined use of Gryzinski’s inner-shell electron excitation function and the dielectric function for taking into account the valence electron contribution in inelastic scattering processes, while the cross-sections derived by partial wave expansion method are used for describing elastic scattering processes. An improvement of the use of this elastic scattering cross-section can be seen in the success to describe the anisotropy of angular distribution of elastically backscattered electrons from Au in low energy region, shown in Fig.l. Fig.l(a) shows the elastic cross-sections of 600 eV electron for single Au-atom, clearly indicating that the angular distribution is no more smooth as expected from Rutherford scattering formula, but has the socalled lobes appearing at the large scattering angle.

Determination of Stoichiometry of GaAs Component in (Gaas)Ge Epitaxially Grown Thin Films by Electron Microprobe X-Ray Analysis

1990 ◽  
Vol 48 (2) ◽  
pp. 264-265
Author(s):  
D. R. Liu ◽  
S. S. Shinozaki ◽  
R. J. Baird
Keyword(s):  
Thin Film ◽  
Thin Films ◽  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Compound Semiconductors ◽  
Energy Dispersive Analysis ◽  
X Ray ◽  
Metastable Alloys ◽  
Lower Voltage

The epitaxially grown (GaAs)Ge thin film has been arousing much interest because it is one of metastable alloys of III-V compound semiconductors with germanium and a possible candidate in optoelectronic applications. It is important to be able to accurately determine the composition of the film, particularly whether or not the GaAs component is in stoichiometry, but x-ray energy dispersive analysis (EDS) cannot meet this need. The thickness of the film is usually about 0.5-1.5 μm. If Kα peaks are used for quantification, the accelerating voltage must be more than 10 kV in order for these peaks to be excited. Under this voltage, the generation depth of x-ray photons approaches 1 μm, as evidenced by a Monte Carlo simulation and actual x-ray intensity measurement as discussed below. If a lower voltage is used to reduce the generation depth, their L peaks have to be used. But these L peaks actually are merged as one big hump simply because the atomic numbers of these three elements are relatively small and close together, and the EDS energy resolution is limited.

Sign in / Sign up

Export Citation Format

Share Document