Listing 1 - 6 of 6 |
Sort by
|
Choose an application
Neuere methodische Weiterentwicklungen der Conjoint-Analyse ermöglichen heute die simultane Segmentierung eines Gesamtmarktes von Konsumenten in homogene Teilmärkte und die Schätzung entsprechender segmentspezifischer Teilnutzenwertstrukturen. Auf diesem Wege soll der Heterogenität im Konsumentenverhalten Rechnung getragen werden. Das im Rahmen der simultanen Segmentierung derzeit meistgenutzte Conjoint Choice-Modell ist das Finite Mixture Logitmodell. Dieses unterstellt Unabhängigkeit der Gesamtnutzen aller Alternativen, die einem Konsumenten zur Auswahl gestellt werden, und postuliert somit, dass Auswahlentscheidungen unabhängig vom Kontext sind, in dem die Alternativen dem Konsumenten präsentiert werden. Diese Annahme erscheint in Bezug auf die Abbildung realen Kaufverhaltens jedoch fraglich. Friederike Paetz entwickelt ein Finite Mixture Multinomiales Probitmodell, welches explizit Abhängigkeiten zwischen (den Gesamtnutzen der) Alternativen berücksichtigen kann. Abhängigkeiten zwischen Alternativen können einerseits innerhalb eines Choice Sets und andererseits durch die Erinnerung an Alternativen vorangegangener Auswahlsituationen entstehen. Das neu entwickelte Modell wird anschließend sowohl in einer Simulationsstudie als auch in einer empirischen Studie mit Modellen, die Unabhängigkeit unterstellen, verglichen. Der Inhalt · Theoretische Grundlegung: Finite Mixture Multinomiales Probitmodell · Finite Mixture Independent Probitmodell · Modellprüfung durch Simulations- und empirische Studie · Kontexteffekte und Heterogenität. Die Zielgruppen · Dozierende und Studierende der Betriebswirtschaftslehre mit Schwerpunkt Marketing, Kaufverhaltensforschung und stochastischer Modellierung sowie der Mathematik · Marketing- und MarktforschungsberaterInnen, die das Kaufverhalten analysieren Die Autorin Friederike Paetz studierte Mathematik mit Nebenfach Betriebswirtschaftslehre an der Universität Paderborn und ist seit 2008 Wissenschaftliche Angestellte am Institut für Wirtschaftswissenschaft der TU Clausthal.
Marketing. --- Consumer behavior --- Probits. --- Mathematical models.
Choose an application
Drug synergism. --- Drug synergism --- Probits. --- Drugs --- Drug Synergism. --- Data Interpretation, Statistical. --- Dose-Response Relationship, Drug. --- Chemotherapy, Combination. --- Regression Analysis. --- Probits --- Mathematics. --- Dose-response relationship
Choose an application
Mathematical statistics --- Estimation theory --- Biomathematics --- Probits --- Théorie de l'estimation --- Biomathématiques --- 519.2 --- Distribution (Probability theory) --- Probabilities --- Transformations (Mathematics) --- Estimating techniques --- Least squares --- Stochastic processes --- Biology --- Mathematics --- Probability. Mathematical statistics --- Biomathematics. --- Estimation theory. --- Probits. --- Basic Sciences. Mathematics --- Applied Mathematics --- Applied Mathematics. --- 519.2 Probability. Mathematical statistics --- Théorie de l'estimation --- Biomathématiques --- STATISTICS --- Monograph --- Statistics. --- Statistical analysis --- Statistical data --- Statistical methods --- Statistical science --- Econometrics
Choose an application
Stochastic processes --- Estatistica aplicada as ciencias sociais --- Logits. --- Probits. --- Lineaire modellen. --- Modèles linéaires (statistique). --- Linear models (Statistics) --- Modèles linéaires (Statistique) --- Logits --- Probits --- #SBIB:303H10 --- #SBIB:303H521 --- #PBIB:2003.3 --- Biomathematics --- Distribution (Probability theory) --- Probabilities --- Transformations (Mathematics) --- Logit transformation --- Logarithms --- Models, Linear (Statistics) --- Mathematical models --- Mathematical statistics --- Statistics --- Methoden en technieken: algemene handboeken en reeksen --- Methoden sociale wetenschappen: waarschijnlijkheid --- Mathematics --- Physical Sciences & Mathematics --- Mathematical Statistics --- Linear models (Statistics). --- Modèles linéaires (statistique). --- Modèles linéaires (Statistique) --- Linear models
Choose an application
We compare how logit (fixed effects) and probit early warning systems (EWS) predict insample and out-of-sample currency crises in emerging markets (EMs). We look at episodes of currency crises that took place in 29 EMs between January 1995 and December 2012. Stronger real GDP growth rates and higher net foreign assets significantly reduce the probability of experiencing a currency crisis, while high levels of credit to the private sector increase it. We find that the logit and probit EWS out-of-sample performances are broadly similar, and that the EWS performance can be very sensitive both to the size of the estimation sample, and to the crisis definition employed. For macroeconomic policy purposes, we conclude that a currency crisis definition identifying more rather than less crisis episodes should be used, even if this may lead to the risk of issuing false alarms.
Currency crises --- Logits --- Probits --- Biomathematics --- Distribution (Probability theory) --- Probabilities --- Transformations (Mathematics) --- Logit transformation --- Logarithms --- Financial crises --- Currency question --- Foreign exchange --- Prevention. --- Financial Risk Management --- Foreign Exchange --- Macroeconomics --- International Finance: General --- Current Account Adjustment --- Short-term Capital Movements --- International Finance Forecasting and Simulation --- Financing Policy --- Financial Risk and Risk Management --- Capital and Ownership Structure --- Value of Firms --- Goodwill --- Financial Crises --- Economic & financial crises & disasters --- Currency --- Early warning systems --- Exchange rate indexes --- Global financial crisis of 2008-2009 --- Crisis management --- Global Financial Crisis, 2008-2009 --- Mexico
Choose an application
Many estimates of early-warning-system (EWS) models of currency crisis have reported incorrect standard errors because of serial correlation in the context of panel probit regressions. This paper documents the magnitude of the problem, proposes and tests a solution, and applies it to previously published EWS estimates. We find that (1) the uncorrected probit estimates substantially underestimate the true standard errors, by up to a factor of four; (2) a heteroskedasicity- and autocorrelation-corrected (HAC) procedure produces accurate estimates; and (3) most variables from the original models remain significant, though substantially less so than had been previously thought.
Financial crises --- Panel analysis. --- Probits. --- Biomathematics --- Distribution (Probability theory) --- Probabilities --- Transformations (Mathematics) --- Panel studies --- Social sciences --- Statistics --- Crashes, Financial --- Crises, Financial --- Financial crashes --- Financial panics --- Panics (Finance) --- Stock exchange crashes --- Stock market panics --- Crises --- Forecasting. --- Methodology --- Econometrics --- Exports and Imports --- Financial Risk Management --- Foreign Exchange --- Macroeconomics --- Simulation Methods --- Time-Series Models --- Dynamic Quantile Regressions --- Dynamic Treatment Effect Models --- Diffusion Processes --- 'Panel Data Models --- Spatio-temporal Models' --- Single Equation Models --- Single Variables: Discrete Regression and Qualitative Choice Models --- Macroeconomic Aspects of International Trade and Finance: Forecasting and Simulation --- Financing Policy --- Financial Risk and Risk Management --- Capital and Ownership Structure --- Value of Firms --- Goodwill --- Trade: General --- Estimation --- Economic & financial crises & disasters --- International economics --- Currency --- Foreign exchange --- Econometrics & economic statistics --- Currency crises --- Early warning systems --- Export performance --- Real exchange rates --- Estimation techniques --- International trade --- Econometric analysis --- Crisis management --- Exports --- Econometric models --- Argentina --- Panel Data Models --- Spatio-temporal Models
Listing 1 - 6 of 6 |
Sort by
|