9 resultados para LOGISTIC REGRESSION WITH STATE-DEPENDENT SAMPLE SELECTION

em Repositório digital da Fundação Getúlio Vargas - FGV


Relevância:

100.00% 100.00%

Publicador:

Resumo:

State-dependent and time-dependent price setting models yield distinct implications for how frequency and magnitude of price changes react to shocks. This note studies pricing behavior in Brazil following the large devaluation of the Brazilian Real in 1999 to distinguish between models. The results are consistent with state-dependent pricing

Relevância:

100.00% 100.00%

Publicador:

Resumo:

This paper examines the output losses caused by disinflation and the role of credibility in a model where pricing mIes are optimal and individual prices are rigid. Individual nominal rigidity is modeled as resulting from menu costs. The interaction between optimal pricing mIes and credibility is essential in determining the inflationary inertia. A continued period of high inflation generates an asymmetric distribution of price deviations, with more prices that are substantially lower than their desired leveIs than prices that are substantially higher than the optimal ones. When disinflation is not credible, inflationary inertia is engendered by this asymmetry: idiosyncratic shocks trigger more upward than downward adjustments. A perfect1y credible disinflation causes an immediate change of pricing rules which, by rendering the price deviation distribution less asymmetric, practically annihilates inflationary inertia. An implication of our model is that stabilization may be sucessful even when credibility is low, provided that it is preceded by a mechanism of price alignment. We also develop an analytical framework for analyzing imperfect credibility cases.

Relevância:

100.00% 100.00%

Publicador:

Resumo:

This paper proposes a test for distinguishing between time-dependent and state-dependent pricing based on whether the timing of pricing changes is affected by realized or expeted inflation. Using Brazilian data and exploring a large discrepancy between realized and expected inflation in 2002-3, we obtain a strong relation between expected inflation and duration of price spells, but little effect of inflation shocks on the frequency of price adjustment. The results thus support models with timedependent pricing, where the timing for following changes is optimally chosen whenever firms adjust prices

Relevância:

100.00% 100.00%

Publicador:

Resumo:

This paper considers two-sided tests for the parameter of an endogenous variable in an instrumental variable (IV) model with heteroskedastic and autocorrelated errors. We develop the nite-sample theory of weighted-average power (WAP) tests with normal errors and a known long-run variance. We introduce two weights which are invariant to orthogonal transformations of the instruments; e.g., changing the order in which the instruments appear. While tests using the MM1 weight can be severely biased, optimal tests based on the MM2 weight are naturally two-sided when errors are homoskedastic. We propose two boundary conditions that yield two-sided tests whether errors are homoskedastic or not. The locally unbiased (LU) condition is related to the power around the null hypothesis and is a weaker requirement than unbiasedness. The strongly unbiased (SU) condition is more restrictive than LU, but the associated WAP tests are easier to implement. Several tests are SU in nite samples or asymptotically, including tests robust to weak IV (such as the Anderson-Rubin, score, conditional quasi-likelihood ratio, and I. Andrews' (2015) PI-CLC tests) and two-sided tests which are optimal when the sample size is large and instruments are strong. We refer to the WAP-SU tests based on our weights as MM1-SU and MM2-SU tests. Dropping the restrictive assumptions of normality and known variance, the theory is shown to remain valid at the cost of asymptotic approximations. The MM2-SU test is optimal under the strong IV asymptotics, and outperforms other existing tests under the weak IV asymptotics.

Relevância:

100.00% 100.00%

Publicador:

Resumo:

This dissertation deals with the problem of making inference when there is weak identification in models of instrumental variables regression. More specifically we are interested in one-sided hypothesis testing for the coefficient of the endogenous variable when the instruments are weak. The focus is on the conditional tests based on likelihood ratio, score and Wald statistics. Theoretical and numerical work shows that the conditional t-test based on the two-stage least square (2SLS) estimator performs well even when instruments are weakly correlated with the endogenous variable. The conditional approach correct uniformly its size and when the population F-statistic is as small as two, its power is near the power envelopes for similar and non-similar tests. This finding is surprising considering the bad performance of the two-sided conditional t-tests found in Andrews, Moreira and Stock (2007). Given this counter intuitive result, we propose novel two-sided t-tests which are approximately unbiased and can perform as well as the conditional likelihood ratio (CLR) test of Moreira (2003).

Relevância:

100.00% 100.00%

Publicador:

Resumo:

Duas classes de modelos buscam explicar o padrão de ajustamento de preço das firmas: modelos tempo-dependente e estado-dependente. O objetivo deste trabalho é levantar algumas evidencias empíricas de modo a distinguir os modelos, ou seja, identificar de que maneira as firmas realmente precificam. Para isso, escolheu-se a grande desvalorização cambial de 1999 como principal ferramenta e ambiente de análise. A hipótese fundamental é que o choque cambial impacta significativamente o custo de algumas indústrias, em alguns casos induzindo-as a alterarem seus preço após o choque. A partir de uma imensa base de micro dados formada por preços que compõem o CPI, algumas estimações importantes como a probabilidade e a magnitude média das trocas foram levantadas. A magnitude é dada por uma média simples, enquanto a probabilidade é estimada pelo método da máxima verossimilhança. Os resultados indicam um comportamento de precificação similar ao proposto por modelos estado-dependente.

Relevância:

100.00% 100.00%

Publicador:

Resumo:

This study aimed to determine if accounting and governance indicators are relevant to foresee the stages of financial stress of companies by using a logistic regression. With the formation of two samples was possible to verify if the inclusion of insolvency data defined by cash flow shortage events were relevant to increase model capacity for prediction of insolvency. The remaining insolvency stages were judicial reorganization and bankruptcy. The control sample is formed by healthy companies, from the same sector and size. The period of analysis includes events that occurred between January 2008 and March 2016. The main variables that showed significant results to predict insolvency states, a year before the event happens, were Profitability, Efficiency and Payment Capacity indicators. The Governance indicator was only significant to predict insolvency arising from judicial reorganization and bankruptcy. Among the models studied, the most accurate model presented total correctness capacity of 88,7%, classifying correctly 88% of solvent companies and 89,3% of insolvent companies. The results indicate the usefulness of financial indicators of Payment Capacity, Efficiency and Profitability, as well as the Governance variable, to discriminate the insolvency of companies.

Relevância:

100.00% 100.00%

Publicador:

Resumo:

A utilização de artefatos de Tecnologias da Informação Móveis e Sem Fio (TIMS) traz consigo alguns paradoxos tecnológicos associados, já identificados na literatura. O aumento do uso de TIMS e suas evoluções acabam por permitir novos tipos de uso e interação junto aos usuários. Tendo como base teorias sobre a existência de paradoxos associados ao uso de equipamentos tecnológicos, mormente TIMS, este estudo buscou aprofundar a relação entre smartphones e profissionais. A partir da coleta de dados por meio de questionário estruturado, esta pesquisa utilizou a análise quantitativa e teve como objetivo determinar a presença e medir a intensidade dos paradoxos tecnológicos, identificados na literatura, quando do uso profissional de smartphones. Outro ponto observado no presente trabalho foi a associação estatística entre esses paradoxos tecnológicos e, ainda, a identificação de fatores que poderiam impactar a percepção desses paradoxos associados ao uso do smartphone pelos profissionais que os utilizam. A análise dos dados permitiu verificar quais dos quatorze paradoxos tecnológicos apresentados por Mick e Fournier (1998), Jarvenpaa e Lang (2005) e Mazmanian et al. (2006) foram percebidos por mais respondentes, com destaque para o paradoxo de autonomia e vício, que foi vivenciado por mais de 85% daqueles que responderam à pesquisa. Usando como base o percentual de respondentes que percebem os paradoxos tecnológicos e considerando suas intensidades, esta dissertação também apresenta um ranking das forças dos paradoxos, determinado pela taxa relativa da força dos paradoxos. Esse ranking traz nas primeiras posições as seguintes ambiguidades: autonomia / vício, engajamento / desengajamento e liberdade / escravidão, respectivamente. Outro apontamento dessa pesquisa foi que nenhum dos paradoxos analisados é estatisticamente independente. Por fim, a realização de uma regressão logística ordinal levou à conclusão que apenas dois dos paradoxos em questão sofrem impacto das variáveis independentes observadas.