|
on Econometrics |
| By: | Xiaohong Chen (New York University); Yingyao Hu (University of Texas at Austin) |
| Abstract: | This paper considers identification and inference of a general latent nonlinear model using two samples, where a covariate contains arbitrary measurement errors in both samples, and neither sample contains an accurate measurement of the corresponding true variable. The primary sample consists of some dependent variables, some error-free covariates and an error-ridden covariate, where the measurement error has unknown distribution and could be arbitrarily correlated with the latent true values. The auxiliary sample consists of another noisy measurement of the mismeasured covariate and some error-free covariates. We first show that a general latent nonlinear model is nonparametrically identified using the two samples when both could have nonclassical errors, with no requirement of instrumental variables nor independence between the two samples. When the two samples are independent and the latent nonlinear model is parameterized, we propose sieve quasi maximum likelihood estimation (MLE) for the parameter of interest, and establish its root-n consistency and asymptotic normality under possible misspecification, and its semiparametric efficiency under correct specification. We also provide a sieve likelihood ratio model selection test to compare two possibly misspecified parametric latent models. A small Monte Carlo simulation and an empirical example are presented. |
| Keywords: | Data combination, Nonlinear errors-in-variables model, Nonclassical measurement error, Nonparametric identification, Misspecified parametric latent model, Sieve likelihood estimation and inference |
| JEL: | C14 |
| Date: | 2006–11 |
| URL: | http://d.repec.org/n?u=RePEc:cwl:cwldpp:1590&r=ecm |
| By: | George Kapetanios (Queen Mary, University of London); Massimiliano Marcellino (IEP-Bocconi University, IGIER and CEPR) |
| Abstract: | This paper analyses the use of factor analysis for instrumental variable estimation when the number of instruments tends to infinity. We consider cases where the unobserved factors are the optimal instruments but also cases where the factors are not necessarily the optimal instruments but can provide a summary of a large set of instruments. Further, the situation where many weak instruments exist is also considered in the context of factor models. Theoretical results, simulation experiments and empirical applications highlight the relevance and simplicity of Factor-GMM estimation. |
| Keywords: | Factor models, Principal components, Instrumental variables, GMM, Weak instruments, DSGE models |
| JEL: | C32 C51 E52 |
| Date: | 2006–10 |
| URL: | http://d.repec.org/n?u=RePEc:qmw:qmwecw:wp577&r=ecm |
| By: | Luc, BAUWENS (UNIVERSITE CATHOLIQUE DE LOUVAIN, Department of Economics); Michel, LUBRANO |
| Abstract: | We review Bayesian inference for dynamic latent variable models using the data augmentation principle. We detail the difficulties of stimulating dynamic latent variables in a Gibbs sampler. We propose an alternative specification of the dynamic disequilibrium model which leads to a simple simulation procedure and renders Bayesian inference fully operational. Identification issues are discussed. We conduct a specification search using the posterior deviance criterion of Spiegelhalter, Best, Carlin, and van der Linde (2002) for a disequilibrium model of the Polish credit market. |
| Keywords: | Latent variables, Disequilibrium models, Bayesian inference, Gibbs sampler, Credit rationing |
| JEL: | C11 C32 C34 E51 |
| Date: | 2006–05–23 |
| URL: | http://d.repec.org/n?u=RePEc:ctl:louvec:2006027&r=ecm |
| By: | Antonello D'Agostino (Central Bank and Financial Services Authority of Ireland - Economic Analysis and Research Department, PO Box 559 - Dame Street, Dublin 2, Ireland.); Domenico Giannone (ECARES, Universit Libre de Bruxelles - CP 114 - av. Jeanne, 44, B-1050, Brussels, Belgium.) |
| Abstract: | This paper compares the predictive ability of the factor models of Stock and Watson (2002) and Forni, Hallin, Lippi, and Reichlin (2005) using a "large" panel of US macroeconomic variables. We propose a nesting procedure of comparison that clarifies and partially overturns the results of similar exercises in the literature. As in Stock and Watson (2002), we find that efficiency improvements due to the weighting of the idiosyncratic components do not lead to significant more accurate forecasts. In contrast to Boivin and Ng (2005), we show that the dynamic restrictions imposed by the procedure of Forni, Hallin, Lippi, and Reichlin (2005) are not harmful for predictability. Our main conclusion is that for the dataset at hand the two methods have a similar performance and produce highly collinear forecasts. JEL Classification: C31, C52, C53. |
| Keywords: | Factor Models, Forecasting, Large Cross-Section. |
| Date: | 2006–10 |
| URL: | http://d.repec.org/n?u=RePEc:ecb:ecbwps:20060680&r=ecm |
| By: | Agostino Consolo |
| Abstract: | The aim of this paper is to forecast some of the most important measures of inflation of the Estonian economy by making use of linear and non-linear models. Results from comparing classes of optimal models are similar to those in the forecasting literature. In particular, there are gains from using more sophisticated methods such as factor analysis and time-varying parameters methods. Model discrimination is based on evaluation criteria which are computed by a real-time dynamic estimation procedure. Moreover, forecasts uncertainty is appropriately taken into account: Fan Charts can exhaustively describe the final output for what concerns out-of-sample forecasting. |
| Keywords: | Estonian Economy, forecasting, inflation modelling |
| JEL: | C22 C32 C53 E31 |
| Date: | 2006–10–10 |
| URL: | http://d.repec.org/n?u=RePEc:eea:boewps:wp2006-03&r=ecm |
| By: | Davis, Peter J |
| Abstract: | In this paper I develop the Discrete Choice Analytically Flexible (DCAF) model of demand for differentiated products. DCAF relaxes the constraints imposed on the matrix of own- and cross-price elasticities of demand by popular analytic discrete choice models such as the Multinomial Logit (MNL) and Nested MNL models. At the same time, in contrast to models such as Probit (Hausman and Wise (1978)) and Random Coefficient-MNL (RC-MNL) models (Berry, Levinsohn and Pakes (1995)), DCAF does not require estimation via simulation; it is fully analytic. I show DCAF is a flexible functional form in the sense of Diewert (1974), thus ensuring that its parameters can be chosen to match a well defined class of possible own- and cross-price elasticities of demand. Under well defined constraints on the parameters, which may or may not be imposed in estimation, DCAF is shown to be a previously unexplored member of Mcfadden's(1978) class of Multivariate Extreme Value (MEV) discrete choice models. Hence, under testable parameter restrictions, DCAF is fully consistent with an underlying structural model of heterogeneous, utility maximizing, consumers. I provide a small monte-carlo study to illustrate use of the model and establish its properties. A full application of the model using data from the UK confectionary market is provided in the companion paper, Davis (2006). |
| Keywords: | demand; demand models; discrete choice; extreme value |
| JEL: | C0 C3 D1 L0 |
| Date: | 2006–10 |
| URL: | http://d.repec.org/n?u=RePEc:cpr:ceprdp:5880&r=ecm |
| By: | Otter, Pieter W.; Jacobs, Jan P.A.M. (Groningen University) |
| Abstract: | This paper employs concepts from information theory in factor models. We show that in the exact factor model the whole distribution of eigenvalues of the covariance matrix contributes to the information and not only the largest ones. In addition, we derive the condition that the first q say eigenvalues diverge whereas the rest remain bounded in the static model rather than having to assume it. Finally, we calculate information in static and dynamic factor models, which can be used to find the dimensions of the factor space. We illustrate the concepts with simulation experiments. |
| Date: | 2006 |
| URL: | http://d.repec.org/n?u=RePEc:dgr:rugccs:200605&r=ecm |
| By: | Eliana González; Miguel I. Gómez; Luis F. Melo; José Luis Torres |
| Abstract: | Many developing countries are adopting inflation targeting regimes to guide monetary policy decisions. In such countries the share of food in the consumption basket is high and policy makers often employ total inflation (as opposed to core inflation) to set inflationary targets. Therefore, central banks need to develop reliable models to forecast food inflation. Our literature review suggests that little has been done in the construction of models to forecast short-run food inflation in developing countries. We develop a model to improve short-run food inflation forecasts in Colombia. The model disaggregates food items according to economic theory and employs Flexible Least Squares given the presence of structural changes in the inflation series. We compare the performance of this new model to current models employed by the central bank. Next, we apply econometric methods to combine forecasts from alternative models and test whether such combination outperforms individual models. Our results indicate that forecasts can be improved by classifying food basket items according to unprocessed, processed and food away from home and by employing forecast combination techniques. |
| Date: | 2006–10–20 |
| URL: | http://d.repec.org/n?u=RePEc:col:001043:002681&r=ecm |
| By: | Jeremy Clark (University of Canterbury); Lana Friesen |
| Abstract: | CV researchers have found that the hypothetical values respondents place on a nested sequence of environmental goods are sensitive to the order in which the goods are presented. Typically, the smallest bundle of goods is valued more highly if presented first than if following more comprehensive bundles. Such effects appear even when each bundle is valued from an "exclusive" list, or as an alternative to any other, so that income and substitution effects are controlled. Order of presentation has also affected the degree to which values are sensitive to scope. We conduct lab experiments where participants are asked to value sequences of nested goods for actual purchase from an exclusive list using the incentive compatible BDM mechanism. We test whether order effects occur in valuation for a) induced value goods, b) actual private goods, and c) identical private goods that are to be donated to charities. We find significant order effects when the goods are valued for own use, but not when they are valued for donation. |
| Keywords: | Order effects; exclusive list; warm glow; contingent valuation |
| Date: | 2006–01–16 |
| URL: | http://d.repec.org/n?u=RePEc:cbt:econwp:06/06&r=ecm |