Search Results
Report
Model selection criteria for factor-augmented regressions
In a factor-augmented regression, the forecast of a variable depends on a few factors estimated from a large number of predictors. But how does one determine the appropriate number of factors relevant for such a regression? Existing work has focused on criteria that can consistently estimate the appropriate number of factors in a large-dimensional panel of explanatory variables. However, not all of these factors are necessarily relevant for modeling a specific dependent variable within a factor-augmented regression. This paper develops a number of theoretical conditions that selection ...
Working Paper
A one-covariate at a time, multiple testing approach to variable selection in high-dimensional linear regression models
Model specification and selection are recurring themes in econometric analysis. Both topics become considerably more complicated in the case of large-dimensional data sets where the set of specification possibilities can become quite large. In the context of linear regression models, penalised regression has become the de facto benchmark technique used to trade off parsimony and fit when the number of possible covariates is large, often much larger than the number of available observations. However, issues such as the choice of a penalty function and tuning parameters associated with the use ...
Working Paper
Big data analytics: a new perspective
Model specification and selection are recurring themes in econometric analysis. Both topics become considerably more complicated in the case of large-dimensional data sets where the set of specification possibilities can become quite large. In the context of linear regression models, penalised regression has become the de facto benchmark technique used to trade off parsimony and fit when the number of possible covariates is large, often much larger than the number of available observations. However, issues such as the choice of a penalty function and tuning parameters associated with the use ...
Working Paper
Deep Neural Network Estimation in Panel Data Models
In this paper we study neural networks and their approximating power in panel data models. We provide asymptotic guarantees on deep feed-forward neural network estimation of the conditional mean, building on the work of Farrell et al. (2021), and explore latent patterns in the cross-section. We use the proposed estimators to forecast the progression of new COVID-19 cases across the G7 countries during the pandemic. We find significant forecasting gains over both linear panel and nonlinear time-series models. Containment or lockdown policies, as instigated at the national level by governments, ...
Report
Revisiting useful approaches to data-rich macroeconomic forecasting
This paper analyzes the properties of a number of data-rich methods that are widely used in macroeconomic forecasting, in particular principal components (PC) and Bayesian regressions, as well as a lesser-known alternative, partial least squares (PLS) regression. In the latter method, linear, orthogonal combinations of a large number of predictor variables are constructed such that the covariance between a target variable and these common components is maximized. Existing studies have focused on modelling the target variable as a function of a finite set of unobserved common factors that ...
Report
Parsimonious estimation with many instruments
We suggest a way to perform parsimonious instrumental variables estimation in the presence of many, and potentially weak, instruments. In contrast to standard methods, our approach yields consistent estimates when the set of instrumental variables complies with a factor structure. In this sense, our method is equivalent to instrumental variables estimation that is based on principal components. However, even if the factor structure is weak or nonexistent, our method, unlike the principal components approach, still yields consistent estimates. Indeed, simulations indicate that our approach ...