Modelling Strategies for Repeated Multiple Response Data

This article discusses modelling strategies for repeated measurements of multiple response variables. Such data arise in the context of categorical variables where one can select more than one of the categories as the response. We consider each of the multiple responses as a binary outcome and use a marginal (or population‐averaged) modelling approach to analyse its means. Generalized estimating equations are used to account for different correlation structures, both over time and between items. We also discuss an alternative approach using a generalized linear mixed model with conditional interpretations. We illustrate the methods using data from a panel study in Australia called the Household, Income, and Labour Dynamics Survey.     

Penalized Regression with Ordinal Predictors

Ordered categorial predictors are a common case in regression modelling. In contrast to the case of ordinal response variables, ordinal predictors have been largely neglected in the literature. In this paper, existing methods are reviewed and the use of penalized regression techniques is proposed. Based on dummy coding two types of penalization are explicitly developed; the first imposes a difference penalty, the second is a ridge type refitting procedure. Also a Bayesian motivation is provided. The concept is generalized to the case of non-normal outcomes within the framework of generalized linear models by applying penalized likelihood estimation. Simulation studies and real world data serve for illustration and to compare the approaches to methods often seen in practice, namely simple linear regression on the group labels and pure dummy coding. Especially the proposed difference penalty turns out to be highly competitive.     

Bayesian prior elicitation in DSGE models: Macro- vs micropriors

Bayesian approaches to the estimation of DSGE models are becoming increasingly popular. Prior knowledge is normally formalized either directly on deep parameters' values (‘microprior’) or indirectly, on macroeconomic indicators, e.g. moments of observable variables (‘macroprior’). We introduce a non-parametric macroprior which is elicited from impulse response functions and assess its performance in shaping posterior estimates. We find that using a macroprior can lead to substantially different posterior estimates. We probe into the details of our result, showing that model misspecification is likely to be responsible of that. In addition, we assess to what extent the use of macropriors is impaired by the need of calibrating some hyperparameters.     

Polytomous logistic regression

In this paper a review will be given of some methods available for modelling relationships between categorical response variables and explanatory variables. These methods are all classed under the name polytomous logistic regression (PLR). Models for PLR will be presented and compared; model parameters will be tested and estimated by weighted least squares and by likelihood. Usually, software is needed for computation, and available statistical software is reported.
An industrial problem is solved to some extent as an example to illustrate the use of PLR. The paper is concluded by a discussion on the various PLR-methods and some topics that need a further study are mentioned.     

Calibrating longitudinal models of residential mobility and migration: an assessment of a non-parametric marginal likelihood approach

"This paper discusses the problems of controlling for omitted variables in estimating the structural parameters of longitudinal models and focuses upon an assessment of a non-parametric marginal maximum likelihood approach suggested by the results of Laird....The approach is shown to be statistically valid for a plausible discrete-time model of the incidence of residential or migration moves, at least for data in which no household moves in every time period. Empirical evaluation with two large [U.S.] datasets on residential mobility indicates that the approach is also computationally feasible and provides a promising alternative to more conventional methods for controlling for omitted variables."     

A study of the family service expenditures and the socio-demographic characteristics via fixed marginals correspondence analysis

Our study focuses on two data set, the former provides the expenditures for several services for each family and the latter contains socio-demographic variables for the same statistical units. The main aim is to analyze, in a Correspondence Analysis context, the service expenditure of families based on the whole given data-set under two types of constraints: the global relative expenses for a given service and the global relative expenses for a given socio-demographic category. The purpose of measuring the relationship between expenditure on social services and the socio-demographic characteristics of families is conducted in an exploratory and predictive perspective. A new approach is then introduced which ensures compliance with the required constraints. Moreover, through a procedure, we have obtained a table of regression coefficients. This table shows interesting properties and it is easy to interpret. Finally, the performance of the results has been evaluated using computer-based resampling techniques.     

The wisdom of crowds: The potential of online communities as a tool for data analysis

Online communities have become an important source for knowledge and new ideas. This paper considers the potential of crowdsourcing as a tool for data analysis to address the increasing problems faced by companies in trying to deal with “Big Data”. By exposing the problem to a large number of participants proficient in different analytical techniques, crowd competitions can very quickly advance the technical frontier of what is possible using a given dataset. The empirical setting of the research is Kaggle, the world?s leading online platform for data analytics, which operates as a knowledge broker between companies aiming to outsource predictive modelling competitions and a network of over 100,000 data scientists that compete to produce the best solutions. The paper follows an exploratory case study design and focuses on the efforts by Dunnhumby, the consumer insight company behind the success of the Tesco Clubcard, to find and lever the enormous potential of the collective brain to predict shopper behaviour. By adopting a crowdsourcing approach to data analysis, Dunnhumby were able to extract information from their own data that was previously unavailable to them. Significantly, crowdsourcing effectively enabled Dunnhumby to experiment with over 2000 modelling approaches to their data rather than relying on the traditional internal biases within their R&D units.     

Daily peak electrical load forecasting with a multi-resolution approach

In the context of smart grids and load balancing, daily peak load forecasting has become a critical activity for stakeholders in the energy industry. An understanding of peak magnitude and timing is paramount for the implementation of smart grid strategies such as peak shaving. The modelling approach proposed in this paper leverages high-resolution and low-resolution information to forecast daily peak demand size and timing. The resulting multi-resolution modelling framework can be adapted to different model classes. The key contributions of this paper are (a) a general and formal introduction to the multi-resolution modelling approach, (b) a discussion of modelling approaches at different resolutions implemented via generalised additive models and neural networks, and (c) experimental results on real data from the UK electricity market. The results confirm that the predictive performance of the proposed modelling approach is competitive with that of low- and high-resolution alternatives.     

Forecasting economic time series using score-driven dynamic models with mixed-data sampling

We introduce a mixed-frequency score-driven dynamic model for multiple time series where the score contributions from high-frequency variables are transformed by means of a mixed-data sampling weighting scheme. The resulting dynamic model delivers a flexible and easy-to-implement framework for the forecasting of low-frequency time series variables through the use of timely information from high-frequency variables. We verify the in-sample and out-of-sample performances of the model in an empirical study on the forecasting of U.S. headline inflation and GDP growth. In particular, we forecast monthly headline inflation using daily oil prices and quarterly GDP growth using a measure of financial risk. The forecasting results and other findings are promising. Our proposed score-driven dynamic model with mixed-data sampling weighting outperforms competing models in terms of both point and density forecasts.     

Cumulative and CUB Models for Rating Data: A Comparative Analysis

Ordinal measurements as ratings, preference and evaluation data are very common in applied disciplines, and their analysis requires a proper modelling approach for interpretation, classification and prediction of response patterns. This work proposes a comparative discussion between two statistical frameworks that serve these goals: the established class of cumulative models and a class of mixtures of discrete random variables, denoted as CUB models, whose peculiar feature is the specification of an uncertainty component to deal with indecision and heterogeneity. After surveying their definition and main features, we compare the performances of the selected paradigms by means of simulation experiments and selected case studies. The paper is tailored to enrich the understanding of the two approaches by running an extensive and comparative analysis of results, relative advantages and limitations, also at graphical level. In conclusion, a summarising review of the key issues of the alternative strategies and some final remarks are given, aimed to support a unifying setting.     

Consumer preferences and demand systems

This paper is an up-to-date survey of the state-of-the-art in consumer demand modelling. We review and evaluate advances in a number of related areas, including different approaches to empirical demand analysis, such as the differential approach, the locally flexible functional forms approach, the semi-non-parametric approach, and a non-parametric approach. We also address estimation issues, including sampling theoretic and Bayesian estimation methods, and discuss the limitations of the currently common approaches. We also highlight the challenge inherent in achieving economic regularity, for consistency with the assumptions of the underlying neoclassical economic theory, as well as econometric regularity, when variables are nonstationary.     

Asset Pricing with Observable Stochastic Discount Factors

The stochastic discount factor model provides a general framework for pricing assets. By specifying the discount factor suitably it encompasses most of the theories currently in use, including CAPM and consumption CAPM. The SDF model has been based on the use of single and multiple factors, and on latent and observed factors. In most situations, and especially for the term structure, single factor models are inappropriate, whilst latent variables require the somewhat arbitrary specification of generating processes and are difficult to interpret. In this paper we survey the principal different implementations of the SDF model for bonds, equity and FOREX and propose a new approach. This is based on the use of multiple factors that are observable and modelling the joint distribution of excess returns and the factors using a multi–variate GARCH–in–mean process. We argue that in general single equation and VAR models, although widely used in empirical finance, are inappropriate as they do not satisfy the no–arbitrage condition. Since risk premia arise from conditional covariation between the returns and the factors, both a multi–variate context and having conditional covariances in the conditional mean process, is essential. We explain how apparent exceptions, such as the CIR and Vasicek models, in fact meet this requirement — but at a price. We explain our new approach, discuss how it might be implemented and present some empirical evidence, mainly from our own researches. Partly, to enable comparisons to be made, the survey also includes evidence from recent empirical work using more traditional approaches.     

Multivariate Small Area Estimation of Multidimensional Latent Economic Well-being Indicators

Factor analysis models are used in data dimensionality reduction problems where the variability among observed variables can be described through a smaller number of unobserved latent variables. This approach is often used to estimate the multidimensionality of well-being. We employ factor analysis models and use multivariate empirical best linear unbiased predictor (EBLUP) under a unit-level small area estimation approach to predict a vector of means of factor scores representing well-being for small areas. We compare this approach with the standard approach whereby we use small area estimation (univariate and multivariate) to estimate a dashboard of EBLUPs of the means of the original variables and then averaged. Our simulation study shows that the use of factor scores provides estimates with lower variability than weighted and simple averages of standardised multivariate EBLUPs and univariate EBLUPs. Moreover, we find that when the correlation in the observed data is taken into account before small area estimates are computed, multivariate modelling does not provide large improvements in the precision of the estimates over the univariate modelling. We close with an application using the European Union Statistics on Income and Living Conditions data.     

Choice Modelling Approaches: A Superior Alternative for Environmental Valuatioin?

In this paper, we examine some popular 'choice modelling' approaches to environmental valuation, which can be considered as alternatives to more familiar valuation techniques based on stated preferences such as the contingent valuation method. A number of choice modelling methods are consistent with consumer theory, and its focus on an attribute‐based theory of value permits a superior representation of many environmental management contexts. However, choice modelling surveys can place a severe cognitive burden upon respondents and induce satisficing rather than maximising behavioural patterns. In this framework, we seek to identify the best available choice modelling alternative and investigate its potential to 'solve' some of the major biases associated with standard contingent valuation. We then discuss its use in the light of policy appraisal needs within the EU. An application to the demand for rock climbing in Scotland is provided as an illustration.     

Cognitive interviewing and factor-analytic techniques: a mixed method approach to validity of survey items measuring national identity

This paper explores the possibilities of method triangulation between two methodological approaches for assessing the validity performance of survey items: cognitive interviewing and factor analytic techniques. Although their means of approaching validity differ, both methods attempt to prove whether a measure corresponds to a theoretical (latent) concept (e.g. patriotism vs. nationalism), thus both are concerned with the question, whether an indicator measures what it is supposed to measure. Based on two representative samples for Austria [data gathered within the framework of the International Social Survey Program (ISSP) on National Identity in 1995 and 2003] and 18 cognitive interviews conducted between 2003 and 2005, the paper shows the considerable advantages of using a multi-method approach for ensuring the quality of survey items. On the one hand, we apply exploratory and confirmatory factor analysis in order to identify poorly performing indicators with regard to validity and reliability. On the other hand, the analysis of the cognitive interviews reveals the substantial sources of response error. Results show that to a large extent, respondents do not understand the items that have been defined to measure national identification and related concepts in Austria the way intended by the drafting group of this ISSP Module, a fact that has considerable implications on the scales’ predictive power.     

Macroeconomic forecasting using penalized regression methods

We study the suitability of applying lasso-type penalized regression techniques to macroe-conomic forecasting with high-dimensional datasets. We consider the performances of lasso-type methods when the true DGP is a factor model, contradicting the sparsity assumptionthat underlies penalized regression methods. We also investigate how the methods handle unit roots and cointegration in the data. In an extensive simulation study we find that penalized regression methods are more robust to mis-specification than factor models, even if the underlying DGP possesses a factor structure. Furthermore, the penalized regression methods can be demonstrated to deliver forecast improvements over traditional approaches when applied to non-stationary data that contain cointegrated variables, despite a deterioration in their selective capabilities. Finally, we also consider an empirical applicationto a large macroeconomic U.S. dataset and demonstrate the competitive performance of penalized regression methods.     

Regression Revisited

Sir Francis Galton introduced median regression and the use of the quantile function to describe distributions. Very early on the tradition moved to mean regression and the universal use of the Normal distribution, either as the natural ‘error’ distribution or as one forced by transformation. Though the introduction of ‘quantile regression’ refocused attention on the shape of the variability about the line, it uses nonparametric approaches and so ignores the actual distribution of the ‘error’ term. This paper seeks to show how Galton's approach enables the complete regression model, deterministic and stochastic elements, to be modelled, fitted and investigated. The emphasis is on the range of models that can be used for the stochastic element. It is noted that as the deterministic terms can be built up from components, so to, using quantile functions, can the stochastic element. The model may thus be treated in both modelling and fitting as a unity. Some evidence is presented to justify the use of a much wider range of distributional models than is usually considered and to emphasize their flexibility in extending regression models.     

Advances in Joint Modelling: A Review of Recent Developments with Application to the Survival of End Stage Renal Disease Patients

The use of joint modelling approaches is becoming increasingly popular when an association exists between survival and longitudinal processes. Widely recognized for their gain in efficiency, joint models also offer a reduction in bias compared with naïve methods. With the increasing popularity comes a constantly expanding literature on joint modelling approaches. The aim of this paper is to give an overview of recent literature relating to joint models, in particular those that focus on the time‐to‐event survival process. A discussion is provided on the range of survival submodels that have been implemented in a joint modelling framework. A particular focus is given to the recent advancements in software used to build these models. Illustrated through the use of two different real‐life data examples that focus on the survival of end‐stage renal disease patients, the use of the JM and joineR packages within R are demonstrated. The possible future direction for this field of research is also discussed.     

Alternative Approaches to Multilevel Modelling of Survey Non‐Contact and Refusal

We review three alternative approaches to modelling survey non‐contact and refusal: multinomial, sequential, and sample selection (bivariate probit) models. We then propose a multilevel extension of the sample selection model to allow for both interviewer effects and dependency between non‐contact and refusal rates at the household and interviewer level. All methods are applied and compared in an analysis of household non‐response in the United Kingdom, using a data set with unusually rich information on both respondents and non‐respondents from six major surveys. After controlling for household characteristics, there is little evidence of residual correlation between the unobserved characteristics affecting non‐contact and refusal propensities at either the household or the interviewer level. We also find that the estimated coefficients of the multinomial and sequential models are surprisingly similar, which further investigation via a simulation study suggests is due to non‐contact and refusal having largely different predictors.     

Automated Model Selection in Finance: General‐to‐Specific Modelling of the Mean and Volatility Specifications*

General‐to‐Specific (GETS) modelling has witnessed major advances thanks to the automation of multi‐path GETS specification search. However, the estimation complexity associated with financial models constitutes an obstacle to automated multi‐path GETS modelling in finance. Making use of a recent result we provide and study simple but general and flexible methods that automate financial multi‐path GETS modelling. Starting from a general model where the mean specification can contain autoregressive terms and explanatory variables, and where the exponential volatility specification can include log‐ARCH terms, asymmetry terms, volatility proxies and other explanatory variables, the algorithm we propose returns parsimonious mean and volatility specifications.