A new class of statistical methods for analysing long memory time series models with heteroskedasticity. This project will result in a class of statistical methods that will aid policy makers and financial analysts when examining and predicting key international and Australian macroeconomic and financial variables that exhibit long memory. Leading applications of long memory modelling in the literature include GDP, CPI, asset pricing models, stock returns, exchange rates and interest rates. It w ....A new class of statistical methods for analysing long memory time series models with heteroskedasticity. This project will result in a class of statistical methods that will aid policy makers and financial analysts when examining and predicting key international and Australian macroeconomic and financial variables that exhibit long memory. Leading applications of long memory modelling in the literature include GDP, CPI, asset pricing models, stock returns, exchange rates and interest rates. It will be possible to robustly and efficiently analyse such series in the presence of changes in variability, such as the overall reduction in variability that has occurred since the 1970's, called the "Great Moderation". The utility of the new methods will be demonstrated by a robust and efficient analysis of the Purchasing Power Parity hypothesis.Read moreRead less
Fractional Integration, Power Laws and Econometric Models: Some Methodological and Theoretical Developments. The fundamental objectives of this project are to: (i) Extend
current econometric practice and consider the use of power laws as
a basis for the construction of a more flexible and realistic
class of models for the analysis of economic and financial time
series. (ii) To develop inferential techniques appropriate for the
modelling of dynamic econometric systems that incorporate
struc ....Fractional Integration, Power Laws and Econometric Models: Some Methodological and Theoretical Developments. The fundamental objectives of this project are to: (i) Extend
current econometric practice and consider the use of power laws as
a basis for the construction of a more flexible and realistic
class of models for the analysis of economic and financial time
series. (ii) To develop inferential techniques appropriate for the
modelling of dynamic econometric systems that incorporate
structure characterized by power laws. This will be achieved by
building upon the class of fractionally integrated processes. New
econometric models and methodologies for the analysis of
non-stationarity series will be developed, along with the
associated theoretical results.Read moreRead less
New Procedures for Multiple Testing of Econometric Models. In discipline areas ranging from biological and medicine sciences to economics and commerce, very important decisions are made on the basis of statistical or econometric models. There is usually a high degree of uncertainty about the exact form the model should take and the data available to help decide on the best form of the model is often limited. The new procedures developed in this project will help statisticians and econometricians ....New Procedures for Multiple Testing of Econometric Models. In discipline areas ranging from biological and medicine sciences to economics and commerce, very important decisions are made on the basis of statistical or econometric models. There is usually a high degree of uncertainty about the exact form the model should take and the data available to help decide on the best form of the model is often limited. The new procedures developed in this project will help statisticians and econometricians make better decisions about the best form of their models. Our approach gives a new method of validating an estimated model before it is put to use to make critical decisions.Read moreRead less
Nonparametric estimation of regression models with unknown error distributions. In discipline areas ranging from bioinformatics to economics and commerce, researchers make important decisions based on regression models, where the error density is often unknown. This project will result in a new sampling procedure that aims to choose bandwidth parameters for estimating the regression function and error density in nonparametric regression models. Our approach is of practical importance and can be ....Nonparametric estimation of regression models with unknown error distributions. In discipline areas ranging from bioinformatics to economics and commerce, researchers make important decisions based on regression models, where the error density is often unknown. This project will result in a new sampling procedure that aims to choose bandwidth parameters for estimating the regression function and error density in nonparametric regression models. Our approach is of practical importance and can be used to investigate relationships between variables that are observable in our economy and community. The nation will benefit from the output of this project by having its own experts in the area of proposed research, raising Australia's academic profile in econometrics and statistics. Read moreRead less
Econometric estimation and analysis of country, regional and global income distributions. The project will provide valuable information on characteristics of the income distribution for Australia, and the distributions for countries of socio-economic significance to Australia. The findings will enable Australian government and non-government organisations and international agencies to assess the effects of various policies such as those designed to reduce world poverty. The project can help Aust ....Econometric estimation and analysis of country, regional and global income distributions. The project will provide valuable information on characteristics of the income distribution for Australia, and the distributions for countries of socio-economic significance to Australia. The findings will enable Australian government and non-government organisations and international agencies to assess the effects of various policies such as those designed to reduce world poverty. The project can help Australia understand the most immediate needs of countries in the region, information that is useful for formulating Australian policy responses that can alleviate poverty and lead to improved living standards in the region, thereby creating a harmonious and safer environment within the Asia-Pacific region.Read moreRead less
Persistence in Economic Time Series: Interpretation, Measurement and Inference. An economic time series is said to be persistent if shocks to the series have a permanent effect. Accurate and unambiguous inferences regarding persistence are crucial to an understanding of the response of the variable to shocks, in particular to policy-induced shocks. In this project we will explore new ways of interpreting, measuring and conducting inference on persistence. The aim is to produce significant theor ....Persistence in Economic Time Series: Interpretation, Measurement and Inference. An economic time series is said to be persistent if shocks to the series have a permanent effect. Accurate and unambiguous inferences regarding persistence are crucial to an understanding of the response of the variable to shocks, in particular to policy-induced shocks. In this project we will explore new ways of interpreting, measuring and conducting inference on persistence. The aim is to produce significant theoretical and methodological advances which, when applied to empirical problems, will enable reliable conclusions to be drawn regarding the propagation of shocks and, hence, the likely impact of interventionist government policies.Read moreRead less
Non-parametric estimation of forecast distributions in non-Gaussian state space models. The production of accurate forecasts is arguably one of the most challenging tasks in economics, business and finance, where data often assume strictly positive, integer or binary values, or are characterized by many extreme values far from the average. This project will produce new, state-of-the-art statistical methods for generating accurate estimates of the probabilities attached to different possible futu ....Non-parametric estimation of forecast distributions in non-Gaussian state space models. The production of accurate forecasts is arguably one of the most challenging tasks in economics, business and finance, where data often assume strictly positive, integer or binary values, or are characterized by many extreme values far from the average. This project will produce new, state-of-the-art statistical methods for generating accurate estimates of the probabilities attached to different possible future values of such variables. Although far-ranging in scope, the techniques advocated will have particular impact in the financial sphere, where the concept of future risk is inextricably linked to the probability of occurrence of extreme values and, hence, to the future probability distribution of the financial variable. Read moreRead less
Effects of Maternal Work, Day Care Use and Other Investments in Children on Child Cognitive Outcomes. Later life outcomes due to investments by individuals and/or society in children is crucial to many countries, including Australia. Appropriate policy responses require reliable and valid estimates of the likely effects of individual investments and policy interventions. Despite many research reports on this topic, almost all do not control for selection bias (eg, high achieving mothers tend to ....Effects of Maternal Work, Day Care Use and Other Investments in Children on Child Cognitive Outcomes. Later life outcomes due to investments by individuals and/or society in children is crucial to many countries, including Australia. Appropriate policy responses require reliable and valid estimates of the likely effects of individual investments and policy interventions. Despite many research reports on this topic, almost all do not control for selection bias (eg, high achieving mothers tend to put children in day care), which is a feature of our work. Thus, our empirical results will have major policy implications, and will suggest ways to obtain similar results for Australian environments. Read moreRead less
Efficient pooling of cross-section and time series data using Bayesian machine learning with two econometric applications. In this project, we adapt a Bayesian modelling strategy, namely the minimum message length principle, to the problem of efficient partitioning of economic units, such as firms or countries, into groups whose behavioural patterns are similar within each group but distinct across groups. This methodology can incorporate the requirements of economic theory. The resulting softwa ....Efficient pooling of cross-section and time series data using Bayesian machine learning with two econometric applications. In this project, we adapt a Bayesian modelling strategy, namely the minimum message length principle, to the problem of efficient partitioning of economic units, such as firms or countries, into groups whose behavioural patterns are similar within each group but distinct across groups. This methodology can incorporate the requirements of economic theory. The resulting software will be developed for the Web. We consider two specific applications, namely modelling gasoline demand in OECD countries, and finding the foreign factor with the most predictive power for the growth rate of the Australian economy. The second application is of considerable national interest.Read moreRead less
Modelling a portfolio of financial assets: structure, estimation, testing and forecasting. Information regarding financial returns and risk is essential for optimal portfolio selection and asset management. Returns and risk have typically been analysed for individual assets. The project provides a theoretical solution to the important practical problem of modelling a portfolio of financial assets in realistic situations. The significance of the research is the development of a new approach to an ....Modelling a portfolio of financial assets: structure, estimation, testing and forecasting. Information regarding financial returns and risk is essential for optimal portfolio selection and asset management. Returns and risk have typically been analysed for individual assets. The project provides a theoretical solution to the important practical problem of modelling a portfolio of financial assets in realistic situations. The significance of the research is the development of a new approach to analyse a portfolio of returns and risk, and the determination of its applicability using numerical simulation techniques. The expected outcomes are an optimal practical method for analysing a portfolio of assets, a scientific monograph, and publications in leading international journals.Read moreRead less