Dynamic Modeling

Forecasting models using business surveys

The identification of the current state in the business cycle and the forecast of the next quarters do not only receive a lot of attention in the public, they are also of prime importance for the plans of firms and the government. The most important leading indicator for the German economy is the ifo Business Climate Index that is based on a monthly business survey with more than 7,000 respondents. Due to the large number of firms, the results can be analysed at a disaggregate level for the different sectors, firms and response categories. Thus, it is possible to use a panel of sector-specific survey indices in order to forecast the sectoral gross value added or to examine whether they are leading important aggregate variables like total gross value added or gross domestic product (GDP).
A number of questions are of interest:

Are there sectors or firms that have stable leading properties to the target series?
Are there interactions between sectors or firms that attenuate or intensify the original signal?
What is the delay with which firms react to macroeconomic impulses? What explanations can be found?

Due to the large number of possible lead-lag relationships and the additional difficulty of time-varying structures it seems necessary to pre-select factors that are relevant for the question of interest. Modern selection methods such as parametric and nonparametric boosting or random forests can be adapted to the problem at hand.

Carstensen, Tutz

Modelling of sojourn time

The modelling of sojourn time is crucial for grasping the dynamics of response behavior in panel surveys. Especially the Ifo Business Survey, that is conducted monthly among 7,000 participating firms, is an excellent basis for the analysis of nonresponse behaviour in business surveys because it can build on an enormous data set. The main research tasks that can be answered by means of business surveys concern nonresponse behavior and expectations at the firm level. Nonresponse considerably influences the stability of the data and can create a bias in the results. While severals analyses of the issue are available for individual and houshold surveys, there is little research on processes and sources of compliance in business surveys. The main factors responsible for "panel fatigue", i.e. a decreasing compliance over time, can be used to improve the quality and uncover present selectivity. At the firm level, the analysis of expectations is of special interest, particularly because current macroeconomic models emphasize the importance of expectations to explain business cycle dynamics. However, it often turns out empirically that the standard assumption of rational expectations does not hold. Since the surveys of the ifo Institute also contain expectational categories, they allow a deeper analysis of the process of expectation formation. An interesting question is in how far current expectations correlate and interact with previous expectations and other response categories, especially with future realisations.

Methodological problems for the ifo data arise from the fact that the responses of the enterprises are given in categorical form (e.g., “better”, “unchanged”, “worse”). In the corresponding competing risk approaches, the question needs to be evaluated whether the monthly survey allows for discrete or continuous modelling. In general, the empirical analysis of sojourn time data often shows that the effect of influencing variables varies over time. Ignoring these effects often results in artificial effect sizes and reduced prediction accuracy. In order to model these variations adequately, it is necessary to incorporate time-varying effects in nonparametric form. This leads to severe selection problems: which variables should be modelled parametrically to be time-constant, which nonparametrically to be time-varying. The selection problems are to be solved by means of modern selection techniques like the Lasso and Boosting. Especially the generalization to multi-state models and the modelling of heterogeneity is of substantial interest for the intended analysis of the ifo business survey as well as other econometric and sociological surveys.

On the infrastructural integration of the project
The Economics & Business Data Center provides a large data base of German firms that merges data from different sources. In particular, ifo Business Survey data are merged with balance sheet data or data on the governance structure of firms and is thus an excellent basis for research in this field. The analysis of nonparametric modelling was part of the project C4 Semi- and Nonparametric Modelling within the framework of SFB 386 (project director G. Tutz). The analysis of Ifo microdata and of improved forecast indicators is part of the research programme in the department Business Cycle Analyses and Surveys of the ifo Institute.

Carstensen, Tutz

Dynamic modeling of financial and real economical interactions

The aim of the project is to investigate dependency structures in hybrid capital and insurance markets. In order to find alternative ways of securitizing risks, insurance companies have tried to take advantage of the vast potential of capital markets by introducing exchange-traded insurance-linked instruments such as mortality derivatives or catastrophe insurance options. At the same time, insurance products such as unit-linked life insurance or payment protection insurance, where the insurance benefits depend on the price of some specific traded stocks or some macro-economic factors like unemployment, combine traditional forms of insurance with economic and financial aspects. Hence insurance and financial markets may no longer be viewed as disjoint objects, but have to be studied as one big hybrid market for which the dependence structures need to be properly understood. A major concern of this project is then to model and calibrate appropriate pricing, hedging and risk measurement schemes. The particularly interesting class of time-continuous, doubly stochastic multi-state Markov chain models provides a mathematical and statistical framework for analysing intensity- or hazard rate processes. Limited data width for example due to privacy restrictions in labor force data, require for efficient solutions of disaggregating aggregate information or cluster and dependence analysis. A large interest in this context is to analyse data concerning macroeconomic factors.
Close cooperations with IAB, the IFO Institute, the Center for Quantitative Risk Analysis (CEQURA) and the Munich Risk and Insurance Center (MRIC) will be pursued, as they are specialized in research areas relevant for the success of this project.

Mittnik, Biagini, Carstensen