Analyse der Prognoseeigenschaften von ifo-Konjunkturindikatoren unter Echtzeitbedingungen / The Forecasting Performance of ifo-indicators Under Real-time Conditions

SummaryIn recent years some papers have been published that deal with the forecasting performance of indicators for the German economy. The real-time aspect, however, was largely neglected. This article analyses the information content of some ifo indicators (the business climate index for the manufacturing sector and its components, the current business situation and business expectations) to predict the German index of production. The analysis is based on cross correlations, Granger causality tests and different out-of-sample forecasts, generated by subset VAR models. First, the out-of-sample forecasts are made, as in conventional studies, with the latest available data and fixed model structure. Afterwards, the out-of-sample indicator properties are analysed in real-time, i.e. with real-time data and variable model structure. In general the indicator properties become worse under real-time conditions. The indicator-based VAR models are not able to beat the forecast performance of a pure autoregressive model for forecast horizons of one and three month. But for forecast horizons of six, nine and twelve months, the indicators seem to be useful in predicting the index of production.

Download Full-text

A neural network extension of the Lee–Carter model to multiple populations

Annals of Actuarial Science ◽

10.1017/s1748499519000071 ◽

2019 ◽

pp. 1-21 ◽

Cited By ~ 7

Author(s):

Ronald Richman ◽

Mario V. Wüthrich

Keyword(s):

Representation Learning ◽

Mortality Rates ◽

Model Structure ◽

Optimal Model ◽

Single Population ◽

Basic Approach ◽

Multiple Populations ◽

Forecasting Performance ◽

Out Of Sample ◽

Carter Model

Abstract The Lee–Carter (LC) model is a basic approach to forecasting mortality rates of a single population. Although extensions of the LC model to forecasting rates for multiple populations have recently been proposed, the structure of these extended models is hard to justify and the models are often difficult to calibrate, relying on customised optimisation schemes. Based on the paradigm of representation learning, we extend the LCmodel to multiple populations using neural networks, which automatically select an optimal model structure. We fit this model to mortality rates since 1950 for all countries in the Human Mortality Database and observe that the out-of-sample forecasting performance of the model is highly competitive.

Download Full-text

Should Forecasters Use Real-Time Data to Evaluate Leading Indicator Models for GDP Prediction? German Evidence

German Economic Review ◽

10.1111/geer.12163 ◽

2019 ◽

Vol 20 (4) ◽

pp. e170-e200 ◽

Cited By ~ 2

Author(s):

Katja Heinisch ◽

Rolf Scheufele

Keyword(s):

Real Time ◽

Optimal Combination ◽

Financial Data ◽

Time Data ◽

Hard Data ◽

Forecasting Performance ◽

Real Time Data ◽

Final Data ◽

Release Data

Abstract In this paper, we investigate whether differences exist among forecasts using real-time or latest-available data to predict gross domestic product (GDP). We employ mixed-frequency models and real-time data to reassess the role of surveys and financial data relative to industrial production and orders in Germany. Although we find evidence that forecast characteristics based on real-time and final data releases differ, we also observe minimal impacts on the relative forecasting performance of indicator models. However, when obtaining the optimal combination of soft and hard data, the use of final release data may understate the role of survey information.

Download Full-text

Prognosegüte alternativer Früh Indikatoren für die Konjunktur in Deutschland / Forecasting Performance of Alternative Indicators for the German Economy

Jahrbücher für Nationalökonomie und Statistik ◽

10.1515/jbnst-2004-0602 ◽

2004 ◽

Vol 224 (6) ◽

Cited By ~ 4

Author(s):

Joachim Benner ◽

Carsten-Patrick Meier

Keyword(s):

German Economy ◽

Forecasting Performance ◽

Out Of Sample

ZusammenfassungUntersuchungen zur Prognosegüte sollten nicht nur Prognosefehler, die auf der Schätzung der Parameter beruhen berücksichtigen, sondern auch solche, die aus der stichprobenabhängigen Auswahl des Prognosemodells resultieren. Wird die Prognosefehlervarianz durch rekursive Out-of-Sample Prognosen geschätzt, so sollte dabei nicht nur die Parameterschätzung, sondern auch die Modellselektion rekursiv vorgenommen werden. Wir wenden dieses Prinzip auf die Analyse der Prognosegüte dreier wichtiger Indikatoren für die Konjunktur in Deutschland an, den vom ifo-Institut erhobenen „Geschäftserwartungen“, den vom Zentrum für Europäische Wirtschaftsforschung veröffentlichten „Konjunkturerwartungen“ und des von der „Wirtschaftswoche“ berechneten „Earlybird“-Indikators. Es zeigt sich, dass die Prognosefehler bei der realistischeren rekursiven Modellauswahl größer sind als bei nicht-rekursiver Spezifikation. Die untersuchten Indikatoren liefern unter bestimmten Umständen bessere Prognosen als ein einfaches autoregressives Modell.

Download Full-text

USING BAIDU INDEX TO NOWCAST MOBILE PHONE SALES IN CHINA

The Singapore Economic Review ◽

10.1142/s021759081743007x ◽

2019 ◽

Vol 64 (01) ◽

pp. 83-96 ◽

Cited By ~ 3

Author(s):

JIANCHUN FANG ◽

WANSHAN WU ◽

ZHOU LU ◽

EUNHO CHO

Keyword(s):

Real Time ◽

Decision Makers ◽

Extended Model ◽

Time Data ◽

Inventory Costs ◽

Marketing Performance ◽

Out Of Sample ◽

Chinese Consumer ◽

Lag Period ◽

Official Data

Most of the official data are released with a lag period, which increases the difficulties for decision-makers assessing the situation. To solve the problem of data lag, we used real-time Baidu Index to nowcast the Chinese consumer behavior of buying the best-selling smartphone, Huawei Mate 7. We introduced keywords like “Mate 7” and “Huawei” in Baidu Index search queries to examine whether the introduction of real-time data can improve the efficiency of benchmark model. Overall, our finding is that the introduction of Baidu Index, both in-sample and out-of-sample, can improve the prediction accuracy of the model significantly. The extended model provided a 55.2% outperformance relative to benchmark one. This can not only make up for official data release lag, but also help firms gain near-real-time insight into the consumer demand trends and reduce inventory costs. The findings suggest that firms can improve marketing performance by use of search engine promotion campaign.

Download Full-text

Do Inflation Expectations Matter for Inflation Forecastability: Evidence from Pakistan

The Pakistan Development Review ◽

10.30541/v55i3pp.211-225 ◽

2016 ◽

Vol 55 (3) ◽

pp. 211-225 ◽

Cited By ~ 2

Author(s):

Fayyaz Hussain ◽

Zafar Hayat

Keyword(s):

Monetary Policy ◽

Predictive Ability ◽

Jel Classification ◽

Inflation Expectations ◽

Forecast Performance ◽

Inflation Forecasts ◽

Forward Guidance ◽

Forecasting Performance ◽

Out Of Sample ◽

Effectiveness Of Monetary Policy

We empirically investigate if the incorporation of inflation expectations helps improve the forecasting performance of a suite of univariate inflation models. Since inflation forecasts are instrumental to the conduct of an effective monetary policy, any possible improvement in the inflation forecastability may tend to enhance the effectiveness of monetary policy—by providing forward guidance both to the monetary authority and the market to effectively anchor inflation expectations. Our results are robust across specifications of our baseline models, sample sizes and forecast horizons. The introduction of inflation expectations, whether contemporaneously or with a 6-months lead improves the predictive ability—both in-sample and out-of-sample for 6 and 12-month horizons. Deterioration however is observed for a 3- month horizon, which point towards the weak representation of the expectations data for a 3- month horizon. JEL Classification: E31, E37 Keywords: Inflation-expectations, Forecast-performance, Pakistan.

Download Full-text

Forecasting exchange rates out-of-sample with panel methods and real-time data

Journal of International Money and Finance ◽

10.1016/j.jimonfin.2013.12.004 ◽

2014 ◽

Vol 43 ◽

pp. 1-18 ◽

Cited By ~ 28

Author(s):

Onur Ince

Keyword(s):

Exchange Rates ◽

Real Time ◽

Time Data ◽

Panel Methods ◽

Real Time Data ◽

Out Of Sample

Download Full-text

Forecasting Exchange Rates Out-of-Sample with Panel Methods and Real-Time Data

CFA Digest ◽

10.2469/dig.v44.n7.2 ◽

2014 ◽

Vol 44 (7) ◽

Author(s):

Biharilal Deora

Keyword(s):

Exchange Rates ◽

Real Time ◽

Time Data ◽

Panel Methods ◽

Real Time Data ◽

Out Of Sample

Download Full-text

Ambulatory Assessment

European Psychologist ◽

10.1027/1016-9040.14.2.109 ◽

2009 ◽

Vol 14 (2) ◽

pp. 109-119 ◽

Cited By ~ 66

Author(s):

Ulrich W. Ebner-Priemer ◽

Timothy J. Trull

Keyword(s):

Real Time ◽

Clinical Psychology ◽

Real Life ◽

Ambulatory Assessment ◽

Computer Assisted ◽

Affective Valence ◽

Time Data ◽

Physiological Processes ◽

Context Specific ◽

Questionnaire Studies

Convergent experimental data, autobiographical studies, and investigations on daily life have all demonstrated that gathering information retrospectively is a highly dubious methodology. Retrospection is subject to multiple systematic distortions (i.e., affective valence effect, mood congruent memory effect, duration neglect; peak end rule) as it is based on (often biased) storage and recollection of memories of the original experience or the behavior that are of interest. The method of choice to circumvent these biases is the use of electronic diaries to collect self-reported symptoms, behaviors, or physiological processes in real time. Different terms have been used for this kind of methodology: ambulatory assessment, ecological momentary assessment, experience sampling method, and real-time data capture. Even though the terms differ, they have in common the use of computer-assisted methodology to assess self-reported symptoms, behaviors, or physiological processes, while the participant undergoes normal daily activities. In this review we discuss the main features and advantages of ambulatory assessment regarding clinical psychology and psychiatry: (a) the use of realtime assessment to circumvent biased recollection, (b) assessment in real life to enhance generalizability, (c) repeated assessment to investigate within person processes, (d) multimodal assessment, including psychological, physiological and behavioral data, (e) the opportunity to assess and investigate context-specific relationships, and (f) the possibility of giving feedback in real time. Using prototypic examples from the literature of clinical psychology and psychiatry, we demonstrate that ambulatory assessment can answer specific research questions better than laboratory or questionnaire studies.

Download Full-text