Abstract
A necessary competence in the present-day reality is the ability to analyze big data in the economy, and therefore one of the key issues is the choice of tools for such analysis. One of the most promising tools is nowcasting, which allows you to accurately determine economic changes in very short time periods. The aim of the study is to analyze successful modern practices of using nowcasting for statistical forecasting of socio-economic indicators. The hypothesis of the research lies in the assumption that nowcasting as a method of macroeconomic analysis can in the near future become a worthy alternative to traditional methods of analysis and statistical forecasting of indicators of socio-economic development, increasing the accuracy of their forecasting. The methodological basis of the study was the scientific works and applied developments of leading domestic and foreign scientists in the field of economic forecasting using statistics of search queries, as well as methods of comparative and statistical analysis, and the systematic approach. The novelty of the results obtained lies in the systematization and description of successful practices of using nowcasting and forecasting indicators using query statistics. The study highlights the basic principle of nowcasting, which is to obtain a more accurate assessment of the state of the economy as new data becomes available. It also describes the key statistical models used as tools for testing in foreign countries. As a result of the study, we highlight the importance of the analysis of statistical search queries, especially in the context of their correlation with classical survey metrics and general statistics. It is in an active phase of development, especially within the framework of the domestic forecasting practice. The results obtained can be applied both in a corporate environment and in the public sector to build macroeconomic forecasts.
Highlights
In this paper, we estimate an approximate dynamic factor model (DFM) for Canada and evaluate its nowcasting performance for Canadian gross domestic product (GDP)
We find that US variables, such as employment and Institute for Supply Management business surveys, are important predictors for nowcasting Canadian GDP growth
A recent paper by Bragoli and Modugno (2016) constructs a DFM for Canada that bears many similarities with the model developed in this paper.1. These papers have shown that DFM nowcasts outperform simple benchmarks and other competing nowcasting approaches, such as bridge models and mixed-data sampling (MIDAS) regressions, and often produce nowcasts that are on par with those of professional forecasters
Summary
We estimate an approximate dynamic factor model (DFM) for Canada and evaluate its nowcasting performance for Canadian GDP. Galbraith and Tkacz (2013) examine the usefulness of payments data to nowcast GDP growth Relative to these papers, we contribute by proposing a different DFM, examining a larger set of monthly and quarterly predictors, and benchmarking the results against other nowcasting models commonly used in the literature. In the United States, Industrial Production is available within two weeks of the reference period, while in Canada it is reported as a special aggregation of monthly real GDP data. As such, it is released 60 days after the reference period.. Series that suffer from this problem are spliced together with the corresponding older series
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
