Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

Results found: 7

first rewind previous Page / 1 next fast forward last

Search results

Search:
in the keywords:  data revisions
help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
1
Publication available in full text mode
Content available

End-of-sample vs. Real-time Data: Perspectives for Analysis of Expectations

100%
Tomczyk E.
Prace i Materiały Instytutu Rozwoju Gospodarczego SGH
|
2013
|
vol. 93: Expectations and Forecasting
45-69
EN
Data revision is usually defined as an adjustment published after initial value had been announced; it may reflect rectification of errors, availability of new information, introduction of new measurement or aggregation techniques etc. This paper addresses the impact of data revisions on measures of expectations and offers an introduction to empirical analysis of data vintage in testing properties of expectations. It also defines and classifies data revisions and presents a review of literature and databases available for the purposes of real time analysis.
2
Publication available in full text mode
Content available

Rationality of expectations and data vintage: evidence from business tendency surveys

100%
Tomczyk E.
Econometrics. Ekonometria. Advances in Applied Data Analytics
|
2015
|
issue 4 (50)
184-195
EN
In this paper, the results of the quantification procedures and the properties of expectations series obtained for two data vintages are compared. The volume index of production sold in manufacturing is defined for end-of-sample and real time data, and evaluated against expectations expressed in business tendency surveys. Empirical analysis shows that (1) there are no statistically significant differences between the quantification results obtained on the basis of real time and end-of-sample data, and (2) the results of unbiasedness and orthogonality tests are not influenced by data vintage. Therefore, for the purposes of analyzing the properties of expectations expressed in the business tendency survey, researchers can use easily available end-of-sample data instead of custom-designed and individually compiled real time databases. Also, (3) expectations series are not unbiased or efficient forecasts of changes in production, regardless of data vintage.
3
Publication available in full text mode
Content available

DATA VINTAGE IN TESTING PROPERTIES OF EXPECTATIONS

86%
Tomczyk E.
Metody Ilościowe w Badaniach Ekonomicznych
|
2015
|
vol. 16
|
issue 2
123-132
EN
Results of quantification procedures and properties of expectations series obtained for two data vintages are described. Volume index of production sold in manufacturing is defined for end-of-sample and real time data, and evaluated against expectations expressed in business tendency surveys. Empirical analysis confirms that while there are only minor differences in quantification results with respect to data vintage, properties of expectations time series obtained on their basis do diverge.
4
Publication available in full text mode
Content available

Quality of Tests of Expectation Formation for Revised Data

86%
Ziembińska P.
Central European Journal of Economic Modelling and Econometrics
|
2021
|
issue 4
5
Publication available in full text mode
Content available

Znaczenie rewizji danych w procesie modelowania

86%
Ziembińska P.
Wiadomości Statystyczne. The Polish Statistician
|
2017
|
issue 2
5-30
PL
Artykuł ma na celu przedstawienie i wstępną analizę nowego — skonstruowanego na podstawie biuletynów statystycznych GUS — zbioru danych w czasie rzeczywistym (real-time data) dla polskiej gospodarki, obejmującego zmienne makroekonomiczne. Zbiór ten umożliwia odpowiedzi na pytania dotyczące procesu rewizji, który wpływa nie tylko na spójność danych, ale także na statystyczne własności modeli ekonometrycznych i oparte na nich wnioskowanie. W szczególności omówiono i wyodrębniono rewizje metodologiczne, co umożliwia ich analizę statystyczną oraz weryfikację przyczyn nieoczekiwanych rewizji niemetodologicznych. Badanie wskazuje, że dla istotnej grupy zmiennych rewizje są systematyczne. Wynikają one z redukcji błędu pomiaru, nie zaś napływu nowych informacji, co ma znaczące konsekwencje dla modelowania.
EN
This study aims to present the new real-time set of macroeconomic data for the Polish economy constructed on the basis of the monthly Statistical Bulletins published by the Central Statistical Office. This dataset gives answers to many important questions on the revision processes which have an influence on the consistency of data as well as effects on attributes of econometric models and statistical inference. In particular, in this article methodological revisions were discussed and their types were specified. It is a base for the statistical analysis and verification of reasons of unexpected non-methodological revisions. The research indicates that in the significant group of variables revisions are systematic. This is a result of the error measurement reduction, not the accessibility of new information which has significant implications for modeling.
6
Publication available in full text mode
Content available

Quantification of expectations for general economic situation on the basis of industrial production index with data revisions

72%
Tomczyk E.
Prace i Materiały Instytutu Rozwoju Gospodarczego SGH
|
2015
|
vol. 97: Economic cycles and uncertainty
95-106
EN
Use of appropriate data vintages and taking data revisions into account have only recently became a staple of applied econometric analysis. In this paper, the topic of data vintage in regression quantification procedures is readdressed for survey data on general economic situation. From empirical analysis it follows that quantification of survey data on general economic situation on the basis of industrial production index does not present a significant improvement over the use of response balance. Additionally, results obtained for real-time and end-of-sample data are very similar and do not suggest superiority of any of these two data vintages as far as quantification of survey data on general economic situation is concerned
7
Publication available in full text mode
Content available

The importance of data revisions for statistical inference

72%
Ziembińska P.
Wiadomości Statystyczne. The Polish Statistician
|
2021
|
vol. 66
|
issue 2
7-24
PL
Celem pracy jest ilościowa analiza rewizji danych makroekonomicznych w czasie rzeczywistym dla Polski pochodzących z nowego zbioru utworzonego na podstawie „Biuletynu statystycznego” GUS i obejmującego okres od 1995 do 2017 r. Polskie dane pozytywnie weryfikują wiele hipotez dotyczących wpływu rewizji danych na proces modelowania. Procedury oceniające własności szeregów czasowych mogą dawać istotnie różne wyniki w zależności od tego, jak bardzo rewidowane dane zostaną użyte. Porównanie dopasowanych modeli ARIMA dla szeregów pierwszych i finalnych odczytów wskazuje, że w przypadku większości zmiennych dopasowane modele są podobne. Gdy postać modelu jest taka sama dla obu szeregów, współczynniki zachowują skalę i znak. Większość różnic we współczynnikach wynika z odmiennej struktury dopasowanego modelu, co wpływa na różnice w strukturze autoregresyjnej i może mieć niemały wpływ na wnioskowanie ex ante. Potwierdza to eksperyment prognostyczny. Dla dużej części zmiennych całkowity wpływ rewizji na proces prognozowania wynosi powyżej 10%. Nie są też wyjątkiem ekstremalne przypadki, w których ten wpływ przekracza 100%, czy sytuacje, w których dane bezpośrednio wpływają na znak prognozy. Uwzględnienie tych wyników przez prognostów mogłoby znacząco poprawić jakość predykcji. Horyzont prognozy ma niewielki wpływ na te konkluzje. Artykuł jest kontynuacją pracy autorki z 2017 r.
EN
The aim of the study is a quantitative analysis of revisions conducted by means of a new, real-time macroeconomic dataset for Poland, designed on the basis of the Statistical bulletin (Biuletyn statystyczny) published by Statistics Poland, covering the period from as early as 1995 until 2017. Polish data have positively verified a number of hypotheses concerning the impact of data revisions on the modelling process. Procedures assessing the properties of time series can yield widely discrepant results, depending on the extent to which the applied data have been revised. A comparison of the fitted ARIMA models for series of initial and final data demonstrates that the fitted models are similar for the majority of variables. In the cases where the form of the model is identical for both series, the coefficients retain their scale and sign. Most differences between coefficients result from a different structure of the fitted model, which causes differ-ences in the autoregressive structure and can have a considerable impact on the ex ante infer-ence. A prognostic experiment confirmed these observations. For a large number of variables, the total impact of revisions on the forecasting process exceeds 10%. Extreme cases, where the impact goes beyond 100%, or situations where data have a direct impact on the forecast sign, are also relatively frequent. Taking these results into account by forecasters could significantly improve the quality of their predictions. The forecast horizon has a minor impact on these conclusions. The article is a continuation of the author's work from 2017.
first rewind previous Page / 1 next fast forward last
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.