Some Consequences of Temporal Aggregation in Empirical Analysis

Marcellino, Massimiliano

doi:10.2307/1392244

Cited by 130 publications

(190 citation statements)

References 0 publications

Supporting

Mentioning

181

Contrasting

Unclassified

Order By: Relevance

“…It is important to notice that the aggregation only affects the parameters of the error process while the parameter characterising the linear relationship between dependent and independent variable is still completely described by β. The latter is thus independent of C m for all m. A general treatment of linear aggregation and its implications for multivariate autoregressive models is provided by Marcellino (1999), for example. Chow and Lin (1971) suggest to estimate ρ and β subject to the aggregation constraint (4).…”

Section: Chowandlin Revisited 21 the Basic Modelmentioning

confidence: 99%

See 1 more Smart Citation

Testing Temporal Disaggregation

Müller¹

2006

SSRN Journal

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Abstract Economists and econometricians very often work with data which has been temporally disaggregated prior to use. Hence, the quality of the disaggregation clearly affects the quality of the analyses. Building on Chow and Lin's (1971) disaggregation model this paper proposes a new estimation approach and a specification test which assesses the quality of the disaggregation model. An advantage of the proposal is that estimation and testing can both be pursued using the aggregated data while the standard method requires a mixture of high and low frequency data. A small simulation study shows that the test indeed provides useful information. Terms of use: Documents in EconStor mayJEL classification: F31, F47, C53

show abstract

Section: Chowandlin Revisited 21 the Basic Modelmentioning

confidence: 99%

“…In general, as Marcellino (1999) One contribution of this paper is to provide an alternative that makes the switching redundant.…”

Section: Estimationmentioning

confidence: 99%

Testing Temporal Disaggregation

Müller¹

2006

SSRN Journal

View full text Add to dashboard Cite

show abstract

“…Thus we selected r = 3, a choice which was confirmed by the significance of each of the equilibrium correction terms in at least one equation, and is in agreement with the choice of r = 3 in Welfe (1996) when analysing a similar system for the full sample 1961-1989. We note that both the number and the composition of the equilibrium terms is unaffected by the choice of the sample frequency, even if the small sample properties of the tests can be modified, see Marcellino (1999) for details. Table 14 gives the resulting equilibria and adjustment coefficients when non-rejected overidentifying restrictions ( 2 (3) = 0:89 0:83]) were imposed.…”

Section: Polandmentioning

confidence: 99%

Modelling shifts in the wage–price and unemployment–inflation relationships in Italy, Poland and the UK

Marcellino

Mizon

2000

Economic Modelling

Self Cite

View full text Add to dashboard Cite

The relationship between wages, prices, productivity, inflation, and unemployment in Italy, Poland, and the UK between the 1960's and the early 1990's is modelled as a cointegrated vector autoregression subject to regime shifts. For each of these economies there is clear evidence of a change in the underlying equilibria of this sector of the economy. Hypotheses concerning the similarity of the transition from a rigid to a flexible labour market are tested.

show abstract

“…Fourth, it is well known that Granger causality is generally not invariant to aggregation: highfrequency data may reveal patterns which are aggregated away in low-frequency data, and causality in low-frequency data can also be spurious; see Tiao and Wei (1976), Wei (1982Wei ( , 1990, Marcellino (1999), Breitung and Swanson (2002), and Silvestrini and Veredas (2008). Indeed, as stressed in Dufour and Renault (1998), the interpretation of Granger causality depends on the forecast horizon and data frequency.…”

Section: Introductionmentioning

confidence: 99%