1974
DOI: 10.1016/0304-4076(74)90034-7
|View full text |Cite
|
Sign up to set email alerts
|

Spurious regressions in econometrics

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

14
1,210
0
74

Year Published

2000
2000
2018
2018

Publication Types

Select...
7
3

Relationship

0
10

Authors

Journals

citations
Cited by 4,429 publications
(1,451 citation statements)
references
References 4 publications
14
1,210
0
74
Order By: Relevance
“…First, doing so renders our data stationarity. Although often neglected in panel studies, nonstationarity of variables can lead to spurious relationships when estimating panel regression models in the same way as it does in time-series models (Granger and Newbold, 1974). However, given the short time dimension in many panel datasets, including ours, panel unit root tests are unreliable.…”
Section: Data Methodology and Resultsmentioning
confidence: 99%
“…First, doing so renders our data stationarity. Although often neglected in panel studies, nonstationarity of variables can lead to spurious relationships when estimating panel regression models in the same way as it does in time-series models (Granger and Newbold, 1974). However, given the short time dimension in many panel datasets, including ours, panel unit root tests are unreliable.…”
Section: Data Methodology and Resultsmentioning
confidence: 99%
“…Nonstationarity of the time series under study may lead to false conclusions by a traditional linear causality test. This phenomenon has been investigated in previous empirical (Granger and Newbold [11]) and theoretical (Phillips [19]) deliberations which led to a cointegration analysis.…”
Section: Fractional Cointegrationmentioning
confidence: 95%
“…It is known since a long time (see for example the presidential address to the Royal Statistical Society of Yule 1926) that the presence of unit roots or stochastic trends has drastic consequences for the behavior of regressions. A regression of two stochastically independent random walks on each other leads to a seemingly significant regression coefficient, a phenomenon labeled nonsense-regression by Yule (1926) and spurious regression by Granger and Newbold (1974). The latter paper provides simulation evidence only and an analytical study of spurious regression and its asymptotic properties is given in Phillips (1986).…”
Section: Unit Roots and Cointegrationmentioning
confidence: 98%