Polynomial Regressions and Nonsense Inference
Polynomial specifications are widely used, not only in applied economics, but also in epidemiology, physics, political analysis and psychology, just to mention a few examples. In many cases, the data employed to estimate such specifications are time series that may exhibit stochastic nonstationary b...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2013-11-01
|
| Series: | Econometrics |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2225-1146/1/3/236 |
| _version_ | 1811306579285245952 |
|---|---|
| author | Daniel Ventosa-Santaulària Carlos Vladimir Rodríguez-Caballero |
| author_facet | Daniel Ventosa-Santaulària Carlos Vladimir Rodríguez-Caballero |
| author_sort | Daniel Ventosa-Santaulària |
| collection | DOAJ |
| description | Polynomial specifications are widely used, not only in applied economics, but also in epidemiology, physics, political analysis and psychology, just to mention a few examples. In many cases, the data employed to estimate such specifications are time series that may exhibit stochastic nonstationary behavior. We extend Phillips’ results (Phillips, P. Understanding spurious regressions in econometrics. J. Econom. 1986, 33, 311–340.) by proving that an inference drawn from polynomial specifications, under stochastic nonstationarity, is misleading unless the variables cointegrate. We use a generalized polynomial specification as a vehicle to study its asymptotic and finite-sample properties. Our results, therefore, lead to a call to be cautious whenever practitioners estimate polynomial regressions. |
| first_indexed | 2024-04-13T08:46:42Z |
| format | Article |
| id | doaj.art-8078aa50d3b14f1bae18d874339d772d |
| institution | Directory Open Access Journal |
| issn | 2225-1146 |
| language | English |
| last_indexed | 2024-04-13T08:46:42Z |
| publishDate | 2013-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Econometrics |
| spelling | doaj.art-8078aa50d3b14f1bae18d874339d772d2022-12-22T02:53:38ZengMDPI AGEconometrics2225-11462013-11-011323624810.3390/econometrics1030236econometrics1030236Polynomial Regressions and Nonsense InferenceDaniel Ventosa-Santaulària0Carlos Vladimir Rodríguez-Caballero1Centro de Investigación y Docencia Económicas (CIDE), División de Economía, Carretera México-Toluca 3655 Col. Lomas de Santa Fe, Delegación Álvaro Obregón, México 01210, MexicoCenter for Research in Econometric Analysis of Time Series (CREATES) and Department of Economics and Business, Aarhus University, Fuglesangs Allé 4, Building 2622 (203), Aarhus V 8210, DenmarkPolynomial specifications are widely used, not only in applied economics, but also in epidemiology, physics, political analysis and psychology, just to mention a few examples. In many cases, the data employed to estimate such specifications are time series that may exhibit stochastic nonstationary behavior. We extend Phillips’ results (Phillips, P. Understanding spurious regressions in econometrics. J. Econom. 1986, 33, 311–340.) by proving that an inference drawn from polynomial specifications, under stochastic nonstationarity, is misleading unless the variables cointegrate. We use a generalized polynomial specification as a vehicle to study its asymptotic and finite-sample properties. Our results, therefore, lead to a call to be cautious whenever practitioners estimate polynomial regressions.http://www.mdpi.com/2225-1146/1/3/236polynomial regressionmisleading inferenceintegrated processes |
| spellingShingle | Daniel Ventosa-Santaulària Carlos Vladimir Rodríguez-Caballero Polynomial Regressions and Nonsense Inference Econometrics polynomial regression misleading inference integrated processes |
| title | Polynomial Regressions and Nonsense Inference |
| title_full | Polynomial Regressions and Nonsense Inference |
| title_fullStr | Polynomial Regressions and Nonsense Inference |
| title_full_unstemmed | Polynomial Regressions and Nonsense Inference |
| title_short | Polynomial Regressions and Nonsense Inference |
| title_sort | polynomial regressions and nonsense inference |
| topic | polynomial regression misleading inference integrated processes |
| url | http://www.mdpi.com/2225-1146/1/3/236 |
| work_keys_str_mv | AT danielventosasantaularia polynomialregressionsandnonsenseinference AT carlosvladimirrodriguezcaballero polynomialregressionsandnonsenseinference |