The analysis of nonstationary time series using regression, correlation and cointegration

Søren Johansen

doi:10.5709/ce.1897-9254.39

The analysis of nonstationary time series using regression, correlation and cointegration

Søren Johansen

Økonomisk Institut

9 Citationer (Scopus)

Abstract

There are simple well-known conditions for the validity of regression and correlation as statistical tools. We analyse by examples the effect of nonstationarity on inference using these methods and compare them to model based inference using the cointegrated vector autoregressive model. Finally we analyse some monthly data from US on interest rates as an illustration of the methods

Originalsprog	Engelsk
Tidsskrift	Contemporary Economics
Vol/bind	6
Udgave nummer	2
Sider (fra-til)	40-57
Antal sider	18
ISSN	2084-0845
DOI	https://doi.org/10.5709/ce.1897-9254.39
Status	Udgivet - 2012

Emneord

Det Samfundsvidenskabelige Fakultet
regression
correlation
cointegration
model based inference
likelihood inference

Adgang til dokumentet

10.5709/ce.1897-9254.39

Citationsformater

@article{3e288356d51f4eb0980c49848147b5a6,

title = "The analysis of nonstationary time series using regression, correlation and cointegration",

abstract = "There are simple well-known conditions for the validity of regression and correlation as statistical tools. We analyse by examples the effect of nonstationarity on inference using these methods and compare them to model based inference using the cointegrated vector autoregressive model. Finally we analyse some monthly data from US on interest rates as an illustration of the methods",

keywords = "Faculty of Social Sciences, regression, correlation, cointegration, model based inference, likelihood inference ",

author = "S{\o}ren Johansen",

note = "JEL Classification: C32",

year = "2012",

doi = "10.5709/ce.1897-9254.39",

language = "English",

volume = "6",

pages = "40--57",

journal = "Contemporary Economics",

issn = "2084-0845",

publisher = "VIZJA Press & IT",

number = "2",

}

TY - JOUR

T1 - The analysis of nonstationary time series using regression, correlation and cointegration

AU - Johansen, Søren

N1 - JEL Classification: C32

PY - 2012

Y1 - 2012

N2 - There are simple well-known conditions for the validity of regression and correlation as statistical tools. We analyse by examples the effect of nonstationarity on inference using these methods and compare them to model based inference using the cointegrated vector autoregressive model. Finally we analyse some monthly data from US on interest rates as an illustration of the methods

AB - There are simple well-known conditions for the validity of regression and correlation as statistical tools. We analyse by examples the effect of nonstationarity on inference using these methods and compare them to model based inference using the cointegrated vector autoregressive model. Finally we analyse some monthly data from US on interest rates as an illustration of the methods

KW - Faculty of Social Sciences

KW - regression

KW - correlation

KW - cointegration

KW - model based inference

KW - likelihood inference

U2 - 10.5709/ce.1897-9254.39

DO - 10.5709/ce.1897-9254.39

M3 - Journal article

SN - 2084-0845

VL - 6

SP - 40

EP - 57

JO - Contemporary Economics

JF - Contemporary Economics

IS - 2

ER -