Introduction to Linear Time Series Modelling

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa S. Yaya

2022-12-04

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 1/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.

Introduction

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.

Introduction

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.

Introduction

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Bibliography
Bartlett, M. S. 1946. “On the Theoretical Specification and Sampling
Properties of Autocorrelated Time Series.” Journal of the Royal
Statistical Society, Ser. B8 27:27–41.
Box, G. E. P., and G. Jenkins. 1976. Time Series Analysis: Forecasting
and Control. Second. San Francisco: Holden Day.
Ljung, G. M., and G. E. P. Box. 1978. “On a Measure of Lack of Fit
in Time Series Models.” Biometrika 65:297–303.
Racine, J. S. 2019. Reproducible Econometrics using R. Oxford
University Press, New York.

Introduction
Time series modelling has its root from Econometrics, where regression,
i.e causal econometric models are dealt with. These models are of the
form

yi = β0 + β1 xi1 + β2 xi2 + · · · + βk xik + ui

The explanatory (independent) variables (i.e., the x ’s) are said to cause
Olusanya E. Olubusoye, Isaac Essi & OlaOluwa
Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 2/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 Examples of Stationary and Non-Stationary Processes
White Noise (stationary) Random Walk with Drift (trend, non-stationary)

0
3
2

-50
1
Y

Y
0
-1

-100
-2
-3

0 200 400 600 800 1000 0 100 200 300 400 500

Time Time

Canadian Lynx (cyclical, no trend or season, stationary) Air Passengers (trend and seasonal, non-stationary)
1000 2000 3000 4000 5000 6000 7000

600
500
AirPassengers

400
lynx

300
200
100
0

1820 1840 1860 1880 1900 1920 1950 1952 1954 1956 1958 1960

Time Time

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 3/7
 White Noise, Random Walks, and their Sample ACFs
White Noise Random Walk White Noise

1.0
2

0.8
1

0.6
4
0

ACF

0.4
Y

2
-1

0.2
0
-2

0.0
-2

-0.2
-3

0 20 40 60 80 100 0 20 40 60 80 100 0 5 10 15 20

Time Time Lag

Random Walk White Noise Random Walk

0.2
1.0

0.8
0.8

0.1

0.6
0.6

Partial ACF

Partial ACF

0.4
ACF

0.0
0.4

0.2
0.2

-0.1

0.0
0.0
-0.2

-0.2
-0.2

0 5 10 15 20 5 10 15 20 5 10 15 20

Lag Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 4/7
 White Noise, Random Walks, and their Sample ACFs
White Noise Random Walk White Noise

1.0
2

0.8
1

0.6
4
0

ACF

0.4
Y

2
-1

0.2
0
-2

0.0
-2

-0.2
-3

0 20 40 60 80 100 0 20 40 60 80 100 0 5 10 15 20

Time Time Lag

Random Walk White Noise Random Walk

0.2
1.0

0.8
0.8

0.1

0.6
0.6

Partial ACF

Partial ACF

0.4
ACF

0.0
0.4

0.2
0.2

-0.1

0.0
0.0
-0.2

-0.2
-0.2

0 5 10 15 20 5 10 15 20 5 10 15 20

Lag Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 4/7
 White Noise, Random Walks, and their Sample ACFs
White Noise Random Walk White Noise

1.0
2

0.8
1

0.6
4
0

ACF

0.4
Y

2
-1

0.2
0
-2

0.0
-2

-0.2
-3

0 20 40 60 80 100 0 20 40 60 80 100 0 5 10 15 20

Time Time Lag

Random Walk White Noise Random Walk

0.2
1.0

0.8
0.8

0.1

0.6
0.6

Partial ACF

Partial ACF

0.4
ACF

0.0
0.4

0.2
0.2

-0.1

0.0
0.0
-0.2

-0.2
-0.2

0 5 10 15 20 5 10 15 20 5 10 15 20

Lag Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 4/7
 White Noise, Random Walks, and their Sample ACFs
White Noise Random Walk White Noise

1.0
2

0.8
1

0.6
4
0

ACF

0.4
Y

2
-1

0.2
0
-2

0.0
-2

-0.2
-3

0 20 40 60 80 100 0 20 40 60 80 100 0 5 10 15 20

Time Time Lag

Random Walk White Noise Random Walk

0.2
1.0

0.8
0.8

0.1

0.6
0.6

Partial ACF

Partial ACF

0.4
ACF

0.0
0.4

0.2
0.2

-0.1

0.0
0.0
-0.2

-0.2
-0.2

0 5 10 15 20 5 10 15 20 5 10 15 20

Lag Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 4/7
 White Noise, Random Walks, and their Sample ACFs
White Noise Random Walk White Noise

1.0
2

0.8
1

0.6
4
0

ACF

0.4
Y

2
-1

0.2
0
-2

0.0
-2

-0.2
-3

0 20 40 60 80 100 0 20 40 60 80 100 0 5 10 15 20

Time Time Lag

Random Walk White Noise Random Walk

0.2
1.0

0.8
0.8

0.1

0.6
0.6

Partial ACF

Partial ACF

0.4
ACF

0.0
0.4

0.2
0.2

-0.1

0.0
0.0
-0.2

-0.2
-0.2

0 5 10 15 20 5 10 15 20 5 10 15 20

Lag Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 4/7
 White Noise, Random Walks, and their Sample ACFs
White Noise Random Walk White Noise

1.0
2

0.8
1

0.6
4
0

ACF

0.4
Y

2
-1

0.2
0
-2

0.0
-2

-0.2
-3

0 20 40 60 80 100 0 20 40 60 80 100 0 5 10 15 20

Time Time Lag

Random Walk White Noise Random Walk

0.2
1.0

0.8
0.8

0.1

0.6
0.6

Partial ACF

Partial ACF

0.4
ACF

0.0
0.4

0.2
0.2

-0.1

0.0
0.0
-0.2

-0.2
-0.2

0 5 10 15 20 5 10 15 20 5 10 15 20

Lag Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 4/7
 White Noise, Random Walks, and their Sample ACFs
White Noise Random Walk White Noise

1.0
2

0.8
1

0.6
4
0

ACF

0.4
Y

2
-1

0.2
0
-2

0.0
-2

-0.2
-3

0 20 40 60 80 100 0 20 40 60 80 100 0 5 10 15 20

Time Time Lag

Random Walk White Noise Random Walk

0.2
1.0

0.8
0.8

0.1

0.6
0.6

Partial ACF

Partial ACF

0.4
ACF

0.0
0.4

0.2
0.2

-0.1

0.0
0.0
-0.2

-0.2
-0.2

0 5 10 15 20 5 10 15 20 5 10 15 20

Lag Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 4/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 First Differencing a Random Walk with Drift
5 Series yt First Difference ∆yt

2
0

1
-5

0
∆yt
yt

-10

-1
-15

-2
-20

-3
0 20 40 60 80 100 0 20 40 60 80 100

Time Time

Series yt First Difference ∆yt

1.0

1.0
0.8

0.8
0.6
0.6
ACF

ACF

0.4
0.4

0.2
0.2

0.0
0.0

-0.2
-0.2

0 5 10 15 20 0 5 10 15

Lag Lag

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 5/7
 Example
Based on T = 100 realizations of a time series, we compute
ρ̂1 = 0.15121 and ρ̂2 = 0.069739

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 6/7
 Example
Based on T = 100 realizations of a time series, we compute
ρ̂1 = 0.15121 and ρ̂2 = 0.069739
Supposed that we wished to test H0 : ρ1 = 0

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 6/7
 Example
Based on T = 100 realizations of a time series, we compute
ρ̂1 = 0.15121 and ρ̂2 = 0.069739
Supposed that we wished to test H0 : ρ1 = 0
We calculate

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 6/7
 Example
Based on T = 100 realizations of a time series, we compute
ρ̂1 = 0.15121 and ρ̂2 = 0.069739
Supposed that we wished to test H0 : ρ1 = 0
We calculate
Var [ρ̂1 ] = 1/100 = .01

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 6/7
 Example
Based on T = 100 realizations of a time series, we compute
ρ̂1 = 0.15121 and ρ̂2 = 0.069739
Supposed that we wished to test H0 : ρ1 = 0
We calculate
Var [ρ̂1 ] =
p1/100 = .01
Z = ρ̂1 / Var [ρ̂1 ] = 0.15121/.1 = 1.5121

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 6/7
 Example
Based on T = 100 realizations of a time series, we compute
ρ̂1 = 0.15121 and ρ̂2 = 0.069739
Supposed that we wished to test H0 : ρ1 = 0
We calculate
Var [ρ̂1 ] =
p1/100 = .01
Z = ρ̂1 / Var [ρ̂1 ] = 0.15121/.1 = 1.5121
We would fail to reject the null at all conventional levels

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 6/7
 Example
Based on T = 100 realizations of a time series, we compute
ρ̂1 = 0.15121 and ρ̂2 = 0.069739
Supposed that we wished to test H0 : ρ1 = 0
We calculate
Var [ρ̂1 ] =
p1/100 = .01
Z = ρ̂1 / Var [ρ̂1 ] = 0.15121/.1 = 1.5121
We would fail to reject the null at all conventional levels
Suppose that we wished to test H0 : ρ1 = 0 ∩ ρ2 = 0

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 6/7
 Example
Based on T = 100 realizations of a time series, we compute
ρ̂1 = 0.15121 and ρ̂2 = 0.069739
Supposed that we wished to test H0 : ρ1 = 0
We calculate
Var [ρ̂1 ] =
p1/100 = .01
Z = ρ̂1 / Var [ρ̂1 ] = 0.15121/.1 = 1.5121
We would fail to reject the null at all conventional levels
Suppose that we wished to test H0 : ρ1 = 0 ∩ ρ2 = 0
We calculate

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 6/7
 Example
Based on T = 100 realizations of a time series, we compute
ρ̂1 = 0.15121 and ρ̂2 = 0.069739
Supposed that we wished to test H0 : ρ1 = 0
We calculate
Var [ρ̂1 ] =
p1/100 = .01
Z = ρ̂1 / Var [ρ̂1 ] = 0.15121/.1 = 1.5121
We would fail to reject the null at all conventional levels
Suppose that we wished to test H0 : ρ1 = 0 ∩ ρ2 = 0
We calculate
Qlb = 100(100+2)[0.151212 /(100−1)+0.0697392 /(100−2)] = 2.86194

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 6/7
 Example
Based on T = 100 realizations of a time series, we compute
ρ̂1 = 0.15121 and ρ̂2 = 0.069739
Supposed that we wished to test H0 : ρ1 = 0
We calculate
Var [ρ̂1 ] =
p1/100 = .01
Z = ρ̂1 / Var [ρ̂1 ] = 0.15121/.1 = 1.5121
We would fail to reject the null at all conventional levels
Suppose that we wished to test H0 : ρ1 = 0 ∩ ρ2 = 0
We calculate
Qlb = 100(100+2)[0.151212 /(100−1)+0.0697392 /(100−2)] = 2.86194
For α = 0.05, χ22,1−α = 5.99147

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 6/7
 Example
Based on T = 100 realizations of a time series, we compute
ρ̂1 = 0.15121 and ρ̂2 = 0.069739
Supposed that we wished to test H0 : ρ1 = 0
We calculate
Var [ρ̂1 ] =
p1/100 = .01
Z = ρ̂1 / Var [ρ̂1 ] = 0.15121/.1 = 1.5121
We would fail to reject the null at all conventional levels
Suppose that we wished to test H0 : ρ1 = 0 ∩ ρ2 = 0
We calculate
Qlb = 100(100+2)[0.151212 /(100−1)+0.0697392 /(100−2)] = 2.86194
For α = 0.05, χ22,1−α = 5.99147
We would fail to reject the null at the 5% level

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 6/7
 R Example

Table 1: ACF Summary (White Noise).

Lag (k) ρ̂k Var [ρ̂k ] Bartlett’s Z Qlb χ2k,0.95

0 1.0000000 NA NA NA NA
1 0.0559231 0.0100000 0.5592310 0.3222162 3.841459
2 -0.0045240 0.0100625 -0.0450993 0.3243464 5.991465
3 0.0354164 0.0100630 0.3530542 0.4562441 7.814728
4 0.0027846 0.0100880 0.0277241 0.4570679 9.487729
5 0.0359565 0.0100882 0.3579902 0.5958817 11.070498
In practice we could use the R function Box.test() as follows:
Box.test(y.wn,lag=2,type="Ljung-Box")$statistic
## X-squared
## 0.3243464

Olusanya E. Olubusoye, Isaac Essi & OlaOluwa

Introduction
S. Yaya to Linear Time Series Modelling 2022-12-04 7/7