DETECTION OF ABERRANT OBSERVATIONS AND MODELLING OF CONSUMER PRICE INDEX AND INFLATION RATE IN NIGERIA FROM 1960 - 2014: THE WAVELET APPROACH

Authors

  • Efuwape, B.T Department of Mathematical Sciences, Olabisi Onabanjo University, Ago-Iwoye, Nigeria
  • Aideyan, D.O Department of Mathematical Sciences, Kogi State University, Ayingba, Nigeria
  • Efuwape, T.O Academic Planning Unit, Bells University of Technology, Ota, Nigeria
  • Solanke, O.O Department of Mathematical Sciences Olabisi Onabanjo University Ago-Iwoye.

DOI:

https://doi.org/10.53555/nnms.v1i1.1495

Keywords:

Wavelets, Aberrant observation, Resolution, Modelling, Distributions

Abstract

Aberrant observations (AO) are data usually inconsistent with the rest of the series and have the tendency to render statistical inference invalid. The spectral method is widely used for detecting AOs but this is restricted to when series is stationary and periodic. Wavelet shrinkage is a mutually exclusive choice to the spectral method which shrinks the size of the series into multi-resolutions without losing the properties of the series. In this research paper, we present aberrant observation detection and modelling approach based on wavelet analysis in the detection of aberrant observations and modelling using Gaussian and Non-Gaussian distributions in the frequency domain with promising results, on inflation rate in Nigeria between 1960 to 2014. In the method of detecting AO, the inflation rate was highest in 1995 followed by 1993, 1994, 1988, 1989 and 1992. These inflation rates were all observed during the military era. Normal distribution has highest values in all the resolutions from the Loglikelihood calculated, hence, it is the best of the three for detecting AO from the data.  Akaike Information Criteria (AIC) confirms that at higher resolutions, cauchy distribution has lowest AIC which confirms it as the best method of modelling data at such resolutions.

 

References

. Nason GP 2002 Choice of wavelet smoothness, primary resolution and threshold in wavelet shrinkage. Statistics and Computing, 12(3), 219-227

. Abraham M 1998 Histogram Smoothing Via the Wavelet Transform. Journal of Computational and Graphic Statistics, 7(4).

. Dainotti A, Pescape A and Viorgio G 2006 Wavelet-based detection of DOS attack. IEEE Globecom, 1-6.

. Nason G and Sapatinas T 2005 Wavelet packet transfer function modeling of nonstationary time series. Statistics and Computing, 12(1), 45-56.

. Polikar R 2001 The Wavelet Tutorial: Fundamental concepts and an overview of the wavelet theory. Rowan University, Glassboro, NJ: Dept of Electrical and Computer Engineering,

. Graps A 1995 An Introduction to Wavelets. IEEE Computational Science and Engineering, 2(2), 50-61.

. Eckley I and Nason GP 2005 Efficient computation of the discrete autocorrelation wavelet inner product matrix. Statistics and Computing, 15, 83-92.

Published

2014-01-24

How to Cite

B.T , E., D.O, A., T.O, E., & O.O, S. . (2014). DETECTION OF ABERRANT OBSERVATIONS AND MODELLING OF CONSUMER PRICE INDEX AND INFLATION RATE IN NIGERIA FROM 1960 - 2014: THE WAVELET APPROACH. Journal of Advance Research in Mathematics and Statistics (ISSN 2208-2409), 1(1), 5-9. https://doi.org/10.53555/nnms.v1i1.1495