Comparison of the Relevance and the Performance of Filling in Gaps Methods in Climate Datasets

  • Jada El KasriEmail author
  • Abdelaziz Lahmili
  • Ouadif Latifa
  • Lahcen Bahi
  • Halima Soussi
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 913)


The lack of values in a climatological series is a severe problem that can mislead and mistake scientific studies. The purpose of this study is to compare three methods of filling in the missing data; the simple arithmetic averaging (AA), Inverse distance interpolation (ID) and the multiple imputation (MI). The comparison of these methods was carried out on a list of mean monthly temperature that concerns one hydrological station localized in the basin of Souss, and was based on four evaluation criteria, namely root mean square error (RMSE), mean absolute errors (MAE), skill score (SS) and coefficient of efficiency (CE). The analysis shows the effectiveness of multiple imputation and the application of the performance criteria shows that MI had the lowest error measures, the best coefficient of efficiency and the best Skill Score. Therefore, we recommend the use of MI to resolve the gap in climatic datasets, especially large ones.


Climate datasets MI Missing data MAR 


  1. 1.
    Aslan, S., Yozgatligil, C., Iyigun, C., Batmaz, I., Turkes, M., Tatli, H., Batmaz, I.: Comparison of missing value imputation methods for turkish monthly total precipitation data (2014)Google Scholar
  2. 2.
    Xia, Y., Fabian, P., Stohl, A., Winterhalter, M.: Forest climatology: estimation of missing values for Bavaria, Germany. Lehrstuhl fuÈr Bioklimatologie und Immissionsforschung, Ludwig-Maximilians UniversitaÈt MuÈnchen, Am Hochanger 13, 85354 Freising, Germany Received 25 September 1998; received in revised form 11 March 1999; accepted 23 March 1999Google Scholar
  3. 3.
    Yuan, Y.C.: Multiple Imputation for Missing Data: Concepts and New Development P267-25. SAS Institute Inc., Rockville, 1700 Rockville Pike, Suite 600, Rockville, MD 20852Google Scholar
  4. 4.
    Little, R.J.A., Rubin, D.B.: Statistical Analysis with Missing Data, 2nd edn. Wiley-Interscience, New York (2002)CrossRefGoogle Scholar
  5. 5.
    He, Y.: Missing data analysis using multiple imputation: getting to the heart of the matter. Circ. Cardiovasc. Qual. Outcomes 3(1), 98–105 (2010)CrossRefGoogle Scholar
  6. 6.
    Schneider, T.: Analysis of incomplete climate data: estimation of mean values and covariance matrices and imputation of missing values. J. Clim. 14, 853–871 (2001)CrossRefGoogle Scholar
  7. 7.
    Hubbard, K.G.: Spatial variability of daily weather variables in the high plains of the USA. Agric. For. Meteorol. 68, 29–41 (1994)CrossRefGoogle Scholar
  8. 8.
    Little, R.J.A., Rubin, D.B.: Statistical Analysis with Missing Data. Wiley, New York (1987)zbMATHGoogle Scholar
  9. 9.
    Schafer, J.L.: Multiple imputation: a primer. Stat. Methods Med. Res. 8, 3–15 (1999)CrossRefGoogle Scholar
  10. 10.
    Teresa, A.M.: Goodbye, listwise deletion: presenting hot deck imputation as an easy and effective tool for handling missing data. Commun. Methods Measur. 5(4), 297–310 (2011)CrossRefGoogle Scholar
  11. 11.
    Chai, T., Kim, H.-C., Lee, P., Tong, D., Pan, L., Tang, Y., Huang, J., McQueen, J., Tsidulko, M., Stajner, I.: Evaluation of the United States National air quality forecast capability experimental real-time predictions in 2010 using air quality system ozone and NO2 measurements. Geosci. Model Dev. 6, 1831–1850 (2013)CrossRefGoogle Scholar
  12. 12.
    Chai, T., Draxler, R.R.: Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature. Geosci. Model Dev. 7, 1247–1250 (2014)CrossRefGoogle Scholar
  13. 13.
    Willmott, C.J., Matsuura, K., Robeson, S.M.: Ambiguities inherent in sums-of squares-based error statistics. Atmos. Environ. 43, 749–752 (2009)CrossRefGoogle Scholar
  14. 14.
    Kashani, M.H., Dinpashoh, Y.: Evaluation of efficiency of different estimation methods for missing climatological data. Stoch. Environ. Res. Risk Assess. 26, 59–71 (2012)CrossRefGoogle Scholar
  15. 15.
    Bhavani, R.: Comparision of mean and weighted annual rainfall in anantapuram district. Int. J. Innovative Res. Sci. Eng. Technol. 2(7), 2794–2800 (2013)Google Scholar
  16. 16.
    Sunni, A.B., Stacy, R.L., Seaman Jr., W.J.: Multiple Imputation Techniques in Small Sample Clinical Trials. Wiley InterScience, Hoboken (2005)Google Scholar
  17. 17.
    El kasri, J., Lahmili, A., Ouadif, L., Bahi, L., Soussi, H., Mitach, M.A.: Comparison of the relevance and performance of filling in gaps methods in rainfall datasets. Int. J. Civil Eng. Technol. (IJCIET) 9(5), 992–1000 (2018). Article ID: IJCIET_09_05_110Google Scholar
  18. 18.
    Carvalho, J.R.P., Monteiro, J.E.B.A., Nakai, A.M., Assad, D.E.: Model for multiple imputation to estimate daily rainfall data and filling of faults. Revista Brasileira de Meteorologia 32(4), 575–583 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Jada El Kasri
    • 1
    Email author
  • Abdelaziz Lahmili
    • 1
  • Ouadif Latifa
    • 1
  • Lahcen Bahi
    • 1
  • Halima Soussi
    • 1
  1. 1.3GIE Laboratory, Mineral Engineering Department, Mohammadia Engineering SchoolMohammed V UniversityRabatMorocco

Personalised recommendations