Time Series Modeling of National Hospital Insurance Fund Coverage in Kenya

Hellen Wawira Ndwiga, Dennis Muriithi and Daniel Mwangi
Additional contact information
Hellen Wawira Ndwiga: Faculty of Physical Sciences, Engineering, and Technology, Tharaka University, Kenya
Dennis Muriithi: Faculty of Physical Sciences, Engineering, and Technology, Tharaka University, Kenya
Daniel Mwangi: Faculty of Physical Sciences, Engineering, and Technology, Tharaka University, Kenya

European Journal of Mathematics and Statistics, 2024, vol. 5, issue 6, 16-24

Abstract: National Hospital Insurance Fund (NHIF) is a state-owned organization that was established in 1966 with the goal of providing Kenyans with social health insurance that is easily accessible, affordable, long-lasting, and of high quality. Only 24% of Kenyans have access to NHIF, this may affect the implementation and outcome of Universal Health Coverage (UHC). NHIF mandate can only be achieved if the whole population is under an insurance health cover. Understanding patterns, trends and forecasting of NHIF population Coverage using time series analysis would help in policy formulation and planning for proper implementation of UHC in Kenya. The main objective of the study was to model and forecast Kenya’s NHIF population coverage using Seasonal Autoregressive Integrated Moving Average model. Time series research design was used as it involved data that was measured at regular intervals over a significant number of observations. This design followed the Box-Jenkins Seasonal Autoregressive Integrated Moving Average (SARIMA) model. Simulated time series data on NHIF enrollment for the period 1998–2023 was used for this study. R and R-studio was used in the statistical analysis of the data. The model which exhibited the least Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) values was picked by fitting the SARIMA model. Finally, forecasting of the data after following the three Box-Jenkins methodologies, that is, model identification, estimation of parameters and diagnostic check is done. Having an AIC value of 2265.00 and BIC value of 2279.66 SARIMA (1,1,3) (0,1,1)4 model fitted the data well. This modelpassed residual normality test and the forecasting evaluation statistics shows the errors as RMSE = -1263.392, MAPE = 5.872978 and MAE = 11197.31 The 3-year ahead forecasts showed that the enrollment had overall increasing trend. However, moving further into the future forecast the confidence intervals tend to widen. This indicated that the model’s predictions became less certain with time. The SARIMA model proved to be a suitable approach for capturing the underlying patterns in the NHIF enrollment data, providing reasonable forecasts. The findings of the study would lead to robust sensitization by both national and county government and all other stakeholders on the importance of National Hospital Insurance Fund coverage which would lead to increased enrollment from 24% to almost 100% through the Social Health Authority (SHA). This in turn would lead to attainment of the Universal Health Coverage an objective of the third Sustainable Development Goal that stipulates healthy lives and promotes well-being for all at all ages.

Keywords: Coverage; modelling; NHIF; time series (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
https://eu-opensci.org/index.php/ejmath/article/view/14382 Abstract page (text/html)
https://eu-opensci.org/index.php/ejmath/article/download/14382/3290 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:epw:ejmath:v:5:y:2024:i:6:id:14382

DOI: 10.24018/ejmath.2024.5.6.382

Access Statistics for this article

More articles in European Journal of Mathematics and Statistics from European Open Science
Bibliographic data for series maintained by Support Team ().