Forecasting Liquidity Ratios Of Commercial Banks In Nigeria Using Autoregressive Fractionally Integrated Moving Average(ARFIMA) Model

Michael Okpara University | 74 pages (14074 words) | Theses

ABSTRACT

This thesis undertakes a forecast of liquidity ratio of commercial banks in Nigeria, using autoregressive fractionally integrated moving average (ARFIMA) model. The research work employs monthly data for the period of 2004 to 2015 (12years). The Augmented Dickey Fuller (ADF) test was conducted to test for stationarity and it showed that the liquidity ratio data was stationary at first difference. The long lasting autocorrelation function of the data showed the presence of long memory structure and Hurst exponent test confirmed the presence of long 'li memory structure. The Geweke and Porter-Hudak method of estimation was used to obtain the ':I. long memory parameter d of the ARFIMA model. The optimal lag lengths for both the AR and MA of the ARFIMA model were obtained using the Akaike Information Criteria (AIC) and the log-likelihood test. ARFIMA(5,0.12,3) was identified and fitted. Similarly, a suitable ARIMA } model was fined for the liquidity ratio data. ARIMA(l,1,1) was identified and fitted. The l autocorrelation function of the residual of both the ARFIMA and ARIMA models were j .· computed and it was found that none of these autocorrelation functions was significantly _different from zero at any reasonable level. Forecasting liquidity ratio of commercial banks was done using the identified models. The predicted values were compared with the observed values. The results showed that ARFIMA (5,0.12,3) model is valid, adequate and good since its j predicted values are much closer to the observed values than the ARIMA( 1, I, I) model. 1j Similarly, the graph of the forecast obviously showed that the predicted values of ARFIMA { model are closer to the observed values than those of ARIMA model. To this end, forecast ·i,·_ evaluation for the two models were carried out using root mean square error (RMSE), and it was j concluded that the ARFIMA model is a much better model in this regard.

Overall Rating

0.0

5 Star
(0)
4 Star
(0)
3 Star
(0)
2 Star
(0)
1 Star
(0)
APA

MICHAEL, U (2023). Forecasting Liquidity Ratios Of Commercial Banks In Nigeria Using Autoregressive Fractionally Integrated Moving Average(ARFIMA) Model. Repository.mouau.edu.ng: Retrieved Jul 16, 2024, from https://repository.mouau.edu.ng/work/view/forecasting-liquidity-ratios-of-commercial-banks-in-nigeria-using-autoregressive-fractionally-integrated-moving-averagearfima-model-7-2

MLA 8th

UNIVERSITY, MICHAEL. "Forecasting Liquidity Ratios Of Commercial Banks In Nigeria Using Autoregressive Fractionally Integrated Moving Average(ARFIMA) Model" Repository.mouau.edu.ng. Repository.mouau.edu.ng, 12 Jul. 2023, https://repository.mouau.edu.ng/work/view/forecasting-liquidity-ratios-of-commercial-banks-in-nigeria-using-autoregressive-fractionally-integrated-moving-averagearfima-model-7-2. Accessed 16 Jul. 2024.

MLA7

UNIVERSITY, MICHAEL. "Forecasting Liquidity Ratios Of Commercial Banks In Nigeria Using Autoregressive Fractionally Integrated Moving Average(ARFIMA) Model". Repository.mouau.edu.ng, Repository.mouau.edu.ng, 12 Jul. 2023. Web. 16 Jul. 2024. < https://repository.mouau.edu.ng/work/view/forecasting-liquidity-ratios-of-commercial-banks-in-nigeria-using-autoregressive-fractionally-integrated-moving-averagearfima-model-7-2 >.

Chicago

UNIVERSITY, MICHAEL. "Forecasting Liquidity Ratios Of Commercial Banks In Nigeria Using Autoregressive Fractionally Integrated Moving Average(ARFIMA) Model" Repository.mouau.edu.ng (2023). Accessed 16 Jul. 2024. https://repository.mouau.edu.ng/work/view/forecasting-liquidity-ratios-of-commercial-banks-in-nigeria-using-autoregressive-fractionally-integrated-moving-averagearfima-model-7-2

Related Works
Please wait...