The impact of the banking sector development on the financial performance of the communication sector in sierra leone
ARDL Unit Root Test for Stationarity
Download 0.58 Mb. Pdf ko'rish
|
4.7 ARDL Unit Root Test for Stationarity
Unit root test is very essential to undertake in order to identify the stationary status of variables and needs to be carry out before the cointegration test can be conducted. The order of integration need to be ascertained to determine if they are at level I(0) or at first difference I(1). Economic theories suggest that, certain pair of variables are linked by a long-run economic relationship and the variables that are integrated in the same order can be cointegrated, particularly regression model at first difference data or I(1). However, if variables are integrated at I(1) they must obey a long-run equilibrium relationship even though they may separate in the short-run from the equilibrium. Spurious regression problem may arise by non-stationery data. (Granger & Newbold, 1974) pointed out, the level of many of economic time-series are integrated (or nearly so), and if these data are used in a regression model then a high value for the coefficient of determination(R2) is likely to arise, even when the series are actually independent of each other. In order to test our data, we need to be ascertained that they are stationary, in this regard a unit root test shall be done to determine if the data are stationary at certain level and OLS will be valid to run the test. The Augmented Dickey-Fuller (ADF) test will be used and a significant P-Value at level I(0) or at first difference I(1) shall provide a valid room for the test to be processed via OLS. One of the most common method to test time series set data set for stationarity is the Dickey& Fuller (ADF) test (Dickey & Fuller, 1979) as time series data with a unite root are considered to be non-stationary. Other method like Phillips-Perron test is also used to test for stationarity but similar to that of the ADF even though with few differences and most of the time produced similar 55 results according to (Brooks, 2014). However, the ADF method is sufficient to conduct the test and thereby utilized in this study as used in (Yua et al., 2021) (Sulehri & Naeem , 2018) amongst others. The ADF test for stationarity is a regression analysis based on the below equation; Download 0.58 Mb. Do'stlaringiz bilan baham: |
Ma'lumotlar bazasi mualliflik huquqi bilan himoyalangan ©fayllar.org 2024
ma'muriyatiga murojaat qiling
ma'muriyatiga murojaat qiling