TY  - JOUR
AB  - In financial analysis, forecasting often involves regressing one time series variable on another. However, to ensure that the models are correctly specified, one needs to first test for stationarity, co‐integration and causality. In testing for causality, the variables should be stationary. If non‐stationary, one can estimate the model in difference form, unless the variables are co‐integrated. This article determines whether cash flow and earnings variables are stationary, and which variable causes the other, using econometric analysis. In most cases, cash flow variables are found to cause earnings variables. This is so when the models are estimated in levels. However, when estimated in first differences, the causal relationship tends to be reversed such that earnings cause cash flows. Further study is recommended, whereby panel data could be used to improve the power of the tests.
VL  - 16
IS  - 1
SN  - 1022-2529
DO  - 10.1108/10222529200800002
UR  - https://doi.org/10.1108/10222529200800002
AU  - Bezuidenhout A.
AU  - Mlambo C.
AU  - Hamman W.D.
PY  - 2008
Y1  - 2008/01/01
TI  - Investigating causality between cash flow and profitability: an econometrics approach
T2  - Meditari Accountancy Research
PB  - Emerald Group Publishing Limited
SP  - 27
EP  - 41
Y2  - 2024/04/19
ER  -