Page 78 - Azerbaijan State University of Economics

THE JOURNAL OF ECONOMIC SCIENCES: THEORY AND PRACTICE, V.78, # 2, 2021, pp. 74-88

I. METHODOLOGY
Data Sources
The study has used 6-year time series data starting from 2001 to 2017. This is due to
the required data series being available only for the 2001–2007-year period. The
annual data were obtained from Central Statistical Agency, National Bank of
Ethiopia (NBE), Ethiopian Economic Association (EEA), National planning
commission, and other international data sources like WB, UNCTAD, and IMF.

Measurement and Estimation of Factor of Productivity
Factor of Productivity measures captures the share of output not described by the
number of physical inputs used to produce the output in which its level is
determined by how efficiently and intensely the inputs are utilized in production
(Comin, 2010). Productivity can be measured in terms of single-factor productivity
measures, and multi-factor productivity measures.(Tsegay et.al, 2017). In this
research, the Tornqvist-Theil index was used to construct the Factor Productivity
index based on simple pre-defined formulas and without the need for econometric
nd
estimation. This approach avoids the statistical problems resulting from 2 -stage
st
regressions as the omitted variable problem not resolved in the 1 stage may provide
nd
inefficient and biased estimates in the 2 stage regression (Wang and Schmidt,
2002). According to this approach, growth in factor productivity is considered
comparable to growth in technical change. The Tornqvist-Theil output, input, and
factor productivity index in logarithm form can be specified as follows:

1 ,
= [ ] = ∑( + ) ( )
−1 2 , , −1 , −1

1 ,
= [ ] = ∑( + , −1 ) ( )
,
−1 2 , −1

= [ ] = [ ] − [ ]
−1 −1 −1

Where;
Rj,t = the share of output (j) in total revenue in time (t),
Qj,t = the output (j) in time (t),
Si,t = the share of input (i) in total input cost, and
Xi,t = the input (i) in time (t),

78