Bayesian technical efficiency analysis of groundnut production in Ghana

Figures & data

Figure 1. Trends of groundnut production in Ghana.Source: Authors Own Plot with Data from MoFA 2016

Figure 2. Conceptual framework.Source: Authors own construct, 2022

Table 1. Summary of inefficiency variables and a priori expectations

Variable	Description	Measurement	A priori Sign	Literature Support
Z1	Age of farmer	Number of years	+/-	Bezemer et al. (2005)
Z2	Gender of farmer	Dummy (male = 0 & female = 1)	+/-	Bezemer et al. (2005)
Z3	Educational level	Number of years spent in school.	+	Danso-Abbeam et al. (2015)
Z4	Household Size	Number of persons	+	Taphe et al. (2015)
Z5	Extension visits	Frequency of times	+	Mahgoup et al. (2017)

Source: Field Survey, 2017

Table 2. Bayesian Parameter Estimates of the Stochastic Frontier Model

Variable	Parameters	Mean	SD	MC_err	2.5%	Median	97.5%
Constant	β0	0.326	0.124	0.006	−0.020	0.348	0.507
Labour	β1	0.269	0.112	0.002	0.054	0.264	0.498
Seed	β2	0.547	0.131	0.002	0.290	0.547	0.806
Herbicides	β3	0.215	0.084	0.009	0.048	0.215	0.379
Intermediate Input	β4	0.071	0.126	0.002	−0.183	0.072	0.317
Labour Square	β5	−0.566	0.339	0.004	−1.208	−0.573	0.097
Seed Square	β6	−0.658	0.273	0.003	−1.190	−0.660	−0.118
Herbicide Square	β7	−0.166	0.185	0.002	−0.529	−0.165	0.198
Intermediate Input Square	β8	−0.167	0.151	0.002	−0.461	−0.168	0.131
Labour * Seed	β9	1.000	0.221	0.003	0.565	1.001	1.426
Labour * Herbicides	β10	−0.804	0.165	0.002	−1.132	−0.802	−0.481
Labour * Intermediate Inputs	β11	−0.082	0.170	0.002	−0.408	−0.083	0.255
Seed * Herbicides	β12	0.472	0.184	0.003	0.113	0.475	0.826
Seed * intermediate Inputs	β13	0.084	0.169	0.002	−0.247	0.083	0.421
Herbicide* Intermediate inputs	β14	0.044	0.087	0.001	−0.121	0.043	0.212
White-noise variance	σ^2	0.223	0.066	0.003	0.141	0.043	0.405
Lambda	λ	0.295	0.098	0.004	0.007	0.298	0.567
DIC		521.50

Source: Field survey with Authors Own Calculations

Figure 3. Posterior kernel density plots of input variable parameters.

Figure 4. Distribution of Technical Efficiency Scores of Farmers.Source: Field Survey with Author’s Own Plot

Table 3. Posterior Distributions of Determinants of Inefficiency

Variables	Param-eters	Mean	SD	MC_error	2.5%	Median	97.5%
Constant	δ0	1.504	0.466	0.997	0.654	1.460	2.819
Age of famer	δ1	0.899	0.771	0.001	0.045	0.201	2.483
Gender of farmer	δ2	1.743	1.079	0.002	0.078	0.185	5.929
Educational level	δ3	2.309	1.599	0.030	0.115	0.294	7.991
Household size	δ4	0.872	0.617	0.002	0.044	0.128	2.877
Extension visits	δ5	1.413	1.046	0.011	0.053	0.367	5.100

Source: Field Survey with Author’s Own Calculations

Bezemer, D., Balcombe, K., Davis, J., & Frazer, I. (2005). Livelihood and Farm Efficiency in Rural Georgia. Applied Economics. University of Groningen. https://doi.org/10.1080/00036840500215253.

 Google Scholar

Danso-Abbeam, G., Dahamani, A. M., & Bawa, A.-S. (2015). Resource-use- efficiency among mallholder groundnut farmers in Northern Region, Ghana. American Journal of Experimental Agriculture, 6(5), 290–304. https://doi.org/10.9734/AJEA/2015/14924

 Google Scholar

Taphe, B. G., Agbo, F. U., & Okorji, E. C. (2015). Resource productivity and technical efficiency of small scale groundnut farmers in Taraba State, Nigeria. Journal of Biology, Agriculture and Healthcare, 5(17), 2224–3208. www.iiste.org

 Google Scholar

Mahgoup, O. B., Ali, A. E. S., & Mirghani, A. O. (2017). Technical efficiency analysis of groundnut production in the gezira scheme, Sudan. International Journal of Scientific and Research Publications, 7(1). www.ijsrp.org

 Google Scholar