Combining time DEA scores using a dynamic panel data model
Subject Areas : International Journal of Data Envelopment Analysis
Geraldo Souza
1
,
Eliane Gomes
2
1 - Brazilian Agricultural Research Corporation
2 - Brazilian Agricultural Research Corporation
Keywords: Fractional regression, Agricultural research, Time series, DEA,
Abstract :
We define a combined DEA score to evaluate efficiency in agricultural research. The production model we propose considers efficiency measurements under variable returns to scale for each year in the period 20122017. We postulate a first-order autoregressive process in the presence of covariates, to explain efficiency. Powers of the autocorrelation coefficient estimated assuming a dynamic panel specification, are used as weights to determine a combined efficiency score. A higher weight is given to recent efficiency measurements. We use a fractional regression model to investigate the statistical significance of covariates on the combined score further.
[1] Souza GS, Alves E, Avila AFD. Technical efficiency of production in agricultural research. Scientometrics 1999;46(1):141-60. DOI: 10.1007/BF02766299
[2] Souza GS, Gomes EG, Magalhães MC, Avila AFD. Economic efficiency of Embrapa’s research centers and the influence of contextual variables. Pesqui Oper. 2007;27(1):15-26. DOI: 10.1590/S0101-74382007000100002
[3] Avila AFD, Gomes EG, Souza GS, Filho, RCP, de Souza MO. Avaliação de desempenho de unidades de pesquisa agropecuária: métricas e resultados da experiência da Embrapa. Brasília: Embrapa - Secretaria de Gestão Estratégica; 2013. Documentos 16. ISSN: 1679-4680.