Wagner's hypothesis: New evidence from Turkey using the bounds testing approach

Purpose – The aim of this paper is to prove the validity of Wagner's hypothesis. Design/methodology/approach – The paper examines the validity of Wagner's hypothesis with annual data for Turkey over 1950-2005 period. Findings – The empirical results using the ARDL bounds tests of cointegration provide strong support for the hypothesis. Also, the results are robust across six alternative specifications of the Wagner's hypothesis as well as four alternative lag length selection criterions. Originality/value – The paper provides useful information on the validity of Wagner's hypothesis.Economic growth, Error handling, Public sector, Turkey