Besedes and Prusa (2006a-b) reveal that international trade relationships are often very short-lived contrary to previously thoughts. In line with this unexpected result, this study provides a statistical description and empirical analysis of the duration of Turkish exports. Specifically, Kaplan-Meier survival function is used to estimate the survival of trade flows over time and also a regression analysis using discrete-time duration models which allow us to properly control for unobserved heterogeneity and the presence of many tied duration times is used to explore the impact of key variables on hazard rates of export flows. The detailed trade data reported by BACI-CEPII are employed to analyze Turkey's export to European Union countries from 1998 to 2013 according to the 6-digit Harmonized system. Results obtained from the analysis of descriptive statistics suggest that the duration of Turkey’s export to European Union countries is short-lived. The median and mean duration of Turkey's exports are merely two years and 4.26, respectively. The Kaplan-Meier estimates of survival functions show that all survival curves are downward sloping with decreasing rate and about 40% of export relationships fails in the first year. The results of the discrete-time duration models indicate that product-market diversification, common language, total exports, initial value, importer GDP and lagged duration have a strong negative impact on the hazard rates of export flows. Whereas distance, common border and difference in GDP per capita have a positive effect on the hazard rates of export flows.
Smoothed Maximum Score Estimation of Discrete Duration Models
