---

The single level analysis had been implemented on hierarchical data structure in social science research. When ´single level´ techniques are applied to hierarchically structured data, the analysis will ignore important aspects of the data structure. Due to this problem it raises the need for multilevel analysis and very little academic literature exists on how to utilize multilevel analysis. Multilevel analysis provides a powerful framework for exploring how average relationships vary across hierarchical structures. This book, therefore, provides application of multilevel analysis for social science researcher, supplemental to single level analysis that most social researchers currently use. The analysis should be especially useful to professionals in social science fields, or anyone else who may be considering utilizing multilevel modeling efforts. This book also demonstrates how men´s attitude (refering husbands´ approval and couple communication) influence couple´s contraceptive use at individual level and community level.

---

BED: Mathematics, MSc: Population Studies/Demography in Addis Abeba University, IGNIS project Coordinator for Institute of Regional and Local Development Studies, Addis Abeba University Ethiopia.

---