Structural Health Monitoring (SHM) has demonstrated to be a fundamental tool for detecting damage in early stages in existent civil engineering structures. This paper explores the accuracy of vibration-based SHM for identifying the existence of damage in adobe constructions, a widespread structural system but on which limited experimental and numerical applications of the technique are available. Two damage detection methodologies are investigated: (i) Autoregressive Models to predict the structural dynamic response taking into account the environmental parameters as input; and (ii) Principal Component Analysis to detect patterns and anomalies in this response without the need of information about environmental conditions. The results of the laboratory tests on a real scale adobe wall positively indicate the capabilities of these two methodologies to accurately identify damage. They also evidence the importance of monitoring several modes as their sensitivity to damage depends on damage location itself. Furthermore, the application of these two damage detection methodologies in a real case study related to the long-term monitoring of a 16th Century adobe church allowed confirming the building safe condition during almost two years of monitoring period, as well as the absence of damage after a 5.2Mw earthquake.