I have a multiyear time series dataset detailing the concentration of environmental contaminant over time. and I need to determine if there is a significant difference between the yearly means. In this instance I am not concerned with trends. I am unsure if running an ANOVA followed by a tukey HSD test to determine which years are different is appropriate to answer my question. I don't think my data meets the requirement of independence for the ANOVA because the years closer together might be more related to each other than years further apart. In addition, the data set runs for 7 years, so using a tukey test would greatly reduce the statistical power of the test. Any clarification or advice is appreciated!