Long term fertility experiments with replications are often statistically analyzed as split plots in time. Due to advancement in agrotechnology, scientists are sometimes changing the package of practices (input factor) but not the basic treatments. The statistical procedure for analyzing the long term experiment with change in input is lacking. The objective of this study was to evaluate long term fertility experiments by stability analysis. Stability analysis was performed on bidi tobacco single-site long term fertility experiment. Stability analysis can be inappropriate without prior evaluation of the relationship between treatment yield and year in single-site long term experiment.