Two-parameter Lindley (TPL) distribution is becoming increasingly popular for modeling lifetime and survival times data, while maximum likelihood estimators (MLEs) are biased for small and moderate sample sizes. This problem has been a motivation to obtain nearly unbiased estimators for the parameters of the model. For this purpose, for the first time, two different techniques, the Cox-Snell methodology, and Efron’s bootstrap method, have been used to improve modified nearly unbiased estimators for MLEs of the unknown parameters of the TPL distribution. A Monte Carlo simulation study has been performed to compare the performance of these proposed techniques with different sample sizes and parameter values. In the simulation study, bias and mean square error (MSE) criteria were taken into consideration
as evaluation criteria. In addition, a real example is given to demonstrate the applicability of the techniques. The numerical results show that the bias-corrected estimators outperform the
other estimators in terms of biases and mean square errors.