I've recently developed a new model for forecasting and the results seems good to me. I've used two different models with 5 different techniques involved in each model. The main motive here is to compare these 5 different techniques and choose the best one. Also, I've to show that the newer model is superior to the previous one.
But I've been asked to do an extensive empirical evaluation on established data sets, and involve statistical significance tests.
So, my question is what are the methods to do statistical significance testing ? I don't have a strong statistical background, so starting from basic explanation would be fine.