comparison of forecasting models for daily data (frequecy=365) I have 852 days of daily attendance data and need to use the first 800 days data to predict the next 52 days and match it with my actual values. How do i decide which is the best model to use for forecasting? will it capture seasonality and trend? What should be the values of input parameter?
 A: This question is quite broad and it would be helpful if you provided more details. Still, some general notes can be made. 
(1) How do you decide which model is the best to use for forecasting?
Split your data into a training sample and a test sample. Estimate your candidate models on the training sample and let them forecast the test sample. Compare the forecasts with the actual values. Choose a measure of forecast accuracy that you find relevant, e.g. root mean square error, mean absolute percentage error, mean absolute scaled error or still some other measure. Think more about your problem to choose the most relevant measure.
(2) Will it capture seasonality and trend?
It is up to you to formulate a model that can accommodate seasonality and trend. Later, you can look at the forecasts of the test sample and the actual values and see whether there is a trend or a seasonal component remaining in the forecast errors. If you find it, it suggests that your model failed to capture it. Hence, reconsider the model.
(3) What should be the values of input parameter?
What input parameter are you talking about? Could you be more specific? In general, parameter values can often be estimated on the test sample, so you need not pre-specify them. But perhaps I am answering a different question than you had in mind.
