I have a data-set with multiple variables. I would like to do a statistical analysis to determine the extent of the impact of factors on the change in time, Which models are best suited for time-series data-set analysis?
First, plot your data versus time. is there some sort of pattern? If so, perhaps you can. what you do then depends on the data and what questions you want to ask. D. Booth
Are your multiple variables, responses or predictors or both. Is there a multilevel structure with say repeated measures (over time) on multiple individuals. If you have only one entity being repeatedly you have in effect a sample of one. (I am being provocative !) And how frequently are you measuring in relation to process of interest, annual, monthly, daily , by the second....... Are you interested in prediction or understanding?
You have not provided sufficient detail to really help.
You should first check the correlation among variables, then select the high correlated variables as your input to your model.
Then you should visualize your data as Prof. David recommended to see whether your data is linear or non-linear data. Depend on that you can know how to pick the model worked best for you. Such as
+ Linear dataset: AR, MA, ARMA, Exponential Smoothing ...
I have a data-set for taxi trips from point A to B (distance is fixed between the two points). I want to know what is the relation of some variables in influencing of the trip duration as an example (weather (rain - snow - temperature)- time (morning-peak-evening)).
Firstly, just I would like to do an explanatory analysis of the effect of variables on time, then I will do predicting.