Hi folks, i have some problems with my evaluation. We have collect tons of data from 23 testpersons for our new road study. I have now a time series for each person and all the logs when he accelerates or hits the break trying to solve five different tasks. The dataset lools like: # Unixtime time accelerate break UserID task #10372 1312358742 10:05:41.600 3.054 0.000 2 "lane" #10373 1312358742 10:05:41.700 3.056 1.000 2 "emergency" The break variable is binary and i want to test if there is a significant difference between the tasks using the break variable. I have not really a clue what i have to look for. My idea was to use a 2 Sample t-test for the accelerate variable but the conditions are not fulfilled for this test. I am not really experienced with time series analysis so thanks a lot for your advice! Bernd -- View this message in context: http://r.789695.n4.nabble.com/Time-series-analysis-with-random-effects-tp4033263p4033263.html Sent from the R help mailing list archive at Nabble.com.