1 00:00:00,220 --> 00:00:04,379 Welcome back to Practical Time Series Analysis, 2 00:00:04,379 --> 00:00:06,785 and welcome to week two. 3 00:00:06,785 --> 00:00:11,685 Now that we have many of our mathematical and statistical preliminaries out of the way, 4 00:00:11,685 --> 00:00:15,285 we can start engaging actual time series themselves. 5 00:00:15,285 --> 00:00:19,500 So, what we'll do this week is learn how to take advantage of 6 00:00:19,500 --> 00:00:22,590 the tremendous insights and intuition we can get 7 00:00:22,590 --> 00:00:26,365 just by doing a simple XY plot for a time series, 8 00:00:26,365 --> 00:00:31,230 looking for trends, seasonality, and other patterns. 9 00:00:31,230 --> 00:00:35,280 We'll begin learning how to analyze time series with 10 00:00:35,280 --> 00:00:41,500 the many functions available to us through R. In particular, 11 00:00:41,500 --> 00:00:45,300 we'll start looking at the Autocorrelation Function. 12 00:00:45,300 --> 00:00:49,980 Now, if you just have a sequence of unrelated data points, 13 00:00:49,980 --> 00:00:51,935 in essence, if you just have noise, 14 00:00:51,935 --> 00:00:54,290 well, you're not going to see much structure there. 15 00:00:54,290 --> 00:00:57,850 But very often, times series do exhibit 16 00:00:57,850 --> 00:01:03,560 a relationship between neighbors that we can describe with the Autocorrelation Function. 17 00:01:03,560 --> 00:01:09,250 And this week, we'll learn how to obtain those and how to start using those. 18 00:01:09,250 --> 00:01:15,335 We can also get a lot of insight into the processes that generate time series, 19 00:01:15,335 --> 00:01:18,065 your so-called Stochastic processes. 20 00:01:18,065 --> 00:01:21,990 If we can write some software simulations ourselves, 21 00:01:21,990 --> 00:01:23,730 and we begin in week two, 22 00:01:23,730 --> 00:01:27,310 writing very simple but nonetheless useful, 23 00:01:27,310 --> 00:01:32,470 simulated data, a simulated time series. 24 00:01:32,470 --> 00:01:34,670 So, welcome to week two.