WEBVTT 00:00.890 --> 00:05.960 Welcome to step two of our solution and here we are asked to create an appropriate index from nineteen 00:05.960 --> 00:10.010 hundred and ninety seven until the end of the year 2008. 00:10.130 --> 00:16.700 That best reflects the marriage strategy and to create a normalized price chart and we should get here 00:16.730 --> 00:19.490 the stock price data from Yahoo Finance. 00:19.700 --> 00:22.860 And let's have a look here again at the case. 00:23.030 --> 00:30.560 So Marriott's is invested in the five most valuable health care stocks and her strategy is pretty simple. 00:30.560 --> 00:35.280 She buys an equal number of shares of each stock and reinvest all dividends. 00:35.480 --> 00:39.930 And we should create an index that best reflects strategy here. 00:40.010 --> 00:47.800 And in this case that's a price weighted Performance Index in Step one we identify to the stock take 00:47.800 --> 00:49.900 us for our five companies. 00:49.900 --> 00:57.510 And here we have the US and now we should download historical price data from nineteen hundred ninety 00:57.510 --> 00:58.380 seven. 00:58.540 --> 01:05.860 So including the very last day of nineteen hundred ninety six until the end of 2018 and therefore we 01:05.860 --> 01:13.390 create here two variables start and end with the respective dates and with the by finance library and 01:13.390 --> 01:20.230 the download method we can actually download the historical price data and we pass here the tick our 01:20.240 --> 01:26.620 list and the start and the end date and for our price where the performance index we are interested 01:26.620 --> 01:33.550 in the columns the adjusted close and close and we save the data frame and the web of stocks 01:39.090 --> 01:46.080 so that's uh the adjusted close and the close price for five stocks here beginning from the very last 01:46.080 --> 01:48.410 day of nineteen hundred ninety six. 01:48.450 --> 01:55.730 So typically here the download method of the finance library if you determine here the start date first 01:55.740 --> 01:58.490 of January nineteen hundred ninety seven. 01:58.590 --> 02:05.280 Then typically we get also the immediately preceding day or year the thirty first of December nineteen 02:05.280 --> 02:07.000 hundred ninety six. 02:07.140 --> 02:13.180 And our task is now to create a price weighted Performance Index and this can be done in few steps. 02:13.200 --> 02:19.470 So first of all we have to calculate the weights of the constituents over time and we have to define 02:19.470 --> 02:23.510 the weights with the closing prices and then we have to wait. 02:23.510 --> 02:29.430 The daily returns based on the adjusted close prices with the weights that we derived in the first step 02:29.850 --> 02:35.910 and by doing so we have the daily returns of our new index and as assets that we have to calculate the 02:35.910 --> 02:42.570 cumulative investment multiple on each timestamp and calculate the index values also in each timestamp 02:42.870 --> 02:53.930 based on a base value of 100 so let's start with the weights and we select the close prices and for 02:53.930 --> 03:00.830 each and every time stand by for each and every row we divide each element and that row by the respective 03:00.920 --> 03:06.650 some of the row and we safe actually hear the new resulting data frame and the variable weights. 03:07.040 --> 03:13.630 And let's overlook so that's the respect for weights based on a price weighted strategy. 03:14.230 --> 03:19.690 And initially in nineteen hundred ninety seven we can see that the highest weights we have for Mark 03:20.380 --> 03:24.260 and let's go down here to 2000 and eighteen. 03:24.320 --> 03:32.720 And we can see that we have the highest rates of 43 percent for the United test group actually. 03:32.740 --> 03:33.430 So here 03:41.450 --> 03:46.380 so that's the debates of our constituents over time and our new index. 03:46.380 --> 03:52.810 And now in the next step we calculate the arc rate a return state of frame and therefore we choose that 03:52.810 --> 03:59.930 the adjusted close prices to calculate the total return based on the assumption that the dividends will 03:59.930 --> 04:06.400 be reinvested into the index and we calculate the daily return with uh the percentage change method. 04:06.410 --> 04:10.230 And of course we also change the drop and a method. 04:10.760 --> 04:14.720 So that's the return data frame and then the next step. 04:14.720 --> 04:21.560 We calculate the daily returns of our index by evading the daily returns of the constituents with their 04:21.560 --> 04:25.970 respective weights at the immediately preceding timestamp. 04:25.970 --> 04:28.160 So that's what we are doing here. 04:28.190 --> 04:35.870 And finally we calculate for each and every timestamp the cumulative investment multiple by adding 1 04:36.320 --> 04:39.710 and using the Camp Road method here. 04:39.710 --> 04:47.180 And finally as our base where you should be 100 we multiply each and every cumulative investment multiple 04:47.180 --> 04:56.320 with 100 and we save our resulting index in the variable health index and let's have a look here. 04:56.320 --> 05:02.400 So here we have a panel series with a index value of ninety nine point eight. 05:02.590 --> 05:06.190 At the second of January nineteen hundred ninety seven. 05:06.250 --> 05:10.470 So the first of January is a bank holiday so we do not have any values here. 05:11.080 --> 05:17.170 And finally we should determine that on the very last timestamp all day of the year nineteen hundred 05:17.170 --> 05:25.450 nineteen six we have the base value of one hundred and therefore we create here a timestamp for the 05:25.480 --> 05:31.770 thirty first of December nineteen hundred ninety six and we actually create a new element for our as 05:31.780 --> 05:39.080 serious here and we assign the value of one hundred and let's have again a look. 05:39.100 --> 05:41.560 So here we cannot see the timestamp. 05:41.590 --> 05:47.260 Thirty first of December nineteen hundred ninety six because it's still not sorted so here it's at the 05:47.260 --> 05:52.340 very end and therefore in a next step we have to start the index. 05:52.490 --> 06:00.600 And also here we pass true to the in-place parameter and we also assign a name to our panda series. 06:00.620 --> 06:04.260 So that's the health care index. 06:04.260 --> 06:05.700 And let's have a final look here. 06:06.480 --> 06:14.220 So that's our large cap health care index that best reflects marries investment strategy starting with 06:14.220 --> 06:19.350 a base value of 100 at the very last day of nineteen hundred ninety six. 06:19.350 --> 06:25.830 And finally we end up here at the end of 2018 at eight hundred ninety. 06:25.860 --> 06:28.170 So that's quite amazing actually. 06:28.230 --> 06:34.590 And we can also plot here the evolution of the price of our index with the plot method 06:38.930 --> 06:42.690 and we can see that from an initial base value of 100. 06:42.860 --> 06:49.160 Mary could manage to increase her investment to a value of almost a 900. 06:49.460 --> 06:56.450 So that's a pretty terrific year because our initial investment increased eight fold are almost nine 06:56.450 --> 06:59.390 fold in only twenty two years. 06:59.390 --> 07:05.660 So that was a very first analysis of our investment strategy and we will continue to do so in the next 07:05.660 --> 07:06.030 video. 07:06.030 --> 07:07.460 So I hope to see it there by.