Hello,    I have some problems identifying the right model for my ARIMA model. Just wanna see if I can get some advice.   Below is my data set:   data ts; input time x; datalines; 1 100.06 2 103.07 3 102.02 4 103.6 5 105.16 6 104.31 7 105.63 8 106.18 9 108.18 10 112.83 11 111.18 12 111.1 13 114.06 14 112.92 15 113 16 113.92 17 114.44 18 117.26 19 122.72 20 117.93 21 121.71 22 124.04 23 122.56 24 120.95 25 124.36 26 122.98 27 125.88 28 120.94 29 120.78 30 119.63 31 117.87 32 122.25 33 124.6 34 126.32 35 122.21 36 123.17 37 122.03 38 121.04 39 121.37 40 118.05 41 117.16 42 122.27 43 125.91 44 123.5 45 123.95 46 120.66 47 125.94 48 131.16 49 131.24 50 135.48 51 130.47 52 128.85 53 125.1 54 123.99 55 128.14 56 125 57 118.73 58 124.35 59 120.2 60 118.87 61 114.34 62 114.37 63 116.97 64 114.25 65 108.21 66 110.48 67 108.29 68 111.06 69 111.46 70 112.65 71 107.04 72 115.57 73 112.91 74 113.78 75 117.17 76 115.65 77 111.62 78 111.16 79 110.51 80 113.97 81 106.6 82 105.08 83 106.39 84 110.55 85 112.19 86 106.68 87 112.57 88 109.27 89 113.19 90 107.41 91 109.63 92 104.12 93 107.31 94 111.46 95 106.53 96 110.75 97 106.25 98 109.24 99 106.27 100 112.58 101 109.99 102 109.74 103 106.91 104 111.15 105 107.17 106 105.55 107 103.58 108 103.72 109 101.82 110 105.61 111 102.81 112 101.43 113 108.76 114 105.08 115 103.23 116 105.4 117 101.67 118 99.36 119 98.58 120 98.7 121 99.19 122 103.58 123 98.8 124 100.07 125 99.38 126 103.04 127 102.2 128 99.43 129 97.73 130 99.93 131 104.9 132 101.25 133 96.99 134 98.63 135 100.85 136 98.82 137 107.32 138 98.88 139 102.45 140 94.76 141 99.78 142 98.61 143 99.37 144 101.18 145 101.14 146 100.08 147 98.43 148 99.5 149 103.72 150 104.07 151 106.86 152 101.67 153 110.08 154 108.92 155 106.51 156 108.73 157 111.99 158 113.41 159 113.08 160 122.24 161 121.92 162 122.71 163 122.11 164 120.82 165 118.34 166 118.72 167 120.24 168 119.24 169 118.71 170 120.71 171 123.43 172 121.86 173 122.87 174 121.78 175 119.77 176 123.73 177 127.03 178 122.6 179 122.65 180 120.34 181 118.63 182 115.47 183 114.24 184 114.86 185 111.09 186 115.95 187 114.88 188 116.52 189 114.31 190 116.97 191 114.85 192 113.83 193 118.1 194 115.49 195 117.8 196 120.77 197 115.12 198 113.04 ; run; I have 198 observations here. I plotted the original time series plot and the series doesn't seem to be stationary:   proc timeseries data=ts plots=(corr); var x; run;   So I did one order of differencing and below is the plot:     After differencing, most of the autocorrelation from the ACF and PACF plots are gone.   I believe based on the ACF and PACF plots, the ARIMA (0, 1, 1) model should be the right model. However, I also fit the ARIMA (2, 0, 0) and ARIMA (1, 1, 0) for comparison purposes.   In addition, I use the last 30 observations as my testing data and below is the Proc ARIMA that I used:   proc arima data=ts plots (only)=(series(corr crosscorr) residual(corr normal) forecast(forecastonly)) out=out_es2; identify var=x(1); estimate q=(1); forecast lead=30 back=30 alpha=0.05; outlier; run; quit; I have the following summary:     Arima (1, 1, 0) Arima (0, 1, 1) Arima (2, 0, 0) AIC 1009.837 1009.94 1085.057 SBC 1016.404 1016.506 1091.633 RMSE 4.7993 4.8193 4.1525 WN test (lag 6) 0.705 0.6315 <0.0001   So below are my questions:   1. Based on the ACF and PACF plots, the ARIMA (0, 1, 1) model should be the right model for the data. However, the ARIMA (1, 1, 0) model also gives similar results in terms of AIC, SBC and RMSE. Is this normal?   2. Based on the AIC and SBC, the right model is ARIMA (1, 1, 0). However, the ARIMA (2, 0, 0) gives the lowest RMSE on the testing data set (4.1525 vs. 4.8193 or 4.7993).   I'm having problems identifying which is the best model for this time series data. If I were to choose a model that has the greatest predictive power, the best model would be ARIMA (2, 0, 0), correct?    Could anyone guide me on how to select the model based on the results that I have?   ... View more

I have a quick question about how the autocorrelation is computed in the ACF plot and I'm hoping someone can help.   I have this simple data set: data test; input a b; datalines; 1 . 2 1 3 2 4 3 5 4 6 5 7 6 8 7 9 8 10 9 ; run; Basically, the test data has variable A and B. Variable B has the lagged value of A.   I'm trying to calculate the autocorrelation of A at lag 1. I read that, by definition, the autocorrelation of A at lag 1 is just the correlation of A with its own lagged value (which is B).   So I did a Proc Corr on A and B:   proc corr data=test; var a b; run; This gets me the correlation of 1 which makes perfect sense.      I then plot the ACF plot for A using Proc Timeseries:   proc timeseries data=test plots=acf; var a; run; I looked at the second bar in the plot which shows the autocorrelation at lag 1 and it is showing something close to 0.7 instead:     Am I doing the plot incorrectly? How come the ACF plot show an autocorrelation of 0.7 when it should be just 1?  ... View more

Hello, I have a question about handling the TIME variable in my time series analysis. Hope someone can help 🙂   Below is my data:   data sales; input Week weekday Target; datalines; 1 4 539.577 1 5 224.675 1 6 129.412 2 2 317.12 2 3 210.517 2 4 207.364 2 5 263.043 2 6 248.958 3 2 344.291 3 3 248.428 3 4 281.42 3 5 243.568 3 6 308.178 4 2 363.402 4 3 336.872 4 4 246.992 4 5 308.88 4 6 233.126 5 2 404.38 1 3 298.56 1 4 229.249 1 5 236.304 1 6 297.174 2 2 409.401 2 3 231.035 2 4 238.826 2 5 235.598 2 6 242.112 3 2 490.79 3 3 289.657 3 4 298.459 3 5 323.603 4 3 616.453 4 4 346.035 4 5 307.645 4 6 253.847 5 2 530.944 5 3 333.359 5 4 306.356 1 6 416.83 2 2 415.187 2 3 268.002 2 4 234.503 2 5 234.724 2 6 230.064 3 2 357.394 3 3 259.246 3 4 244.235 3 5 402.607 3 6 255.061 4 2 342.606 4 3 268.64 4 4 188.601 4 5 202.022 4 6 213.509 5 2 316.849 5 3 286.412 5 4 303.447 5 5 304.95 5 6 331.9 ; run; So basically, I have three columns. The first two are the WEEK and WEEKDAY columns. The WEEK column contains the week number and the second column contains the day of the week (e.g. 2=Monday, 3=Tuesday, 4=Wednesday...etc).   Just as an example, the first observation has WEEK=1 and WEEKDAY=4. This is the time point for the Wednesday in week 1.   I'm modeling the TARGET variable using Proc Arima and Proc ESM. I believe I need one TIME variable for the x-axis. There are in total 60 observations. I did a quick check and saw that the response is substantially higher on Monday and lower on the rest of the week.   I'm wondering how I can establish the TIME variable that reflects the weekday information. For example, if I treat the TIME simply as something from 1 to 60, I will lose the seasonal component of the data (because there are some missing days due to holiday).    I believe I have two options: Convert the WEEK and WEEKDAY columns into an actual date column. That should account for the weekday information. Create a new TIME variable that goes from 1 to 60 and use it as my TIME variable on the x-axis. Create dummy input variables for Monday to Friday. I'm fairly new to time series. Does anyone have any comment about how this situation should be handled?   Thanks! ... View more

I'm trying to read in this set of data and I need some help:   A123456789,A,3 1,Y,15Feb1960,M,M,3,FT,55000 2,N,3Jun1965,F,M,3,UE,0 A135790234,B,1 1,Y,19Oct1944,F,D,0,NA,3000 B234523456,A,2 1,Y,30Jun1978,F,M,1,PT,4000 2,N,21May1975,M,M,2,FT,30000   I need the output to look like this:   I have come up with this solution which works fine:   Data Yourdata (drop=temp); Infile datalines dsd; retain var1-var3; input temp : $10. @; if length(temp) ^= 1 then do; Input @1 var1 $10. @12 var2 $ var3 $ var4 var5 $ var6 : date9. var7 $ var8 $ var9 var10 $ var11 ; end; else do; Input @1 var4 var5 $ var6 : date9. var7 $ var8 $ var9 var10 $ var11 ; end; format var6 date9.; datalines; A123456789,A,3 1,Y,15Feb1960,M,M,3,FT,55000 2,N,3Jun1965,F,M,3,UE,0 A135790234,B,1 1,Y,19Oct1944,F,D,0,NA,3000 B234523456,A,2 1,Y,30Jun1978,F,M,1,PT,4000 2,N,21May1975,M,M,2,FT,30000 ; run; However, I'm partially using formatted input instead of list input and I'm ignoring the delimiter for some of the columns. I am wondering if there is a better solution for this.   Can anyone help? Thanks 🙂   ... View more

Hi, I got a problem when I tried to export data from a data set to a text file. I'm wondering if anyone can help 🙂   So below is my code:   data _null_; set sashelp.class; file '/folders/myfolders/class.txt'; put name age height; run;     I'm trying to export the name, age and height variables to a text file. The variables are from sashelp.class and I'm running the code on SAS Studio.   I'm expecting the data to be exported record by record. So if there are 19 records in sashelp.class, I am expecting the text file will have 19 records as well.   However, when I look at the text file, all the records stayed in one line. It looks like this:   Alfred 14 69Alice 13 56.5Barbara 13 65.3Carol 14 62.8Henry 14 63.5James 12 57.3Jane 12 59.8Janet 15 62.5Jeffrey 13 62.5     Does anyone know why? ... View more