Hello I have plot looking like this:
http://www.nabble.com/file/p22453304/Index%2Bgraf.jpeg Where each continues line corresponds to a period og days, and each break on the line corresponds to a shift in the index level. So what i thought about was, is it possible to make a model predicting the index level depending on the length of period? Here is a bit of my dataset: > b[b$a.CHR_NR==97592,] a.CHR_NR a.SALMO_INDEX a.x a.diffdato1 a.akkusum 1492 97592 20.6 62 34 34 1493 97592 18.7 62 14 48 1494 97592 18.1 62 14 62 1495 97592 19.8 16 16 16 1496 97592 18.1 139 7 7 1497 97592 18.1 139 10 17 1498 97592 22.2 139 3 20 1499 97592 22.2 139 11 31 1500 97592 23.2 139 7 38 1501 97592 23.2 139 23 61 1502 97592 26.2 139 7 68 1503 97592 26.2 139 30 98 1504 97592 15.2 139 10 108 1505 97592 15.2 139 7 115 1506 97592 10.8 139 4 119 1507 97592 10.8 139 20 139 1508 97592 15.2 62 6 6 1509 97592 15.2 62 28 34 1510 97592 12.3 62 4 38 1511 97592 12.3 62 24 62 1512 97592 14.2 22 10 10 1513 97592 14.2 22 12 22 1514 97592 31.6 140 32 32 1515 97592 35.1 140 24 56 1516 97592 30.0 140 39 95 1517 97592 10.9 140 11 106 1518 97592 11.8 140 34 140 1519 97592 10.1 329 28 28 1520 97592 10.6 329 30 58 1521 97592 57.0 329 30 88 1522 97592 47.3 329 27 115 1523 97592 30.4 329 28 143 1524 97592 19.3 329 21 164 1525 97592 28.8 329 39 203 1526 97592 20.4 329 23 226 1527 97592 35.1 329 26 252 1528 97592 21.3 329 32 284 1529 97592 16.6 329 45 329 Where a.CHR_NR is a particular herd (i have a lot of herds), a.SALMO_INDEX is the index level (the responds variable), a.x is the length of period (the lines on the plot), a.diffdato1 is the days in the period and a.akkusum is the cumulated sum of a.diffdato1 making the breaks on the lines. Hope you can help me -- View this message in context: http://www.nabble.com/Making-a-prediction-model-from-a-plot-tp22453304p22453304.html Sent from the R help mailing list archive at Nabble.com. ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.