Not all residuals are negative... see how OLS works...

Your model lacks dummies to control outliers on your INF series....

The OLS minimizes the residuals of all observations. If your inf variable explodes on some points, these will generate a distortion in your estimates and produce a bad model. That's what is occurring.

Years 1988-1990. There is something in your series right there! 

Enviado do meu iPhone

Em 1 de mar de 2017, às 20:16, HEBERT SUAREZ CAHUANA <hsuarezc@unsa.edu.pe> escreveu:

I sent my dataset, I run regresion INF on PBI
My series from this regression are: uhat=INF-yhat
Why all uhat are negatives?
Excuse me, I couldn't speak English very well. 
              INF          PBI             uhat        yhat

1950       10,290      40920,0     -251,328     261,6187
1951        9,954      44711,0     -250,035     259,9892
1952        6,921      47347,0     -251,935     258,8562
1953        9,087      50085,0     -248,593     257,6794
1954        5,405      52762,0     -251,124     256,5288
1955        4,702      55858,0     -250,496     255,1981
1956        5,474      58484,0     -248,595     254,0694
1957        7,400      62371,0     -244,999     252,3987
1958        7,941      61706,0     -244,744     252,6845
1959       12,702      63653,0     -239,145     251,8476
1960        8,626      69946,0     -240,517     249,1428
1961        6,020      75085,0     -240,914     246,9340
1962        6,618      82620,0     -237,077     243,6953
1963        6,023      86196,0     -236,135     242,1583
1964        9,853      91840,0     -229,879     239,7324
1965       16,363      97003,0     -221,150     237,5132
1966        8,889     104995,0     -225,189     234,0781
1967       11,455     109040,0     -220,884     232,3395
1968       19,117     109206,0     -213,151     232,2682
1969        6,231     113044,0     -224,388     230,6185
1970        5,017     116849,0     -223,966     228,9831
1971        6,807     122213,0     -219,871     226,6775
1972        7,192     126463,0     -217,659     224,8508
1973        9,513     134401,0     -211,925     221,4389
1974       16,877     147017,0     -199,139     216,0163
1975       23,634     153340,0     -189,665     213,2986
1976       33,495     155559,0     -178,850     212,3448
1977       38,042     156102,0     -174,069     212,1114
1978       57,850     151977,0     -156,034     213,8844
1979       67,698     158194,0     -143,515     211,2122
1980       59,161     167596,0     -148,011     207,1711
1981       75,418     176901,0     -127,754     203,1716
1982       64,460     176507,0     -138,881     203,3410
1983      111,149     158136,0     -100,088     211,2372
1984      110,209     163842,0      -98,576     208,7846
1985      163,398     167219,0      -43,935     207,3331
1986       77,921     182981,0     -122,637     200,5584
1987       85,846     200778,0     -107,063     192,9089
1988      666,955     181822,0      465,899     201,0565
1989     3398,272     159436,0     3187,593     210,6784
1990     7481,691     151492,0     7267,598     214,0929
1991      409,528     154854,0      196,880     212,6478
1992       73,529     154017,0     -139,479     213,0076
1993       48,580     162093,0     -160,957     209,5364
1994       23,735     182043,7     -177,227     200,9612
1995       11,131     195536,0     -184,031     195,1620
1996       11,549     201009,3     -181,260     192,8095
1997        8,547     214028,3     -178,667     187,2137
1998        7,255     213190,0     -180,319     187,5740
1999        3,469     216376,7     -182,735     186,2043
2000        3,759     222206,7     -179,940     183,6984
2001        1,975     223579,6     -181,133     183,1084
2002        0,192     235772,9     -177,676     177,8674
2003        2,261     245592,6     -171,386     173,6468
2004        3,662     257769,8     -164,751     168,4128
2005        1,618     273971,2     -159,831     161,4492
2006        2,001     294597,8     -150,582     152,5835
2007        1,779     319693,0     -140,018     141,7971
2008        5,788     348923,0     -123,446     129,2335
2009        2,935     352584,0     -124,725     127,6600
2010        1,530     382380,0     -113,324     114,8531
2011        3,370     407052,0     -100,879     104,2487
2012        3,655     431273,0      -90,183      93,8381
2013        2,806     456365,6      -80,247      83,0528
2014        3,246     467275,8      -75,117      78,3634
2015        3,548     482809,0      -68,139      71,6870
2016        3,599     501621,9      -60,001      63,6008







2017-03-01 9:45 GMT-05:00 HEBERT SUAREZ CAHUANA <hsuarezc@unsa.edu.pe>:
I installed Gretl 2016.d when I run a regression OLS and I generate forecast or save residuals every residual is lower cero or each residual is negative, it is not posible.
Whats up in Gretl? Perhaps any problem in program code.

--
Hebert Suarez Cahuana
Economics Department
Saint Augustin University
Peru


"Ninguna nación llegó a la ruina por el libre comercio" Benjamin Franklin



--
Hebert Suarez Cahuana
Secretario del Departamento de Economía
Universidad Nacional de San Agustín
Arequipa-Perú

"Ninguna nación llegó a la ruina por el libre comercio" Benjamin Franklin
<INFLACION_ANUAL_1950-2017.gdt>
_______________________________________________
Gretl-users mailing list
Gretl-users@lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users