Hidrológiai Közlöny 1977 (57. évfolyam)

5. szám - Domokos Miklós–Dr. Csermák Béla–Dr. Jean Weber: Többváltozós regressziós modellek alkalmazása a vízigények előrejelzésére

Domokos M. és mtsai: Többváltozós regressziós modellek [2] Blattberg, R. C. (1973): Evaluation of the Power of the Durbin —Watson Statistic for Non-First Or­der Serial Correlation Alternatives. Review of Eco­nomics and Statistics, LV, 508—515. [3] Csermák, B. és Domokos M. (1970): A távlati víz­igények előrejelzése. KGST Vízgazdálkodási Szim­pózium, Budapest. (Sokszorosítás, orosz nyelven). [4] Csermák, B. (1972): Methods for Water Require­ments Forecasting. U.N. Ad Hoc Group of Experts on Water Requirements Forecasting. ESA(RT) AC. 3/5., with Addendum. (Lytography). New York­Budapest 1972. [5] Csermák, B. (1973): Ermittlung des zukünftigen Wasserbedarfs, gwf-wasser/abwasser, 114 Jg. H. 11. [6] Csuka, J. (1975): Possibilities of river basin deve­lopment depending on hydrologieal and economic background. Proceedings of the UN DP/UN Interre­gional Seminar on River Basin and Interbasin De­velopment, September 1975, Budapest, Hungary. [7] Durbin, J. and Watson, G. S. (1950): Testing for Serial Correlation in Least-Squares Regression 1. Biometrika, 37, 409—428. [8] Durbin, J. and Watson, G. S. (1951): Testing for Serial Correlation in Least-Squares Regression II-, Biometrika, 38, 159—177. [9] Durbin, J. (1957): Testing for Serial Correlation in Systems of Simultaneous Regression Equations. Biometrika, 44, 380—377. [10] Durbin, J. (1960): Estimation of Parameters in Time-Series Regression Models. Journal of the Royal Statistical Society, Series B, 22, 139—153. [11] Durbin, J. (1970): An Alternative to the Bounds Test for Testing Serial Correlation in Least-Squares Regression. Econometrica, 38, 422—429. [12] Farrar, D. E. and Glauber, R. S. (1976): Multieolli­nearity in Regression Analysis: The Problem Re­visited. The Review of Economics and Statistics, XLIX, 92—107. [13] Fox K. A. and Cooney, J. F. (1954): Effects of In­tercorrelations Upon Multiple Correlation and Reg­ression Measures. U.S. Department of Agriculture, Agricultural Marketing Service, Washington, D.C. [14] Gangart, C. C. (1970): A távlati vízigények megha­tározásának módszerei. KGST Vízgazdálkodási Szimpózium, Budapest. (Sokszorosítás, orosz nyel­ven). [15] Girardot, F. L. (1970): Prevision des besoins en eau des réseaux publics de distribution d'eau. Société Hydrotechnique de France. Xlmes Journées de VHydraulique. Paris. [16] Griliches, Z. and Rao, P. (1969): Small-Sample Pro­perties of Several Two-Stage Regression Methods in the Context of Autocorrelated Errors. Journal of the American Statistical Association, 64. 253—272. [17] Henshaw, R. C. (1966): Testing Single-Equation Least-Squares Regression Models for Autocorrela­ted Disturbances. Econometrica, 34, 646—660. [18] Hessing, F. J. (1965): Die Entwicklung des Brut­toinlandsprodukts und der gewerbliche Wasserver­brauch. GWF. Wasser-Abwasser No. 50. [19] KGST Titkársága, Vízgazdálkodási Csoport (1970): A KGST-tagországokban folyó vízgazdálkodás je­lenlegi helyzetének elemzése és fejlesztési irányzatai­nak meghatározása. (Sokszorosítás, orosz nyelven). [20] Klein, L. R. and Nakamura, M. (1962): Singularity in the Equation Systems of Economics: Some As­pects of the Problem of Multicollinearity. Inter­national Economic Review, 3/3/, 274—299. [21] Koerts, J. and Abrahamse, A. P. J. (1968): On the Power of the BLUS Procedure, Journal of the Ame­rican Statistical Association, 63, 1227—1236. [22] Malinvaud, E. (1961): Estimation et Prévision dans les Modeies Economiques Autoregressifs. Review of the International Institute of Statistics, 29, 1—32. [23] Silvey, S. D. (1969): Multicollinearity and Imprecise Estimation. Journal of the Royal Statistical Society (Series B), 31 (3) 539—552. [24] Stewart R. H. and Metzger (1971): Industrial Water Forecasts. J. AWWA. March. Hidrológiai Közlöny 1977. 5. sz. 213 [25] Theil, H. and Nagar, A. L. (1961): Testing the In­dependence of Regression Disturbances. Journal of the American Statistical Association, 56, 793— 806. [26] Theil, H. (1965): The Analysis of Disturbances in Regression Analysis. Journal of the American Sta­tistical Association, 60, 1067—1079. [27] UN ECE Committee on Water Problems. (1974). Manual for the Compilation of Balances of Water Resources and Needs. New York. [28] Weber, J. E. and Monarchi, D. (1973): Perfor­mance of the Durbin —Watson Test When the Dis­turbance Term is Not First-Order Autocorrelated. Preliminary Paper. npHivieHeHHe moAejieß MHOwecTBeHHoß jiHHefiHoii perpecHH «JIH nporH03a o>KHAaeMoro BOAonoTpeßjieHHji JIOMOKOW, M. —lepMaic, B. — Beöep, ft. B MOflejiyix MHOwecTBeHHon jiHHeÜHoft KoppejinuMM AJIFL ripoi'Hoaa OWNAAEMORO BOAONOTPEßJTEHHFL B KANECTBE HCXOAHMX AAHHBIX npiiMeHHKJTCH BpeMeHHbie PHÄW npj-i­pocTa Hapo/iOHaceJiemm, SKOHOMMqecKoro pa3BHTHH, pocTa AOXOAOB, pocTa 3aTpaT H np. Ilp0rH03bi o>KHflaeMoro BOflonoTpeSjiemiH Ha OCHOBC MOfleJiefi MHOHCeCTBeHHOii JlHHeHHOÍi KOppeJlHUHH conpn­>KeHi>i onpe/jejieHHbiMii TpyAHOCTHMii aa>Ke B TOM cjiynae, Koraa perpecciioHHoe ypaBHeHne xopomo corjracyeTcn c HMeiOmHMHCH AäHHbIMM. IlpHHHHbl 3THX TpyflHOCTeií CJte­flyiomne : a) BpeMeHHbie paau AaHHbix, Kai< npaBHJio, He yAOB­JieTBOpfllOT HpeAnOJIO>KeHHHM O BepOHTHOCTHOfl CyiUHOCTH 0I1IIIÖ0K MOAeJieft MHOJKeCTBeHHOH JlHHeHHOÍÍ KOppeJIflUHI-i; Ő) BpeMeHHbie pflAbi Ha6juoAeHHH, xapaKTepn3yiomne He3aBncHMbie nepeMeHHbie MOAeJieft, KaK npaBHJio, npo­HBJIiUOT B3aHMHyi0 KOppeJIHpOBaHHOCTb; e) B MHTepecax nporHOsa 3aBiicnMoii nepeMCHHoii (BO­AonorpeßjieHiiH), IOK npaBHJio, npuxoAHTca onepi-ipoBaTb c np0rH03yeMHMH 3HaHeHiiHMH HC3aBncHMbix nepeMeH­Hbix. HMeioTCfl CTaTHcrimecKiie MeTOAw npii noMomn KOTO­pbix BO3MO>KHO npoaHajTH3HpoBaTb xapaKTep, Bejiniimy H CTerieHb BJIHAHHH Ha np0i H03 STHX Tpex (JiaKTopoB. BU­nojiHeHne CTaTHCTtmecKnx aHajiH30B HeoßxoAHMO no­CKOJibKy pe3)>Jibmambi npoeH030e eodonompeöMHua HÜM­nozo GoAee yeepeHHO npuMenfiwmca, ec/iu 6ydym U3eecmnbi c6H3aHHbie c HUMU OWUOKU u neonpedeAeHHoemu. Multivariate regression models in water demand forecasting By M. Domokos—Dr. B. Csermák — Dr. J. Weber The multivariate regression models applied for water demands forecasting may be based on records of the population, of income, economic growth, costs, etc. Water demand forecasts based on multivariate reg­ression models may encounter difficulties even in cases where the regression equation fits well to the data avai­lable. These difficulties may be due to the following reasons : a ) The (lata time series fail as a rule in meeting the criteria under which the error of the linear regression model is a random one. b ) The elements of the observation data series relat ing to the independent variables in the model are usually intercorrelated. c ) For predicting the value of the dependent vari­able, namely the water demand, it is commonly neces­sary to predict the future values of the independent variables as well. Statistical methods are available by which the cha­racter, extent and impact on the forecast of these three obstacles can be determined. These statistical analyses are essential, since the results of the water demand prognosis are of much greater value, if the uncertainties involved in them are known and taken into considera­tion.

Next

/
  • Layout
  • Zoom
  • Rotation
Thumbnails
Contents