Simple relative curvature measures of nonlinearity are developed to measure the extent of the nonlinearity in a model-experimental design-parameterization combination. We review the geometric aspects of linear and nonlinear least squares and, using the geometric concept of curvature, compute the maximum relative intrinsic curvature of the solution locus as well as the maximum relative parameter-effects curvature. The relative curvatures are independent of scale changes of the data and of the parameters so they can be used to compare different data sets as well as different parameterizations of the same data set. The methods are applied to 24 published nonlinear data sets, and in all cases it is found that the intrinsic curvature is less than the parameter-effects curvature. The nonlinearity measures of Beale (1960) and the bias expressions developed by Box (1971) are shown to be related to the curvature measures.

SAŽETAKU radu su analizirana dva primera za opis nepreciznosti obrade podataka od strane softverskog paketa Statistica. U prvom ogledu meren je intenzitet sabijanja zemljišta i određen polinomni trend za aproksimaciju zavisnosti intenziteta sabijanja zemljišta od dubine obrade. Prvi primer pokazuje neprecizno određene koeficijente u polinomnom trendu višeg reda. Dobijeni koeficijent determinacije daje pogrešnu sliku o preciznosti dobijenog polinoma, tj. koeficijenata u njemu. Nakon detaljne provere utvrđena je greška pri određivanju koeficijenata do 230%. U drugom ogledu praćeno je sagorevanje slame i vremenski merena promena toplotne snage kotla. U programskom paketu Statistica, korišćenjem nelinearne regresione analize određena je aproksimativna funkcija eksperimentalno dobijenih podataka. Njen grafik, formiran u pomenutom programskom paketu, bez obzira na korektnost proračuna aproksimativne funkcije, apsolutno ne odgovara eksperimentalnim podacima, što dokazuje njen grafik dobijen u programskom paketu Mathematica. Ovakve greške prouzrokovaće lošu interpretaciju dobijenih rezultata, tj. neadekvatnost njihovog daljeg korišćenja.

No abstract

No abstract

JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship. For more information about JSTOR, please contact support@jstor.org.. Biometrika Trust is collaborating with JSTOR to digitize, preserve and extend access to Biometrika. SUMMARYFor experimental data which appear to behave according to two different distinct linear relationships, a general model is proposed which allows for a smooth transition from one linear regime to the other. The transition is accomplished by a curve incorporating a transition parameter. The special case of two intersecting straight lines is included in this model. A Bayesian estimation procedure is used to determine the plausibility of different parameter values. The analysis procedure may be extended to any number of join points and for any linear intersecting functions.