Recent studies of population distribution in urban settings suggest th
at cubic-spline functions may be preferable to the conventional expone
ntial form. It is contemplated that this specification is more suitabl
e for untangling, discovering and depicting the complex density patter
ns of today's relatively dispersed urban areas. This paper examines th
e usefulness as well as the amenability of the cubic-spline function f
or describing and testing hypotheses on the processes underlying the d
etermination of population densities in Tel Aviv-Yafo. The principal f
indings of the analysis are threefold. First, from the theoretical and
empirical points of view the cubic-spline function is unlikely to be
useful for testing hypotheses. Multicollinearity among distance variab
les renders the cubic-spline function without much practical merit for
this purpose. Secondly, an exponential spline form which does not uti
lise high-order terms of distance is better suited for this purpose an
d should therefore be preferred to the cubic-spline. Thirdly, an alter
native approach which employs an improved exponential form obtained by
incorporating pertinent information on actual patterns of land-use de
velopment into the theoretically derived exponential form was highly s
upported by the data. Utilisation of the latter approach led to an inc
rease in the explanatory power of the model from a mere 0.24 to a resp
ectable 0.83. Indeed, the general lesson to be learned from the analys
is is that utilisation of general functional forms cannot by itself co
rrect for possible biases in sample selection, model specification or,
for that matter, replace thorough understanding of the processes one
is trying to model.