We consider the question of numerical treatment of irregularly sampled time
series. This problem is quite common in astronomy because of factors such
as the day-night alternation, weather conditions, nonobservability of the o
bjects under study, etc. For this reason an extensive literature is availab
le on this subject. Most of the proposed techniques, however, are based on
heuristic arguments, and their usefulness is essentially in the estimation
of power spectra and/or autocovariance functions. Here we propose an approa
ch, based on the reasonable assumption that many signals of astronomical in
terest are the realization of band-limited processes, which can be used to
fill gaps in experimental time series. By using this approach we propose se
veral reconstruction algorithms that, because of their regularization prope
rties, yield reliable signal reconstructions even in case of noisy data and
large gaps. A detailed description of these algorithms is provided, their
theoretical implications are considered, and their practical performances a
re tested via numerical experiments. MATLAB software implementing the metho
ds described in this work is obtainable by request from the authors.