Menéndez Calleja, María LuisaMorales González, DomingoPardo Llorente, LeandroVadja, Igor2023-06-202023-06-201988-030039-040210.1111/1467-9574.00069https://hdl.handle.net/20.500.14352/57875For a wide class of goodness-of-fit statistics based on phi-divergences between hypothetical cell probabilities and observed relative frequencies, the asymptotic normality is established under the assumption n/m(n) --> gamma is an element of (0, infinity), where n denotes sample size and m(n) the number of cells. Related problems of asymptotic distributions of phi-divergence errors, and of phi-divergence deviations of histogram estimators from their expected values, are considered too.engjournal articlehttp://onlinelibrary.wiley.com/doi/10.1111/1467-9574.00069/pdfhttp://onlinelibrary.wiley.com/restricted access519.2goodness-of-fitsparse testing schemeshistogram estimatesdivergence errorsL(p)-errorsasymptotic distributionshistogram density-estimationkullback-leibler lossEstadística aplicada