Your browser does not support JavaScript!


digital STATISTICA & APPLICAZIONI - 2005 - 1
Digital issue
issue 1 - 2005
publisher Vita e Pensiero
format Digital issue | Pdf
Write a comment for this product

Ebook format Pdf readable on these devices:

Primo fascicolo del 2005


Bipolar mean for ordinal variables
by Walter Maffenini, Michele Zenga pages: 16 Download
This paper proposes, for ordinal variables, a new type of mean called bipolar mean, that is a frequency distribution with the total size n concentrated on one category or on two consecutive categories. The bipolar mean is coherent with the usual statistics dominance that is based on the retro-cumulative frequencies. The paper shows that the number of bipolar means that it is possible to get for the frequency distributions with k categories and total size n is nk –n+1. Note that the traditional means utilised for ordinal variables (the median and the mode) take only k categories. Two applications are presented to show how the BM works.

Keywords: Bipolar mean; statistical dominance; decreasing frequency transfer; total ordering, complete ordered chain.
Center Sampling and Dual Frame surveys: comparisons among estimators for the total
by Fulvia Mecatti pages: 17 Download
Center Sampling is a recent Italian proposal useful in surveying elusive finite populations such as, for instance, legal and illegal immigrants. Several analogies between Center Sampling and Multiple Frame surveys are appreciable. Two estimators for the total rising from Center Sampling setup are adapted and inserted into the Dual Frame context. The proposed estimators are compared with the majors Dual Frame competitors with respect to inferential properties and operative performances. Simulation results are also provided.

Keywords: Elusive Finite Population, Overlapping Frames, Multiple Frame survey, Simulations.
On the accuracy of three statistical softwares
by Angelo M. Mineo, Rino Richiusa pages: 22 Download
In this paper we compare the accuracy of three packages that are commonly used for statistical calculations: Excel of Microsoft, version XP Edition 2003, Statistica of Statsoft, version 6, and R, an open-source free software, available on the web, version 1.9.0. To assess the accuracy of each software in different statistical areas, we are going to use benchmarks expressly developed for this aim. The obtained results show a superiority of R in comparison with the other two softwares.

Keywords: benchmark, univariate statistics, linear and nonlinear regression, probability distributions.
Criteri ottimali e “quasi” ottimali di classificazione per caratteri continui nel caso della varianza fra i gruppi
by Alessandro Zini pages: 21 Download
This work presents a continuous characters classification tecnique, which satisfies some optimality criterion, such as the maximisation of the variance “between” or the minimisation of the concentration “within” the groups, measured by some index which admits a decomposition. Such a tecnique is based on an algorithm which gives all the possible frequency distributions with fixed sum, the way that each class is not empty. As the algorithm is exponential, it is necessary to impose the minimum number of statistical units per class, which fact implies the construction of two classes of residual statistical units, to the left and to the right. In order to have indications about the optimal number of classes, the minimum number of statistical units per class, and about the imputation of the residual statistical units to the left and the right class, the tecnique will be applied to classify a 13868 individual income sample, drawn by Italian Bank in 1991.

Keywords: Exponential algorithm, Concentration within groups, Continous character, Optimality criterion, Variance between groups.
Efficienza e protezione della privacy nei Randomized Response Model
by Massimo Guerriero pages: 15 Download
Randomized response is a method used in statistical surveys whose goal is to reduce or eliminate respons errors which occour when respondents are queired about sensitive or highly personal matters. In this work the goals are to analyze and compare the respondent privacy protection in some randomized response models according to efficiency and privacy protection. We prove that some single and double randomization models give no advantage in terms of efficiency under the condition of equal respondent protection compared to Warner’s and Simmons’ models.

Keywords: randomized, privacy protection, response models, efficiency, jeopardy.