primo fascicolo del 2018
CONTENTS
by Eugenio Brentari
pages: 1
Download
by Isabella Morlini
pages: 13
Download
Abstract ∨
Psychometrics should ideally measure multidimensional concepts like skills, knowledge, abilities, attitudes, personality traits and educational achievement, which cannot be captured by a single variable. In this paper, we suggest a method based on the fuzzy set theory for the construction of a fuzzy synthetic index of the latent psychometric phenomenon, using the set of variables obtained with instruments such as questionnaires or tests. Criteria for assigning values to the membership function as well as criteria for defining the weights of the variables are discussed. For discrete variables, we use a fuzzy quantification method based on the sampling cumulative function. An application regarding the measurement of reading disability in students attending elementary and middle school in Italy is presented.
by Amjad D. Al-Nasser, Midhat M. Eidous
pages: 11
Download
Abstract ∨
In this article, we suggest using the sample entropy to fit the structural measurement error model. Using sample entropy in data analysis can be considered as a data screening to avoid problem in the data such as heteroscedasticity and co-linearity. The measurement error model is fitted under the assumption that the intercept is known. The mathematical derivation of the slope and its properties are given. An illustration using real data analysis to fit the relationship between happiness rate and human development index is given. The data analysis showed that there is a positive effect of human development index on happiness rate.
by Igor Valli, Michele M. Zenga
pages: 49
Download
Abstract ∨
The decompositions proposed in this paper are applied to the net disposable income of the 8156 italian households supplied by Bank of Italy (2016) where the households are partitioned in four subpopulations according to the number of family members and the total income is the sum of four sources.
by Danilo Aringhieri, Camilla Ferretti
pages: 36
Download
Abstract ∨
The Directional Mobility Measurement tool (DMMtool.m) is a free interactive instrument, which computes in MATLAB the directional mobility index by automatically importing and elaborating the data from a wide-format panel, not necessarily balanced, stored in a ‘.xls’ or ‘.xlsx’ spreadsheet, for a single, quantitative, ‘size-type’ scalar variable. We will imagine a sample of firms observed over many successive years to assess their tendency to upsize or downsize. The researcher is requested to provide all the inputs necessary for calculations: the name of the data file, the extremes of intervals partitioning the variable’s domain, the starting and the final time of the transition, the shape of all parameters within the directional index. The statistical units are automatically allocated into the states, the first-order not-stationary Markov transition matrix is estimated between the selected temporal extremes, the directional index is evaluated. Its value is compared with some other not-directional mobility indices based on the transition matrix between the same selected dates. Accuracy of each input respect to its constraints is verified. Download Supplementary Material.
|
|