1,721,014 research outputs found
A parametric empirical likelihood approach to data matching under nonignorable sampling and nonresponse
No full textStatistical matching attempts to combine the information obtained from different non-overlapping samples. The samples selected are often non representative of the finite population from which they are taken and not all the sampled units respond. The aim of this paper is to illustrate how informative sampling and not missing at random (NMAR) nonresponse can be handled in the statistical matching context
Accordo assoluto tra valutazioni espresse su scala ordinale
No full textMany methods for measuring agreement among raters have been proposed and applied
in many domains in the areas of education, psychology, sociology, and medical research.
A brief overview of the most used measures of interrater absolute agreements for ordinal
rating scales is provided, and a new index is proposed that has several advantages. In particular, the new index allows to evaluate the agreement between raters for each single case
(subject or object), and to obtain also a global measure of the interrater agreement for the
whole group of cases evaluated. The possibility of having evaluations of the agreement on
the single case is particularly useful, for example, in situations where the rating scale is being
tested, and it is necessary to identify any changes to it, or to request the raters for a specific
comparison on the single case in which the disagreement occurred. The index is not affected
by the possible concentration of ratings on a very small number of levels of the ordinal scal
A nonparametric approach for statistical matching under informative sampling and nonresponse
No full textStatistical matching attempts to combine the information obtained from different,
non-overlapping samples, selected from the same target population, to form a matched sample
containing the data in the different samples. The aim of this paper is to propose a
nonparametric approach of handling statistical matching under informative sampling and not
missing at random (NMAR) nonresponse, by use of empirical likelihood
Impact of educational test features on item difficulties by the Linear Logistic Test Model
No full textThe aim of the paper is to investigate the effect of item and person properties on
item difficulties using the Linear Logistic Test Model (LLTM) and its extensions. The data under
investigation are the Italy mathematics data from the Program for International Student
Assessment (PISA) 2006. The information regarding the geographical macro-area (North-Italy
versus South-Italy) has been used in the application as person property. Furthermore, the
comparison on item properties effects between North-Italy versus South-Italy is performed
fitting the LLTM for each geographical macro-area
Sampling properties of an ordinal measure of interrater absolute agreement
No full textA measure of interrater absolute agreement was recently proposed capitalizing on the dispersion index for ordinal variables proposed by Giuseppe Leti. The
new measure is not affected by restriction of variance problems and does not depend
on the choice of a particular null distribution. In this presentation an unbiased estimator of such a measure is proposed and its variance is evaluat
Graphical model using copulas for measurement error modeling.
No full textIn this paper the use of non-parametric Bayesian belief networks for
modeling measurement error in Italian Survey on Household Income and Wealth 2008
is investigated. Non-parametric Bayesian belief networks are graphical models expressing the dependence structure between the marginals through the use of bivariate copulas associated to the arcs of the graph. Thanks to their directed structure,
non-parametric Bayesian belief networks can be easily used for measurement error
correction
Insicuri e/o insoddisfatti
No full textInsicuri e/o insoddisfatti. In Il lavoro che cambia. Curatori: M. Carrieri, C. Damiano, B. Ugolin
- …
