Papers by Marco Terribili
Rivista Italiana di Economia Demografia e Statistica, 2021
Organization declared the COVID-19 pandemic. Italy was one of the first Western countries severel... more Organization declared the COVID-19 pandemic. Italy was one of the first Western countries severely affected by the coronavirus pandemic, with the first devastating wave affecting mainly the northern and central regions of the country, and afterwards spreading nationwide. Since the start of this pandemic, it was clear that the range of disease manifestations and immune responses, which occur after infection with SARS-CoV-2, vary significantly. Many individuals present with either asymptomatic or mild disease. Therefore, the true extent of the pandemic may be underestimated. Globally researchers and public health organizations explored strategies to better understand the spread of SARS-CoV-2 disease, using seroprevalence as a critical measure. A seroprevalence survey uses antibody tests to estimate the percentage of people in a population who, at a specific time point, have antibodies against SARS-CoV-2. The results can tell us how many people in a specific population may have been previously infected with SARS-CoV-2 (Larremore et al., 2021). Just to estimate the seroprevalence rate in Italy, the Health ministry, and the National Institute of Statistics (Istat) launched a seroprevalence survey of the SARS-CoV-2 virus, carried out between May and July 2020, in collaboration with the Italian Red Cross. In this paper, the aims pursued by this study and the main achieved results will be shown. Through descriptive analysis and statistical models, the factors playing the main roles in having a positive IgG outcome have been studied.
The Italian National Institute of Statistics (ISTAT) is planning a redesign of Consumer Price Sur... more The Italian National Institute of Statistics (ISTAT) is planning a redesign of Consumer Price Survey (CPS). Register of local units and availability of scanner data (SD) from retail modern distribution, provided through an agreement with Nielsen, are the starting point of this transformation. Especially SD represents a big opportunity for introducing improvements in terms of both data collection and sampling perspective. This work aims to compare the properties of weighted and unweighted higher level elementary price indices when different sample schemes are implemented on SD (modern distribution for food and grocery data). Probabilistic and non-probabilistic samples of series have been drawn with different schemes. Furthermore, different criteria of sample allocation both for outlets and elementary items were also considered. The comparison among different sampling strategies (allocation, selection) has been carried out through a Montecarlo simulation evaluating bias and efficiency...
A sampling design widely adopted in official statistics is the Stratified Simple Random Sampling ... more A sampling design widely adopted in official statistics is the Stratified Simple Random Sampling (SSRS) design in which strata are defined by crossing of the variables that define the domains of estimate. When there are many strata, the SSRS design could be inefficient. We propose an alternative sampling design denoted as Incomplete Stratified Sampling (ISS) design. The design exploits all the potential auxiliary information available both from the sampling frame and from other sources such as previous surveys in a more efficient way with respect to the traditional SSRS design. The ISS design enable to fix the sample size for the each estimation domain obtaining the required precisions for the sample estimates, achieving a reduction of the overall sample size with respect to the SSRS design since for the latter the allocation process has no constraints on stratum sample sizes.
%207-8%20 December%20(Section%20A_%20LFS)/2.%20Documents/Doc%2029%20Item %204.1%20Annex%20II%20SA... more %207-8%20 December%20(Section%20A_%20LFS)/2.%20Documents/Doc%2029%20Item %204.1%20Annex%20II%20SAS%20programs%20explanation.pdf OSIER G., RAYMOND V. 2017. Development of methodology for the estimate of variance of annual net changes for LFS-based indicators-Deliverable 1-Short document with derivation of the methodology (FINAL).
The mixed mode (MM), i.e. the use of different collection techniques in the same survey, is a rel... more The mixed mode (MM), i.e. the use of different collection techniques in the same survey, is a relatively new approach that ISTAT, as well as other NSI, is adopting especially for social surveys. Its use is expected to spread both to contrast declining response rates and to reduce the total cost of the surveys. The use of different data collection techniques, in fact, helps in contacting different types of respondents in the most suitable way for each of them.
New Statistical Developments in Data Science, 2019
The Italian National Institute of Statistics (ISTAT) is carrying out a redesign of Consumer Price... more The Italian National Institute of Statistics (ISTAT) is carrying out a redesign of Consumer Price Survey (CPS). The availability of Scanner Data (SD) from retail modern distribution, provided to ISTAT by Nielsen for a large number of stores selling food and grocery, is the starting point of this innovation. Indeed, SD represent a big opportunity for improving the computation of Consumer Price Index (CPI). This work aims to study the properties of alternative aggregation formulas of the elementary price index in different sampling schemes implemented on SD. Bias and efficiency of the estimated indices are evaluated through a Monte Carlo simulation.
Statistics and demography, the legacy of Corrado Gini, 2015
This paper reports the results of a work conducted for classifying Italian households in relation... more This paper reports the results of a work conducted for classifying Italian households in relation to their socio-economic vulnerability, by aggregating information concerning different dimensions. The paper address the methods used (composite indicator and cluster analysis) and presents an application to real data, in order to show the potential of the integration of different methods.
Sommario L’indagine di copertura del censimento 2011(PES) ha il duplice obiettivo di stimare il n... more Sommario L’indagine di copertura del censimento 2011(PES) ha il duplice obiettivo di stimare il numero corretto di individui residenti in Italia alla data di riferimento del censimento e di valutare gli errori di sotto e sovra copertura dell’indagine censuaria. Per stimare tali quantita e stato applicato un modello statistico basato essenzialmente sulle ipotesi adottate nel modello di Petersen; una delle ipotesi alla base del modello di stima impone che le probabilita di cattura del Censimento e dell’indagine PES siano costanti per ogni unita all’interno della sottopopolazione. L’Hard To Count index (HTC) e una delle variabili utilizzata nella fase di post stratificazione, che ha contribuito ad individuare delle aree omogenee rispetto alla difficolta di una popolazione ad essere conteggiata. Nel paper viene descritta la costruzione dell’HTC; attraverso l’applicazione di un modello di regressione logistica multilivello si e ottenuta una categorizzazione dei comuni Italiani basata sul...
The Italian National Statistical Institute had certified the quality of the 15th Italian populati... more The Italian National Statistical Institute had certified the quality of the 15th Italian population and housing census thanks to a Post Enumeration Survey (PES) taken throughout the months immediately after the Census. The aim of the PES is to produce total estimates adjusted for under coverage and, for the first time, over coverage. The model underlying the under and over coverage estimation, takes into account the differences between individual probabilities of responding to the Census. For this aim a regression unit-level model was applied; in order to study the individual probability to be censused on the basis of which the Hard to Count Index (HTC) of Italian municipalities it was created. In the model were used variables derived from the PES questionnaire and additional area-level variables from other sources. HTC categorises the 8092 Italian municipalities in 3 different levels, partitioning the distribution of municipal non-response propensities, based on percentiles. This p...
Weighting adjustment techniques, adopted in the estimation phase to compensate nonresponse effect... more Weighting adjustment techniques, adopted in the estimation phase to compensate nonresponse effect, are based on the use of auxiliary information known both for respondent and not respondent units, usually without distinguishing among different types of nonresponse. This paper proposes to treat separately the components of nonresponse, i.e. noncontact and refusal, with the aim of reducing nonresponse bias. Our weight adjustment method takes into account the sequential nature of the response process. Nested models are used to construct nonresponse adjustment weights in a two-stage response process, i.e. contact and participation conditional on contact. The assumption underlying this approach is that, conditional on auxiliary information, the different types of response are linearly independent.
For sampling surveys aiming at producing estimates for different domains of interest, a sampling ... more For sampling surveys aiming at producing estimates for different domains of interest, a sampling design widely adopted in official statistics is the Stratified Simple Random Sampling (SSRS) design in which strata are defined by crossing of the variables that define the domains of estimate. When there are many strata, the SSRS design could be inefficient. We propose an alternative sampling design denoted as Incomplete Stratified Sampling (ISS) design. The design exploits all the potential auxiliary information available both from the sampling frame and from other sources such as previous surveys in a more efficient way with respect to the traditional SSRS design. The ISS design enable to fix the sample size for the each estimation domain obtaining the required precisions for the sample estimates, achieving a reduction of the overall sample size with respect to the SSRS design since for the latter the allocation process has no constraints on stratum sample sizes.
The social network coming-out. Planning a survey about LGBTQ population(s) on Instagram Author: M... more The social network coming-out. Planning a survey about LGBTQ population(s) on Instagram Author: Marco Dionisio Terribili SAPIENZA-UNIVERSITY OF ROME P. l e A l d o M o r o n. 5-00185 Roma T (+39) 06 49910563 F (
The Post Enumeration Survey (PES) 2011 has the goal of estimating the real number of the people l... more The Post Enumeration Survey (PES) 2011 has the goal of estimating the real number of the people living in Italy on 9 October 2011 and also the aim of evaluating the errors of overcoverage and undercoverage in the individuals count. In order to estimate the coverage rate a statistic model, based on the Petersen’s model, assumption have been estimated; one of the basic hypothesis of this estimation model is the constant capture probabilities, for all the units belonging to the subpopulation. One of the used post-stratification variables is the Hard To Count index (HTC), which contributes to detect homogeneous areas relatively to the difficulty of a subpopulation to be enumerated. The paper describes the development of the HTC; by means of a multilevel logistic regression model a categorization of the Italian municipalities has been obtained, based on nonresponse propensity in the 2011 census,. Finally an alternative partition of the Italian territory is presented and compared with the...
Journal of Official Statistics
For the first time in 2018 the Italian Institute of Statistics (Istat) implemented the annual Per... more For the first time in 2018 the Italian Institute of Statistics (Istat) implemented the annual Permanent Population Census which relies on the Population Base Register (PBR) and the Population Coverage Survey (PCS). This article provides a general overview of the PCS sampling design, which makes use of the PBR to correct population counts with the extended dual system estimator (Nirel and Glickman 2009). The sample allocation, proven optimal under a set of precision constraints, is based on preliminary estimates of individual probabilities of over-coverage and under-coverage. It defines the expected sample size in terms of individuals, and it oversamples the sub-populations subject to the risk of under/over coverage. Finally, the article introduces a sample selection method, which to the greatest extent possible satisfies the planned allocation of persons in terms of socio-demographic characteristics. Under acceptable assumptions, the article also shows that the sampling strategy enh...
Journal of Official Statistics
The mixed-mode (MM) designs are adopted by NSIs both to contrast declining response and coverage ... more The mixed-mode (MM) designs are adopted by NSIs both to contrast declining response and coverage rates and to reduce the cost of the surveys. However, MM introduces several issues that must be addressed both at the design phase, by defining the best collection instruments to contain the measurement error, and at the estimation phase, by assessing and adjusting the mode effect. In the MM surveys, the mode effect refers to the introduction of bias effects on the estimate of the parameters of interest due to the difference in the selection and measurement errors specific to each mode. The switching of a survey from single to mixed-mode is a delicate operation: the accuracy of the estimates must be ensured in order to preserve their consistency and comparability over time. This work focuses on the methods chosen for the evaluation of the mode effect in the Italian National Institute of Statistics (ISTAT) mixed-mode survey “Aspects of Daily Life – 2017”, in the experimental context for w...
![Research paper thumbnail of Intra-seasonal variation of anthropometrical, conditional, and technical tests in U14 soccer players. [Variación en los parámetros antropométricos, condicionales y test técnicos de jugadores de fútbol SUB-14]](https://attachments.academia-assets.com/79173641/thumbnails/1.jpg)
RICYDE. Revista internacional de ciencias del deporte, Jul 1, 2018
This study aimed to analyze the annual variation of soccer players abilities assessed by means of... more This study aimed to analyze the annual variation of soccer players abilities assessed by means of a field-battery test administered six times during an entire competitive season (from T0 to T5). Anthropometric (i.e., body mass, stature, and body mass index), soccer skill (i.e., touch with the body, touch with the head, passing, shooting, dribbling with pass, and dribbling) and functional capacities (i.e., counter-movement jump with and without free arms, and speed) tests were submitted to 33 Under-14 soccer players. A general improvement across the season as confirmed by the rising effects from 0.3 (T2) to 0.6 (T5) was showed. The technical skills (except touch with the head and dribbling) and functional tests showed significant differences (p < 0.001) between T0 and T5 but they were not dependent by the exposure to training. This study underlined that the skills' development in youth soccer players are not linear due to the effects of the growth and maturation. In order to optimize this process, in-season assessment are needed. Finally, programs and decisions promoted by coaches and scouts aimed to the development of youth soccer players should be inspired by the potential results that might be achieved by players.
Uploads
Papers by Marco Terribili