What statistical method should be used to evaluate risk factors associated with dmfs index? Evidence from the National Pathfinder Survey of 4‐year‐old Italian children

Solinas, Giuliana; Campus, Guglielmo; Maida, Carmelo Massimo; Sotgiu, Giovanni; Cagetti, Maria Grazia; Lesaffre, Emmanuel; Castiglia, Paolo

doi:10.1111/j.1600-0528.2009.00500.x

Cited by 22 publications

(30 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methodological approaches have been proposed to understand caries risk factors and to counteract their development, consisting of modeling the DMFT index through zero-inflated models [Böhning et al, 1999;Solinas et al, 2009;Javali and Pandit, 2010;Lesaffre and Lawson, 2012;Matranga et al, 2013a], although recommendations are provided to enhance the use of these models [Preisser et al, 2012]. The topic of simultaneous occurrence of zero inflation and correlation has been thoroughly tackled by various studies for the analysis of hierarchical data for either study design or data collection procedures [Burnside et al, 2007;Moghimbeigi et al, 2008].…”

mentioning

confidence: 99%

Italian Deprivation Index and Dental Caries in 12-Year-Old Children: A Multilevel Bayesian Analysis

Matranga¹,

Campus²,

Castiglia

et al. 2014

Caries Res

Self Cite

View full text Add to dashboard Cite

Evidence from the literature has shown that people with a lower socioeconomic status enjoy less good health than people with a higher socioeconomic status. The Italian deprivation index (DI) was used with the aim to evaluate the association between the DMFT index and risk factors for dental caries, including city population and DI. The study included 4,305 12-year-old children living in 38 cities classified by demographic size as small, midsize and large. Zero-inflated negative binomial multilevel regression models were used to assess risk factors for DMFT and to address excess of zero DMFT and overdispersion through a Bayesian approach. The difference in the average level of DMFT among children living in cities with different DI quintile was not statistically significant (p = 0.578). The DI and ln(population), included as city-level fixed effects in the two-level variance components model, were not statistically significant. Consuming sweet drinks on average increased the mean DMFT of a susceptible child, while having a highly educated mother reduced it. Unobserved heterogeneity among cities was detected for the probability to be non-susceptible to caries (city-level variance = 0.26 with 95% credibility interval 0.09-0.57), while no territorial effect was found for the mean DMFT of the susceptible children. Our results suggest that the DI and city population did not play a role in explaining between-city variability. Interventions against social deprivation can be influential on the perception of oral health in Italian 12-year-old children to the extent that they can also affect individual level factors.

show abstract

mentioning

confidence: 99%

Italian Deprivation Index and Dental Caries in 12-Year-Old Children: A Multilevel Bayesian Analysis

Matranga¹,

Campus²,

Castiglia

et al. 2014

Caries Res

Self Cite

View full text Add to dashboard Cite

show abstract

“…The use of ZI models has been increasing in the modelling of numbers of decayed teeth since 2004 and the article by Lewsey and Thomson [2004]. There is a clear trend in applications of ZI models to epidemiological studies on dental caries [Solinas et al, 2009]. However, the rationale for using ZI models in dental epidemiology is also questionable.…”

Section: Discussionmentioning

confidence: 99%

“…In this paper, we show that the ZI and hurdle models already used in dental literature to model the number of decayed teeth [Lewsey and Thomson, 2004;Solinas et al, 2009;Vergnes et al, 2012] can both be expressed as a compound sum. Using the same compound sum, we then introduce a new kind of dental caries count data distribution, the generalized negative binomial (GNB) model, which was proposed by Santos Silva and Windmeijer [2001] to model the number of visits to a doctor in a given period.…”

mentioning

confidence: 99%

Discrete Distribution Based on Compound Sum to Model Dental Caries Count Data

Vergnes

Boucher²,

Lelong³

et al. 2016

Caries Res

View full text Add to dashboard Cite

Methods for analysing dental caries and associated risk indicators have evolved considerably in recent decades. The use of zero-inflated or hurdle models is increasing so as to take account of the decayed, missing, and filled teeth (DMFT) distribution, which is positively skewed and has a high proportion of zero scores. However, there is a need to develop new statistical models that involve pragmatic biological considerations on dental caries in epidemiological surveys. In this paper, we show that the zero-inflated and the hurdle models can both be expressed as a compound sum. Using the same compound sum, we then present the generalized negative binomial (GNB) distribution for dental caries count data, and provide a numerical application using the data of the EPIPAP study. The GNB model generates the best score functions while handling the lifetime dental caries disease process better. In conclusion, the GNB model suits the nature of some count data, in particular when structural zeros are unlikely to occur and when several latent spells can lead to new countable events. For these reasons, the use of the GNB distribution appears to be relevant for the modelling of dental caries count data.

show abstract

“…The consequences can be severe if over-dispersion is not considered. In a previous paper, the same research group [Solinas et al, 2009] evaluated the probability of 'cariesfree' subjects and the dependence of DMFS index on the influence of childhood socio-demographic factors, through the application of regression models (Poisson, negative binomial and zero-inflated models, Poisson and negative binomial). The zero-inflated Poisson model achieved a better fit to the data than the Poisson model; the zero-inflated negative binomial model was the best one to use for the dataset object of the paper.…”

Section: Replymentioning

confidence: 99%

Statistical Analysis of Dental Caries: Different Methods for Different Outcomes

Long¹,

Preisser²,

Stamm

2012

Caries Res

View full text Add to dashboard Cite

What statistical method should be used to evaluate risk factors associated with dmfs index? Evidence from the National Pathfinder Survey of 4‐year‐old Italian children

Abstract: These regression models provide a useful approach to handling count outcomes as dmfs/DMFS index in caries epidemiology.

Cited by 22 publications

References 29 publications

Italian Deprivation Index and Dental Caries in 12-Year-Old Children: A Multilevel Bayesian Analysis

Italian Deprivation Index and Dental Caries in 12-Year-Old Children: A Multilevel Bayesian Analysis

Discrete Distribution Based on Compound Sum to Model Dental Caries Count Data

Statistical Analysis of Dental Caries: Different Methods for Different Outcomes

Contact Info

Product

Resources

About