Limits...
Assessment and Selection of Competing Models for Zero-Inflated Microbiome Data.

Xu L, Paterson AD, Turpin W, Xu W - PLoS ONE (2015)

Bottom Line: We examine varying degrees of zero inflation, with or without dispersion in the count component, as well as different magnitude and direction of the covariate effect on structural zeros and the count components.We focus on the assessment of type I error, power to detect the overall covariate effect, measures of model fit, and bias and effectiveness of parameter estimations.We then discuss the model selection strategy for zero inflated data and implement it in a gut microbiome study of > 400 independent subjects.

View Article: PubMed Central - PubMed

Affiliation: Dalla Lana School of Public Health, University of Toronto, ON, M5T 3M7, Canada.

ABSTRACT
Typical data in a microbiome study consist of the operational taxonomic unit (OTU) counts that have the characteristic of excess zeros, which are often ignored by investigators. In this paper, we compare the performance of different competing methods to model data with zero inflated features through extensive simulations and application to a microbiome study. These methods include standard parametric and non-parametric models, hurdle models, and zero inflated models. We examine varying degrees of zero inflation, with or without dispersion in the count component, as well as different magnitude and direction of the covariate effect on structural zeros and the count components. We focus on the assessment of type I error, power to detect the overall covariate effect, measures of model fit, and bias and effectiveness of parameter estimations. We also evaluate the abilities of model selection strategies using Akaike information criterion (AIC) or Vuong test to identify the correct model. The simulation studies show that hurdle and zero inflated models have well controlled type I errors, higher power, better goodness of fit measures, and are more accurate and efficient in the parameter estimation. Besides that, the hurdle models have similar goodness of fit and parameter estimation for the count component as their corresponding zero inflated models. However, the estimation and interpretation of the parameters for the zero components differs, and hurdle models are more stable when structural zeros are absent. We then discuss the model selection strategy for zero inflated data and implement it in a gut microbiome study of > 400 independent subjects.

No MeSH data available.


Related in: MedlinePlus

The empirical probability of choosing a model using AIC criterion for ZIP distributed data.The X axis is the value of the covariate effect on the count data γ1 and the Y axis is the empirical probability of choosing a model using AIC criterion. Three different cases of covariate effect, i.e., the consonant (ϕt = ϕc − 5%), neutral (ϕt = ϕc) and dissonant (ϕt = ϕc + 5%) effect, are presented in (A), (B) and (C); (D), (E) and (F); and (G), (H) and (I), respectively. Each column reflects different proportion of zero inflation in the unexposed group: 20% in (A), (D) and (G); 50% in (B), (E) and (H); and 80% in (C), (F) and (I) from the first to the third column.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4493133&req=5

pone.0129606.g008: The empirical probability of choosing a model using AIC criterion for ZIP distributed data.The X axis is the value of the covariate effect on the count data γ1 and the Y axis is the empirical probability of choosing a model using AIC criterion. Three different cases of covariate effect, i.e., the consonant (ϕt = ϕc − 5%), neutral (ϕt = ϕc) and dissonant (ϕt = ϕc + 5%) effect, are presented in (A), (B) and (C); (D), (E) and (F); and (G), (H) and (I), respectively. Each column reflects different proportion of zero inflation in the unexposed group: 20% in (A), (D) and (G); 50% in (B), (E) and (H); and 80% in (C), (F) and (I) from the first to the third column.

Mentions: We examine the ability to select the correct model based on AICs. We also evaluate the performance of Vuong test in the testing of ZINB vs. NB model for the ZINB distributed data. We illustrate the empirical probability of selecting different models using AIC criterion in Fig 8 and Fig 9. Notice that in these simulation studies, because of the binary covariate setting, a ZI model and its corresponding hurdle model have identical AIC values. However, AIC values can be different if continuous covariates are involved [27].


Assessment and Selection of Competing Models for Zero-Inflated Microbiome Data.

Xu L, Paterson AD, Turpin W, Xu W - PLoS ONE (2015)

The empirical probability of choosing a model using AIC criterion for ZIP distributed data.The X axis is the value of the covariate effect on the count data γ1 and the Y axis is the empirical probability of choosing a model using AIC criterion. Three different cases of covariate effect, i.e., the consonant (ϕt = ϕc − 5%), neutral (ϕt = ϕc) and dissonant (ϕt = ϕc + 5%) effect, are presented in (A), (B) and (C); (D), (E) and (F); and (G), (H) and (I), respectively. Each column reflects different proportion of zero inflation in the unexposed group: 20% in (A), (D) and (G); 50% in (B), (E) and (H); and 80% in (C), (F) and (I) from the first to the third column.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4493133&req=5

pone.0129606.g008: The empirical probability of choosing a model using AIC criterion for ZIP distributed data.The X axis is the value of the covariate effect on the count data γ1 and the Y axis is the empirical probability of choosing a model using AIC criterion. Three different cases of covariate effect, i.e., the consonant (ϕt = ϕc − 5%), neutral (ϕt = ϕc) and dissonant (ϕt = ϕc + 5%) effect, are presented in (A), (B) and (C); (D), (E) and (F); and (G), (H) and (I), respectively. Each column reflects different proportion of zero inflation in the unexposed group: 20% in (A), (D) and (G); 50% in (B), (E) and (H); and 80% in (C), (F) and (I) from the first to the third column.
Mentions: We examine the ability to select the correct model based on AICs. We also evaluate the performance of Vuong test in the testing of ZINB vs. NB model for the ZINB distributed data. We illustrate the empirical probability of selecting different models using AIC criterion in Fig 8 and Fig 9. Notice that in these simulation studies, because of the binary covariate setting, a ZI model and its corresponding hurdle model have identical AIC values. However, AIC values can be different if continuous covariates are involved [27].

Bottom Line: We examine varying degrees of zero inflation, with or without dispersion in the count component, as well as different magnitude and direction of the covariate effect on structural zeros and the count components.We focus on the assessment of type I error, power to detect the overall covariate effect, measures of model fit, and bias and effectiveness of parameter estimations.We then discuss the model selection strategy for zero inflated data and implement it in a gut microbiome study of > 400 independent subjects.

View Article: PubMed Central - PubMed

Affiliation: Dalla Lana School of Public Health, University of Toronto, ON, M5T 3M7, Canada.

ABSTRACT
Typical data in a microbiome study consist of the operational taxonomic unit (OTU) counts that have the characteristic of excess zeros, which are often ignored by investigators. In this paper, we compare the performance of different competing methods to model data with zero inflated features through extensive simulations and application to a microbiome study. These methods include standard parametric and non-parametric models, hurdle models, and zero inflated models. We examine varying degrees of zero inflation, with or without dispersion in the count component, as well as different magnitude and direction of the covariate effect on structural zeros and the count components. We focus on the assessment of type I error, power to detect the overall covariate effect, measures of model fit, and bias and effectiveness of parameter estimations. We also evaluate the abilities of model selection strategies using Akaike information criterion (AIC) or Vuong test to identify the correct model. The simulation studies show that hurdle and zero inflated models have well controlled type I errors, higher power, better goodness of fit measures, and are more accurate and efficient in the parameter estimation. Besides that, the hurdle models have similar goodness of fit and parameter estimation for the count component as their corresponding zero inflated models. However, the estimation and interpretation of the parameters for the zero components differs, and hurdle models are more stable when structural zeros are absent. We then discuss the model selection strategy for zero inflated data and implement it in a gut microbiome study of > 400 independent subjects.

No MeSH data available.


Related in: MedlinePlus