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.


The flowchart for simulation studies.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0129606.g002: The flowchart for simulation studies.

Mentions: We generate 1,000 datasets for each simulation scenario and fit the data using different methods such as LOLS, Poisson, NB, ZIP, ZINB, PH, NBH, and 2P-LOLS assuming that the exposed/unexposed group indicator X is the only predictor in the models. For the hurdle/ ZI models, X is the predictor for both the probability of zeros/structural zeros and the count component. For comparison, we also apply the non-parametric WRS, 2P-WRS, OLS and logistic regression in the hypothesis testing in the significance of the exposure effect. The flowchart of the simulation studies is shown in Fig 2.


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

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

The flowchart for simulation studies.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0129606.g002: The flowchart for simulation studies.
Mentions: We generate 1,000 datasets for each simulation scenario and fit the data using different methods such as LOLS, Poisson, NB, ZIP, ZINB, PH, NBH, and 2P-LOLS assuming that the exposed/unexposed group indicator X is the only predictor in the models. For the hurdle/ ZI models, X is the predictor for both the probability of zeros/structural zeros and the count component. For comparison, we also apply the non-parametric WRS, 2P-WRS, OLS and logistic regression in the hypothesis testing in the significance of the exposure effect. The flowchart of the simulation studies is shown in Fig 2.

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.