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 estimate of γ1 and its standard error for data simulated under ZIP with ϕc = 20%.The figure displays box-plots of estimates and their standard errors for γ1 from 1000 replications in (A) and (B); (C) and (D); and (E) and (F) for the consonant (ϕt = ϕc − 5%), neutral (ϕt = ϕc) and dissonant (ϕt = ϕc + 5%) effect case, respectively. For each box of the boxplots, the center line represents the median, the bottom line represents the 25th percentiles and the top line represents the 75th percentiles. The whiskers of the boxplots show 1.5 interquartile range (IQR) below the 25th percentiles and 1.5 IQR above the 75th percentiles, and outliers are represented by small circles. The horizontal line in (A), (C) and (E) represents the true value of γ1 (= 0.4) and the bias, standard deviation (SD), and root mean square error (RMSE) of the estimations of γ1 are shown above its box-plot for each method. The mean and standard deviation (SD) of the standard error (SE) estimations are shown above the box-plot for each method in panels (B), (D) and (F).
© Copyright Policy
Related In: Results  -  Collection

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

pone.0129606.g005: The estimate of γ1 and its standard error for data simulated under ZIP with ϕc = 20%.The figure displays box-plots of estimates and their standard errors for γ1 from 1000 replications in (A) and (B); (C) and (D); and (E) and (F) for the consonant (ϕt = ϕc − 5%), neutral (ϕt = ϕc) and dissonant (ϕt = ϕc + 5%) effect case, respectively. For each box of the boxplots, the center line represents the median, the bottom line represents the 25th percentiles and the top line represents the 75th percentiles. The whiskers of the boxplots show 1.5 interquartile range (IQR) below the 25th percentiles and 1.5 IQR above the 75th percentiles, and outliers are represented by small circles. The horizontal line in (A), (C) and (E) represents the true value of γ1 (= 0.4) and the bias, standard deviation (SD), and root mean square error (RMSE) of the estimations of γ1 are shown above its box-plot for each method. The mean and standard deviation (SD) of the standard error (SE) estimations are shown above the box-plot for each method in panels (B), (D) and (F).

Mentions: We first examine the covariate effect estimates and their SEs on the log scale of count data levels γ1. Fig 5 and Fig 6 are the box plots of the estimation results of γ1 and their standard errors (SEs) for ZIP and ZINB distributed data, respectively, when the true proportion of inflated zeros for unexposed group is 20%and the true value of γ1 is equal to 0.4. Notice that for every method investigated, the standard deviation (SD) of the estimations for ZINB distributed data are larger than those for ZIP distributed data.


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

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

The estimate of γ1 and its standard error for data simulated under ZIP with ϕc = 20%.The figure displays box-plots of estimates and their standard errors for γ1 from 1000 replications in (A) and (B); (C) and (D); and (E) and (F) for the consonant (ϕt = ϕc − 5%), neutral (ϕt = ϕc) and dissonant (ϕt = ϕc + 5%) effect case, respectively. For each box of the boxplots, the center line represents the median, the bottom line represents the 25th percentiles and the top line represents the 75th percentiles. The whiskers of the boxplots show 1.5 interquartile range (IQR) below the 25th percentiles and 1.5 IQR above the 75th percentiles, and outliers are represented by small circles. The horizontal line in (A), (C) and (E) represents the true value of γ1 (= 0.4) and the bias, standard deviation (SD), and root mean square error (RMSE) of the estimations of γ1 are shown above its box-plot for each method. The mean and standard deviation (SD) of the standard error (SE) estimations are shown above the box-plot for each method in panels (B), (D) and (F).
© Copyright Policy
Related In: Results  -  Collection

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

pone.0129606.g005: The estimate of γ1 and its standard error for data simulated under ZIP with ϕc = 20%.The figure displays box-plots of estimates and their standard errors for γ1 from 1000 replications in (A) and (B); (C) and (D); and (E) and (F) for the consonant (ϕt = ϕc − 5%), neutral (ϕt = ϕc) and dissonant (ϕt = ϕc + 5%) effect case, respectively. For each box of the boxplots, the center line represents the median, the bottom line represents the 25th percentiles and the top line represents the 75th percentiles. The whiskers of the boxplots show 1.5 interquartile range (IQR) below the 25th percentiles and 1.5 IQR above the 75th percentiles, and outliers are represented by small circles. The horizontal line in (A), (C) and (E) represents the true value of γ1 (= 0.4) and the bias, standard deviation (SD), and root mean square error (RMSE) of the estimations of γ1 are shown above its box-plot for each method. The mean and standard deviation (SD) of the standard error (SE) estimations are shown above the box-plot for each method in panels (B), (D) and (F).
Mentions: We first examine the covariate effect estimates and their SEs on the log scale of count data levels γ1. Fig 5 and Fig 6 are the box plots of the estimation results of γ1 and their standard errors (SEs) for ZIP and ZINB distributed data, respectively, when the true proportion of inflated zeros for unexposed group is 20%and the true value of γ1 is equal to 0.4. Notice that for every method investigated, the standard deviation (SD) of the estimations for ZINB distributed data are larger than those for ZIP distributed data.

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.