### Abstract

This study proposes a time-varying effect model for examining group differences in trajectories of zero-inflated count outcomes. The motivating example demonstrates that this zero-inflated Poisson model allows investigators to study group differences in different aspects of substance use (e.g., the probability of abstinence and the quantity of alcohol use) simultaneously. The simulation study shows that the accuracy of estimation of trajectory functions improves as the sample size increases; the accuracy under equal group sizes is only higher when the sample size is small (100). In terms of the performance of the hypothesis testing, the type I error rates are close to their corresponding significance levels under all settings. Furthermore, the power increases as the alternative hypothesis deviates more from the null hypothesis, and the rate of this increasing trend is higher when the sample size is larger. Moreover, the hypothesis test for the group difference in the zero component tends to be less powerful than the test for the group difference in the Poisson component.

Original language | English (US) |
---|---|

Pages (from-to) | 827-837 |

Number of pages | 11 |

Journal | Statistics in Medicine |

Volume | 36 |

Issue number | 5 |

DOIs | |

State | Published - Feb 28 2017 |

### Fingerprint

### All Science Journal Classification (ASJC) codes

- Epidemiology
- Statistics and Probability

### Cite this

*Statistics in Medicine*,

*36*(5), 827-837. https://doi.org/10.1002/sim.7177

}

*Statistics in Medicine*, vol. 36, no. 5, pp. 827-837. https://doi.org/10.1002/sim.7177

**A time-varying effect model for examining group differences in trajectories of zero-inflated count outcomes with applications in substance abuse research.** / Yang, Songshan; Cranford, James A.; Jester, Jennifer M.; Li, Runze; Zucker, Robert A.; Buu, Anne.

Research output: Contribution to journal › Article

TY - JOUR

T1 - A time-varying effect model for examining group differences in trajectories of zero-inflated count outcomes with applications in substance abuse research

AU - Yang, Songshan

AU - Cranford, James A.

AU - Jester, Jennifer M.

AU - Li, Runze

AU - Zucker, Robert A.

AU - Buu, Anne

PY - 2017/2/28

Y1 - 2017/2/28

N2 - This study proposes a time-varying effect model for examining group differences in trajectories of zero-inflated count outcomes. The motivating example demonstrates that this zero-inflated Poisson model allows investigators to study group differences in different aspects of substance use (e.g., the probability of abstinence and the quantity of alcohol use) simultaneously. The simulation study shows that the accuracy of estimation of trajectory functions improves as the sample size increases; the accuracy under equal group sizes is only higher when the sample size is small (100). In terms of the performance of the hypothesis testing, the type I error rates are close to their corresponding significance levels under all settings. Furthermore, the power increases as the alternative hypothesis deviates more from the null hypothesis, and the rate of this increasing trend is higher when the sample size is larger. Moreover, the hypothesis test for the group difference in the zero component tends to be less powerful than the test for the group difference in the Poisson component.

AB - This study proposes a time-varying effect model for examining group differences in trajectories of zero-inflated count outcomes. The motivating example demonstrates that this zero-inflated Poisson model allows investigators to study group differences in different aspects of substance use (e.g., the probability of abstinence and the quantity of alcohol use) simultaneously. The simulation study shows that the accuracy of estimation of trajectory functions improves as the sample size increases; the accuracy under equal group sizes is only higher when the sample size is small (100). In terms of the performance of the hypothesis testing, the type I error rates are close to their corresponding significance levels under all settings. Furthermore, the power increases as the alternative hypothesis deviates more from the null hypothesis, and the rate of this increasing trend is higher when the sample size is larger. Moreover, the hypothesis test for the group difference in the zero component tends to be less powerful than the test for the group difference in the Poisson component.

UR - http://www.scopus.com/inward/record.url?scp=85005965380&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85005965380&partnerID=8YFLogxK

U2 - 10.1002/sim.7177

DO - 10.1002/sim.7177

M3 - Article

C2 - 27873343

AN - SCOPUS:85005965380

VL - 36

SP - 827

EP - 837

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 5

ER -