Gao, Qi
(2019)
Multinomial logistic regression and group-based trajectory modeling for longitudinal data of contraceptive methods and recognition of abusive behaviors among women seeking family planning clinical care.
Master's Thesis, University of Pittsburgh.
(Unpublished)
This is the latest version of this item.
Abstract
In the family planning study, Addressing Reproductive Coercion in Health Settings (ARCHES), an intervention to reduce intimate partner violence (IPV) and reproductive coercion (RC), was offered by healthcare providers to women seeking reproductive healthcare services. To evaluate the effect of ARCHES, three surveys were administered by the women during the one-year period of study; from the above study, the data indicated that ARCHES failed to provide extra help in reduction of IPV or RC compared to standard-of-care.
In this thesis, we were interested in the association between different birth control methods and the intervention, age, race, experiences of IPV/RC, and relationship status. Also, we were interested in recognition of abusive behaviors experienced by individual women in terms of time, unconditionally and also conditionally on whether they received the intervention or not, their ages, relationship status, IPV, RC, race and birth control methods. Thus, I demonstrated the following: (a) the application of a multinomial logistic regression model to find the association between contraceptive methods and variables of interest and we hypothesized that there should exist associations between IPV/RC and choices of contraceptive methods; and (b) the application of group-based trajectory modeling (GBTM) to delineate and describe distinct subpopulations that had similar longitudinal trajectories in recognition of abusive behaviors with and without taking into consideration risk factors, and we hypothesized that women’s individual level of recognizing abusive behaviors over time would be associated with different choices of birth control methods and experiences of IPV/RC.
Public Health Relevance:
This study proposed a method which could determine if intervention, IPV, RC and characteristics of women were associated with contraceptive methods; this study also proposed a method which could classify distinct groups of women according to the 1-year longitudinal trajectory patterns of women’s recognition of abusive behaviors to find the factors that distinguish groups of women. The models built would be of great significance to determine the factors related to choices of contraceptive methods, which would help in designing a study to reduce risk for IPV/RC, and the built models would provide important information for further study of abusive behaviors.
Share
| Citation/Export: |
|
| Social Networking: |
|
Details
| Item Type: |
University of Pittsburgh ETD
|
| Status: |
Unpublished |
| Creators/Authors: |
|
| ETD Committee: |
|
| Date: |
25 June 2019 |
| Date Type: |
Publication |
| Defense Date: |
12 April 2019 |
| Approval Date: |
25 June 2019 |
| Submission Date: |
31 March 2019 |
| Access Restriction: |
No restriction; Release the ETD for access worldwide immediately. |
| Number of Pages: |
72 |
| Institution: |
University of Pittsburgh |
| Schools and Programs: |
School of Public Health > Biostatistics |
| Degree: |
MS - Master of Science |
| Thesis Type: |
Master's Thesis |
| Refereed: |
Yes |
| Uncontrolled Keywords: |
GBTM, multinomial logistic regression |
| Date Deposited: |
25 Jun 2019 17:02 |
| Last Modified: |
25 Jun 2019 17:02 |
| URI: |
http://d-scholarship.pitt.edu/id/eprint/36992 |
Available Versions of this Item
-
Multinomial logistic regression and group-based trajectory modeling for longitudinal data of contraceptive methods and recognition of abusive behaviors among women seeking family planning clinical care. (deposited 25 Jun 2019 17:02)
[Currently Displayed]
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
 |
View Item |
![[feed]](/images/feed-icon-32x32.png){kind=icon}