TITLE:
Statistical Analysis of Variables Influencing Type of Birth in Sri Lanka: A Logistic Regression Approach
AUTHORS:
H. P. R. R. Pathirana, N. Varathan
KEYWORDS:
Caesarean, Logistic Regression, Type of Birth, Odds Ratio, Chi-Square Test
JOURNAL NAME:
Open Journal of Statistics,
Vol.8 No.2,
April
13,
2018
ABSTRACT: Caesarean is a major surgical procedure undertaken
in obstetrics and its rate is increasing in Sri Lanka as well as in the world.
In Sri Lanka, health statistics show an increase in caesarean rates from 13.3%
in 1998 to 30.6% by 2007. Due to its potential serious risks and the burden on
the health system, many authorities have recommended reducing the caesarean
rate for many years. This motivated us to study the most influential variables
on the type of birth in Sri Lanka. In this study, based on the Anuradhapura
Teaching Hospital records, entire 805 new born babies’ birth information was
considered during the month of May, 2015. The variable “Type of Birth”
(Normal/Caesarean) was considered as a binary response variable and age,
height, weight of mother and sex, weight, length, shoulder length, head
circumference of the baby were treated as explanatory variables. Logistic
regression was used to model the data and using stepwise regression; mother’s
age, height and weight were identified as
the most influential variables on the type of birth. Further, it was observed
that the odds of having normal birth is 80% higher for woman who belongs to the
age group less than or equal to 30 years compared to woman who belongs to the
age group greater than 30 years. Moreover, the Hosmer-Lemeshow goodness
of fit test was used to check the adequacy of the fitted model. Results from
this study revealed that in future, the type of birth may be predicted by
considering these identified influential variables.