Maternal and child health researchers are concerned about the outcome of low bir
ID: 3325369 • Letter: M
Question
Maternal and child health researchers are concerned about the outcome of low birth weight in the population currently under investigation. Suppose they gather a sample of women in the population and record their health status with regard to many highly impacting co-variables. The research question in their case is whether maternal depression significantly impacts the likelihood of low birth weight. Assume the following computerized output represents the final multiple regression model.
Analysis Of Maximum Likelihood Parameter Estimates
Parameter
DF
Estimate
Standard Error
Wald 95% Confidence Limits
Wald Chi-Square
Pr > ChiSq
Intercept
1
0.1872
0.0538
0.0818
0.2925
12.12
0.0005
dep
1
-0.0065
0.0284
-0.0622
0.0492
0.05
0.8201
poverty
1
-0.0634
0.0320
-0.1262
-0.0006
3.92
0.0478
bmicontinuous
1
-0.0018
0.0015
-0.0048
0.0012
1.45
0.2287
Scale
1
0.2756
0.0076
0.2611
0.2909
A) Write out your model in symbols incorporating your beta coefficients.
B) What can be said about the association between maternal depression and low birth weight?
C) Which of the co-variables included has a significant relationship with the outcome?
Analysis Of Maximum Likelihood Parameter Estimates
Parameter
DF
Estimate
Standard Error
Wald 95% Confidence Limits
Wald Chi-Square
Pr > ChiSq
Intercept
1
0.1872
0.0538
0.0818
0.2925
12.12
0.0005
dep
1
-0.0065
0.0284
-0.0622
0.0492
0.05
0.8201
poverty
1
-0.0634
0.0320
-0.1262
-0.0006
3.92
0.0478
bmicontinuous
1
-0.0018
0.0015
-0.0048
0.0012
1.45
0.2287
Scale
1
0.2756
0.0076
0.2611
0.2909
Explanation / Answer
Part (A)
Model:
Birth weight
= 0.1872 – 0.0065dep – 0.0634poverty – 0.0018bmicontinuous + 0.2756Scale + ,
where = error which is assumed to be N(0, 2). ANSWER
Part (B)
Since 95% Confidence Limits for the beta coefficient of dep includes 0, the corresponding beta coefficient is not significant. This indicates that dep (i.e., maternal depression) does not impact low birth weight. ANSWER
Part (C)
Of all the given explanatory (independent) variables, the 95% Confidence Limits for the beta coefficient does not include 0 only for poverty. This indicates that only poverty impacts low birth weight. Further, the corresponding beta coefficient of – 0.-0634 being negative, we conclude that the impact is on the opposite direction. i.e., as poverty increases, birth weight decreases. ANSWER