Question

What method( ANOVA, Regression, Cluster, Factor, etc.) should be used and why? Independent and Dependent variables?

A.    A dataset contains information on new born babies and their parents. Variables shown in Table below:

Name	Variable
ID	Baby number
length	Length of baby (inches)
Birthweight	Weight of baby (lbs)
headcirumference	Head Circumference
Gestation	Gestation (weeks)
smoker	Mother smokes 1 = smoker 0 = non-smoker
motherage	Maternal age
mnocig	Number of cigarettes smoked per day by mother
mheight	Mothers height (inches)
mppwt	Mothers pre-pregnancy weight (lbs)
fage	Father's age
fedyrs	Father’s years in education
fnocig	Number of cigarettes smoked per day by father
fheight	Father's height (inches)
lowbwt	Low birth weight, 0 = No and 1 = yes
mage35	Mother over 35, 0 = No and 1 = yes

Answer 1

1. According to me this is a classification problem where dependent variable is "lowbwt" (Low birth weight). This is a nominal categorical variable. This has only two values, 1 (yes) and 0 (No). This is the reason for calling this problem as classification.
2. Independent variables are all except lowbwt, Name, ID, birthweight.
3. So as a whole we are fitting a model to predict whether a newborn baby is low weight or not based on his/her body information and parents' information.