6. Evaluating the contribution of an additional predictor variable Aa Aa A study

Question

6. Evaluating the contribution of an additional predictor variable Aa Aa A study conducted at Baystate Medical Center in Springfield, Massachusetts, identified factors that affect the risk of giving birth to a low-birth-weight baby. Low birth weight is defined as weighing less than 2,500 grams (5 pounds, 8 ounces) at birth. Low-birth-weight babies have increased risk of health problems, disability, and death. [Source: Hosmer, D., & Lemeshow, S. (2000). Applied logistic regression (2nd ed.). Hoboken, NJ: Wiley You conduct a similar study focusing on the age (AGE) and weight gain (GAIN) of the mothers as predictors of their babies' birth weight (BIRTHWT) among 54 low-birth-weight babies. Before you estimate the regression equation, you calculate the Pearson correlations among the three variables you have measured: Correlations BIRTHWT AGE GAIN BIRTHWT 1.000 .3799 1925 AGE .3799 1.000 .0864 GAIN 1925 .0864 1.000 Your regression equation predicted R2 = 17.00% of the variance for the baby's birth weight (Y). The regression equation is: Y = -28.3843 AGE + 5.1100 GAIN + 2,582.7755

Explanation / Answer

Age predicts the -28.3843 of the variance for the birthweight values. The additional amount of variance predicted by the relationship between GAIN and BIRTHWT when AGE is already in the equation is 5.1100 Additional variability by adding GAIN is 1071171.7 F ratio to evaluate the contribution of GAIN is 5.223 with (2,51) degrees of freedom The value that bounds the critical region for F ratio at alpha 0.05 is 0.0086 At 5% level of significance with p value 0.0086 we can significantly conclude that adding GAIN to regression equation improvws the prediction compared to using AGE as asingle predictor

Related Questions

Navigate

• Browse (All)
• Browse 6
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.