Tell me more ×
Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.
up vote 0 down vote favorite

The average height and weight of a group of students turned out to be 5 ft 6 inches and 65 kilograms respectively. The correlation between heights and weights was found to be 0.6. Using the regression equation for predicting weight from height, the estimated weight of a 6 ft tall student was calculated to be 80 kilograms. Predict the height of a student whose weight is 60 kilograms

share|improve this question
please give me full solution of it. I can't solve it – Argha Jul 16 '12 at 6:08
Think about what the equation of the line of best fit (for weight in terms of height) might be. – user22805 Jul 16 '12 at 7:14
Try the model $h(w) = h_0 + \alpha w$. Figure out what $h_0$ and $\alpha$ must be. – copper.hat Jul 16 '12 at 8:23

1 Answer

up vote 0 down vote accepted

The fitted model can be used to predict height from weight using h= a + bw where a and b are the fitted regression coefficients (intercept and slope respectively).

Now if h=a + bw (h-a)/b = w. Use this equation to solve for w given h.

share|improve this answer
the correlation between heights and weights is 0.6. then why we assume the linear function – Argha Jul 17 '12 at 10:06
Linear regression is historically the classical approach first applied by Galton (late 19th cwntury). If you view the correlation between height and weight to be weak enough that a nonlinear relationship between height and weight might increase the correlation you should try it. But first look at a scatterplot and the residuals. It is possible that the scatter plot will show that the linear function best describes how h and w are related and the "low" correlation is strictly due to a large variance for the residuals. – Michael Chernick Jul 17 '12 at 10:47

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.