Exercise 3.1 – Fitting regression lines by least squaresClass 12 Commerce Maths · Chapter 3 Linear Regression · Exercise 3.1 – Maharashtra Board

Textbook: Mathematics and Statistics (Commerce) Part II – Class 12 (Balbharati, official free PDF) · pages 34–42

Correlation tells us how strongly two variables move together; regression goes one step further and gives an equation to predict one variable from the other. In this exercise you fit a straight line to paired data by the method of least squares, write the line of regression of Y on X (to predict Y) and of X on Y (to predict X), and use them for estimates such as a starting salary or a productivity index. The whole job is a careful table of sums followed by two short formulas.

🎧 Listen to the summary

Summary: Exercise 3.1 – Fitting regression lines by least squares

The least-squares line is the straight line for which the sum of squared vertical errors (residuals) is smallest.

Regression of Y on X: Y − ȳ = b_YX(X − x̄) with b_YX = cov(X, Y)/var(X); use it to predict Y from X.

Regression of X on Y: X − x̄ = b_XY(Y − ȳ) with b_XY = cov(X, Y)/var(Y); use it to predict X from Y.

Both lines pass through the point of means (x̄, ȳ).

When the means are whole numbers, work with deviations from the means; otherwise use the raw sums Σx, Σy, Σx², Σy², Σxy.

Key points to remember

  • Dependent variable (response) = the one you predict; independent variable (predictor) = the one you know.
  • b_YX = Σ(x − x̄)(y − ȳ)/Σ(x − x̄)² = (Σxy − n x̄ ȳ)/(Σx² − n x̄²).
  • b_XY = Σ(x − x̄)(y − ȳ)/Σ(y − ȳ)² = (Σxy − n x̄ ȳ)/(Σy² − n ȳ²).
  • Intercepts: a = ȳ − b_YX x̄ for Y on X, a′ = x̄ − b_XY ȳ for X on Y.
  • cov(X, Y) = Σxy/n − x̄ ȳ; var(X) = Σx²/n − x̄².
  • Both regression coefficients and r always have the same sign.
  • Predict Y from X with the Y-on-X line only; predict X from Y with the X-on-Y line only.
  • If the question says which variable is dependent, fit only that regression ('appropriate regression equation').
  • Keep 4 decimal places in b while working; round only the final estimate.
  • If all points lie exactly on a line (r = ±1), the two regression lines coincide.
Want a teacher to explain Exercise 3.1 – Fitting regression lines by least squares?

Get a ✓ Verified tutor for “Exercise 3.1 – Fitting regression lines by least squares” — live online or at home. We aim to suggest up to 3 tutors within 24 hours.

Get a tutor for this chapter →

👩‍🏫 Class 12 Commerce Maths Book classes — live online, request a call back

Prefer a real teacher? TalentJR teachers take live online classes anywhere in India. Tell us what you need and our team will call you with timings and fees.

Live online classesSmall groups or 1:1 with a teacher, from home, any city.
We call you backOur team asks what your child needs, then shares timings and fees.
Home tutor?We are still building our list of home tutors — ask on the call if there is one near you.

Keep learning