---
title: "Multiple regression: yield on rainfall, fertilizer"
subject: "Probability and Statistics"
chapter: 5
key: "semester_5/probability_and_statistics:multiple-regression-yield-rainfall-fertilizer"
source: https://www.bctengineer.com/q/semester_5/probability_and_statistics/multiple-regression-yield-rainfall-fertilizer
site: BCT Engineering
---

# Multiple regression: yield on rainfall, fertilizer

Probability and Statistics · Chapter 5: Correlation and regression

- Asked in: 2076 Asoj, 5 marks
- Answer checked by Claude Sonnet 5.5 on 2026-10-14
- Page: https://www.bctengineer.com/q/semester_5/probability_and_statistics/multiple-regression-yield-rainfall-fertilizer
- Whole chapter: https://www.bctengineer.com/md/semester_5/probability_and_statistics/chapter-5

## Question

Fit the regression line of yield of crop ('000 tones) on amount of rainfall (mm) and amount of fertilizers used (kg). Also estimate the yield of crop for the year in which rainfall is 13 mm and fertilizer used is 9 kg.
| Yield | 4 | 6 | 7 | 9 | 13 | 15 |
|---|---|---|---|---|---|---|
| Rainfall | 3 | 4 | 6 | 8 | 12 | 15 |
| Fertilizer | 4 | 10 | 14 | 20 | 24 | 30 |

## Short answer

Least squares plane: yield = 1.706 + 0.738·rainfall + 0.082·fertilizer. For 13 mm rainfall and 9 kg fertilizer, estimated yield is 12.03 thousand tonnes.

## Answer

Let y = yield, x₁ = rainfall, x₂ = fertilizer. Fit the plane **y = a + b₁x₁ + b₂x₂** by least squares; n = 6.

#### Normal equations

Σy = na + b₁Σx₁ + b₂Σx₂
Σx₁y = aΣx₁ + b₁Σx₁² + b₂Σx₁x₂
Σx₂y = aΣx₂ + b₁Σx₁x₂ + b₂Σx₂²

#### Calculation of sums

```text
      y     x1     x2    x1y    x2y    x1²    x2²   x1x2
      4      3      4     12     16      9     16     12
      6      4     10     24     60     16    100     40
      7      6     14     42     98     36    196     84
      9      8     20     72    180     64    400    160
     13     12     24    156    312    144    576    288
     15     15     30    225    450    225    900    450
--------------------------------------------------------
     54     48    102    531   1116    494   2188   1034
```

Substituting:

```text
54 = 6a + 48b₁ + 102b₂
531 = 48a + 494b₁ + 1034b₂
1116 = 102a + 1034b₁ + 2188b₂
```

Solving the three equations simultaneously (elimination or Cramer's rule):

a = 1.7061, b₁ = 0.7376, b₂ = 0.0820

**Fitted regression: y = 1.706 + 0.738x₁ + 0.082x₂**

#### Estimate for x₁ = 13 mm, x₂ = 9 kg

y = 1.7061 + 0.7376(13) + 0.0820(9) = **12.03** thousand tonnes.

**Answer: y = 1.706 + 0.738x₁ + 0.082x₂; estimated yield ≈ 12.03 thousand tonnes (about 12032 tonnes).**

## Check yourself

The answer's key points as multiple-choice questions, with the correct option and why.

1. How many normal equations are solved for y = a + b1x1 + b2x2?
   A. Two
   B. Four
   C. Three, for a, b1 and b2
   D. One
   Answer: C. There is one normal equation for each of the three unknowns a, b1, b2. (Key point: Normal equations)

2. The fitted plane is:
   A. y = 0.082 + 0.738x1 + 1.706x2
   B. y = 1.706 + 0.738x1 + 0.082x2
   C. y = 1.706 + 0.082x1 + 0.738x2
   D. y = 54 + 48x1 + 102x2
   Answer: B. Solving gives a = 1.7061, b1 = 0.7376 (rainfall), b2 = 0.0820 (fertilizer). (Key point: Fitted equation)

3. Estimated yield for rainfall 13 mm and fertilizer 9 kg is about:
   A. 9.6
   B. 13.5
   C. 12.03 thousand tonnes
   D. 1.7
   Answer: C. 1.7061 + 0.7376(13) + 0.0820(9) = 12.03. (Key point: Estimation)

## Related in Probability and Statistics

- [Regression of rice yield on tillers](https://www.bctengineer.com/question.md?key=semester_5%2Fprobability_and_statistics%3Arice-yield-tillers-regression) — Probability and Statistics, chapter 5
- [Twists regression; predict at 20%](https://www.bctengineer.com/question.md?key=semester_5%2Fprobability_and_statistics%3Atwists-regression-predict-20) — Probability and Statistics, chapter 5, asked 3×
- [Regression: chemical yield vs temperature](https://www.bctengineer.com/question.md?key=semester_5%2Fprobability_and_statistics%3Ayield-temperature-regression-200c) — Probability and Statistics, chapter 5
- [Fit straight line: humidity and moisture](https://www.bctengineer.com/question.md?key=semester_5%2Fprobability_and_statistics%3Ahumidity-moisture-straight-line-fit) — Probability and Statistics, chapter 5
- [Twists regression; CI for slope](https://www.bctengineer.com/question.md?key=semester_5%2Fprobability_and_statistics%3Atwists-regression-with-ci-slope) — Probability and Statistics, chapter 5, asked 3×
- [Regression: operator experience and performance](https://www.bctengineer.com/question.md?key=semester_5%2Fprobability_and_statistics%3Aexperience-performance-regression-r2) — Probability and Statistics, chapter 5

## Related in other subjects

- [24-hr maximum rainfall for 50-year return period](https://www.bctengineer.com/question.md?key=semester_5%2Fengineering_hydrology%3Agumbel-24hr-max-50yr-semilog) — Engineering Hydrology, chapter 6
- [K-map Σm(7,9,12,13,14,15)+d, NOR-only](https://www.bctengineer.com/question.md?key=semester_3%2Fdigital_logic%3Akmap-nor-sum-7-9-12) — Digital Logic, chapter 3
- [Minterms/maxterms; K-map Σm(0,1,2,4,6,8,9,12,13,14)](https://www.bctengineer.com/question.md?key=semester_3%2Fdigital_logic%3Aminterm-maxterm-kmap-01246) — Digital Logic, chapter 3
- [K-map Σ(1,2,3,8,9,10,11,13,14)+d, POS](https://www.bctengineer.com/question.md?key=semester_3%2Fdigital_logic%3Akmap-pos-form-12389) — Digital Logic, chapter 3
