Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
6 views3 pages

Statistical Analysis With Math Steps

The document presents a statistical analysis example involving correlation, regression, chi-square test, and hypothesis testing based on a dataset of 5 students. It calculates a strong positive correlation (r = 0.996) and establishes a regression equation (Y = 41 + 5.5X) to predict exam scores based on study hours. The chi-square test indicates no significant association between attendance and exam results, concluding that while study hours predict scores strongly, attendance does not significantly affect results.

Uploaded by

jiapia13
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
6 views3 pages

Statistical Analysis With Math Steps

The document presents a statistical analysis example involving correlation, regression, chi-square test, and hypothesis testing based on a dataset of 5 students. It calculates a strong positive correlation (r = 0.996) and establishes a regression equation (Y = 41 + 5.5X) to predict exam scores based on study hours. The chi-square test indicates no significant association between attendance and exam results, concluding that while study hours predict scores strongly, attendance does not significantly affect results.

Uploaded by

jiapia13
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

Statistical Analysis Example with

Mathematical Steps
This document includes a fully worked example covering correlation, regression, observed
vs expected values, chi-square test, and hypothesis testing using the alpha (α) level.

Step 1: Dataset
We will use the following dataset of 5 students (for simplicity):

Student | Hours Studied (X) | Exam Score (Y)


--------|-------------------|----------------
1 |2 | 50
2 |4 | 65
3 |6 | 75
4 |8 | 85
5 | 10 | 95

Step 2: Correlation Coefficient (r)


Formula:
r = Σ[(X - X̄ )(Y - Ȳ)] / sqrt[Σ(X - X̄ )² * Σ(Y - Ȳ)²]

Mean of X = (2+4+6+8+10)/5 = 6
Mean of Y = (50+65+75+85+95)/5 = 74

Now compute deviations and products:

X Y (X−X̄ ) (Y−Ȳ) (X−X̄ )(Y−Ȳ) (X−X̄ )² (Y−Ȳ)²


2 50 -4 -24 96 16 576
4 65 -2 -9 18 4 81
6 75 0 1 0 0 1
8 85 2 11 22 4 121
10 95 4 21 84 16 441

Σ(X−X̄ )(Y−Ȳ) = 220


Σ(X−X̄ )² = 40
Σ(Y−Ȳ)² = 1220

r = 220 / sqrt(40 × 1220) ≈ 220 / 220.9 ≈ 0.996


Interpretation: Strong positive correlation.

Step 3: Simple Linear Regression


Regression line: Y = a + bX

b = Σ[(X−X̄ )(Y−Ȳ)] / Σ(X−X̄ )² = 220 / 40 = 5.5


a = Ȳ − bX̄ = 74 − (5.5)(6) = 74 − 33 = 41

So regression equation:
Y = 41 + 5.5X

Example: Predict score for X = 8:


Y = 41 + 5.5×8 = 41 + 44 = 85 → Matches actual score.

Step 4: Observed vs Expected Scores


Use regression line to find expected scores and compare with actual:

X | Actual Y | Predicted Y = 41 + 5.5X | Error


2 | 50 | 52 | -2
4 | 65 | 63 | +2
6 | 75 | 74 | +1
8 | 85 | 85 |0
10| 95 | 96 | -1

Step 5: Chi-Square Test


Hypothesis: Attendance and Result are independent.

Contingency Table:
| Pass | Fail | Total
------------|------|------|------
Low Att. | 1 | 2 | 3
High Att. | 4 | 1 | 5
Total |5 |3 |8

Expected (Low, Pass) = (3×5)/8 = 1.875


Expected (Low, Fail) = (3×3)/8 = 1.125
Expected (High, Pass) = (5×5)/8 = 3.125
Expected (High, Fail) = (5×3)/8 = 1.875

χ² = Σ[(O−E)² / E]
= (1−1.875)²/1.875 + (2−1.125)²/1.125 + (4−3.125)²/3.125 + (1−1.875)²/1.875
≈ 0.408 + 0.680 + 0.245 + 0.408 = 1.741

Degrees of freedom = (2−1)(2−1) = 1


Critical value (α=0.05) = 3.841

Conclusion: 1.741 < 3.841 → Fail to reject H₀ → No significant association.

Step 6: Alpha (α) and Hypothesis Testing


We used α = 0.05 throughout.

- Correlation: r = 0.996 → Strong → Significant


- Regression: Good fit, low error → Significant
- Chi-Square: χ² = 1.741 < 3.841 → Not significant

Final Conclusion: Study hours predict exam scores strongly. However, no strong evidence
was found linking attendance to results.

You might also like