Scribd
Upload
21 views2 pages

CFA Level 1: Tests of Independence Guide

Reading 9 focuses on parametric and non-parametric tests of independence, highlighting their differences in assumptions and applications for hypothesis testing. Parametric tests rely on specific distributional assumptions, while non-parametric tests require fewer assumptions and are suitable for ordinal data or small sample sizes. The chi-square test of independence is discussed for testing the relationship between two categorical variables, emphasizing the importance of expected frequencies for validity.

Uploaded by

SIDDHARTH 80
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
21 views2 pages

CFA Level 1: Tests of Independence Guide

Reading 9 focuses on parametric and non-parametric tests of independence, highlighting their differences in assumptions and applications for hypothesis testing. Parametric tests rely on specific distributional assumptions, while non-parametric tests require fewer assumptions and are suitable for ordinal data or small sample sizes. The chi-square test of independence is discussed for testing the relationship between two categorical variables, emphasizing the importance of expected frequencies for validity.

Uploaded by

SIDDHARTH 80
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

CFA Level 1 Quant Methods

Great! Let’s proceed with Reading 9: Parametric and Non-Parametric Tests of Independence. This
reading builds on hypothesis testing and shows when and how to use different test types based on data
characteristics.

📘 READING 9: Parametric and Non-Parametric Tests of


Independence

LOS 9.a: Compare and contrast parametric and non-parametric tests and describe
their use in testing a hypothesis.

📊 Parametric Tests:
Rely on specific distributional assumptions (typically normality).

Require estimation of parameters (mean, variance).

Test Type Used When...

t-test Comparing means (known/unknown variance)


F-test Comparing variances

z-test Large sample size with known population σ

📉 Non-Parametric Tests:
Make fewer assumptions about the population.

Used when:

Distribution is unknown or not normal


Data is ordinal, ranked, or has outliers

Common Non-Parametric Tests Purpose

Wilcoxon signed-rank Median differences (paired samples)

Mann-Whitney U test Differences between 2 groups


Kruskal-Wallis Multiple independent groups

Spearman rank correlation Relationship between ranked variables

✅ CFA Tip: Use non-parametric tests for small sample sizes with skewed or ordinal data.
LOS 9.b: Describe how the chi-square test of independence is used and interpret its
results.

🔍 Chi-Square Test of Independence:


Printed using ChatGPT to PDF, powered by PDFCrowd HTML to PDF API. 1/2
Used to test whether two categorical variables are independent.
Based on observed vs expected frequencies.

🧮 Test Statistic:
(Oi − Ei )2
χ =∑
2 ​ ​

Ei ​

Oi : observed frequency
​

Ei : expected frequency under independence


​

✅ Steps:
1. Set up a contingency table of counts.
2. Calculate expected values:

(Row Total) ⋅ (Column Total)


E=
Grand Total
​

3. Calculate χ2 and compare with critical value.

4. Reject H0 if test statistic > critical value.


​

❗ Key Assumption: Expected frequency in each cell should be ≥ 5 for test validity.
📘 Interpretation:
If χ2 is large → reject H0 → variables are not independent.
​

✅ READING 9 TAKEAWAYS:
LOS Concept Key Insight
9.a Parametric vs non-parametric Non-parametric = fewer assumptions

9.b Chi-square test of independence Use with contingency tables for categorical variables

Would you like me to continue with Reading 10: Simple Linear Regression (LOS 10.a–10.f)?

Printed using ChatGPT to PDF, powered by PDFCrowd HTML to PDF API. 2/2

You might also like