Is this Accor

t di
true? heory theor ng to
y,
is sph the earth
er
Could
t shape ical in
be fla he earth
t rath
er ?

Hypothesis Testing
CHAPTER 6

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 1
 HYPOTHESIS TESTING
Analysts often confront competing ideas about how financial markets work.
Some of these ideas develop through personal research, experience with
markets, interactions with colleagues or professional literature on finance
and investments.

How can an analyst decide whether statements about the financial world
are probably true or probably false?
Through hypothesis testing

Hypotheses: a statement about the value of a

population parameter developed for the purpose of testing a theory or belief.

Hypothesis Testing: statistical assessment of a statement or idea regarding a population.

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 2
 HYPOTHESIS TESTING
EXAMPLE

Research
question

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 3
 HYPOTHESIS TESTING

Very broad

Two types of errors in hypothesis testing

Type I Error: incorrect reject the null when it is actually true (e.g. reject the null that grape is a fruit, while
grape is indeed a fruit) – incorrect rejection!

Type II Error: incorrect accept the null when it is actually false (e.g. accept the null that earth is flat while earth
is actually round) – incorrect acceptance!

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 4
 HYPOTHESIS TESTING

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 5
FORMULATION OF HYPOTHESES
Two tailed test

Upper tail test

Lower tail test

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 6
 HYPOTHESIS TESTING METHODS

1. Critical value method

2. p-value method
3. Confidence Interval method

All three approaches lead to the same decision

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 7
 STEPS IN HYPOTHESIS TESTING

1. Stating the hypotheses.

2. Identifying the appropriate test statistic and its probability distribution.
3. Specifying the significance level.
4. Stating the decision rule.
5. Collecting the data and calculating the test statistic.
6. Making the statistical decision.
7. Making the economic or investment decision.

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 8
 CRITICAL VALUE METHOD
1. Convert sample statistic (e.g.: sample mean) to the test statistic ( Z or t test statistic )

2. Determine the critical value(s) for a specified level of significance α from a distribution table
⮚ Either the t-distribution or the z-distribution table depending on the test stat used
3. Compare test statistic to the critical value (e.g. the z value from the table for a z-test or the t-value from
the table for a t-test). If the test statistic falls in the rejection region, reject H 0 ; otherwise do not reject
H0. The rejection points are created using the L.O.S

OR if test statistic is > critical value, reject null hypothesis

ALWAYS interpret this in the context of the problem!

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 9
 Test Statistic for Hypothesis Tests of the
Population Mean
Case: Population Variance known [z-test]

If the population sampled is normally distributed (small or large) with known variance σ2, then the test
statistic for a hypothesis test concerning a single population mean, μ, is

Sample mean
hypothesized value of the population mean

the known population standard deviation

If variance is
unknown
Sample size

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 10
 Z-critical values

Under z-test, at a 5% significance level, if test statistic is > critical value of 1.96, or if test statistic is <
critical value of -1.96, we reject the hypothesis!

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 11
 Test Statistic for Hypothesis Tests of the
Population Mean
Case: Population Variance Unknown [t-test]
If the population sampled has unknown variance and either of the conditions below holds:
1. the sample is large, or
2. the sample is small but the population sampled is normally distributed, or approximately normally
distributed, then the test statistic for hypothesis tests concerning a single population mean, μ, is
Sample mean
hypothesized value of the population
mean

sample std. dev

The denominator of the
Degrees of
t-statistic is an estimate
freedom Sample size of the sample mean
standard error

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 12
 Z-test and t-test

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 13
Hypothesis testing examples

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 14
 Hypothesis testing examples
Problem 1 solutions

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 15
Hypothesis testing examples

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 16
 Hypothesis testing examples
Problem 2 Solutions

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 17
Hypothesis testing examples

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 18
 Hypothesis testing examples
Problem 3 solution

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 19
 THE P-VALUE METHOD
p-value: the smallest level of significance for which the null can be rejected. The
smaller the p-value, the easier it is to reject the null!

❑ p-value is the probability that lies above the test statistic in the upper tail or
below the test statistic in the lower tail for one-tailed tests.
❑ p-value is the sum of the probability that lies above the test statistic in the upper
tail and the probability that lies below the test statistic in the lower tail for two-
tailed tests.
❑ Decision to accept or reject the null (for both one- and two-tailed tests):
• Sig. Level > p-value: reject the null
• Sig. Level <= p-value: accept the null

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 20
 THE P-VALUE METHOD

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 21
 THE P-VALUE METHOD

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 22
THE P-VALUE METHOD EXAMPLES

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 23
 THE P-VALUE METHOD EXAMPLES
Problem solution

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 24
THE P-VALUE METHOD EXAMPLES

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 25
THE P-VALUE METHOD EXAMPLES

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 26
THE P-VALUE METHOD EXAMPLES

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 27
THE P-VALUE METHOD EXAMPLES

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 28
THE P-VALUE METHOD EXAMPLES

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 29
Hypothesis testing steps summary

Institute, CFA. Quantitative Investment Analysis, 4th Edition. John Wiley & Sons P&T, 20200907. 30