Scribd
Upload
13 views

Week 3 - Statistical hypothesis testing

The document outlines the learning objectives and key concepts related to statistical hypothesis testing in biostatistics for Semester 1, 2024-2025. It covers definitions of null and alternative hypotheses, types of errors, decision-making processes, and various hypothesis tests including z-tests, t-tests, and chi-square tests. Additionally, it provides practical examples and scenarios for applying these concepts in real-world situations.

Uploaded by

18 Trần Đức Minh
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
13 views

Week 3 - Statistical hypothesis testing

The document outlines the learning objectives and key concepts related to statistical hypothesis testing in biostatistics for Semester 1, 2024-2025. It covers definitions of null and alternative hypotheses, types of errors, decision-making processes, and various hypothesis tests including z-tests, t-tests, and chi-square tests. Additionally, it provides practical examples and scenarios for applying these concepts in real-world situations.

Uploaded by

18 Trần Đức Minh
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
You are on page 1/ 18

PRACTICE in BIOSTATISTICS

Semester 1, 2024-2025

Statistical Hypothesis
testing
Learning objectives

• Define the null hypothesis and alternative hypothesis

• Know the relation between H0 and H1

• Different types of errors with probabilities

• Understand the concepts: test statistic, decision rule, decision


making, p-value, 1- or 2-tailed test, rejection vs nonrejection
regions, critical region, critical points/values

• Formulars and Excel application


Hypotheses

• Null hypothesis H0
• Alternative hypothesis H1 or HA
• H0 & H1 - Mutually exclusive & Exhaustive
• 2 possible states of nature: H0 is true or H0 is false
→ 2 possible decisions: Fail to reject H0 as true or Reject as H0
false
• 2 types of error: Type I error with probability 𝛼 & Type II error
with probability 𝛽
→ 𝛼 – level of significance, 1 − 𝛽 – power of the test
1- or 2-tailed tests

• A 1-tailed test is used when we are testing for the possibility


of a relationship in one direction only:

A right-tailed test when H1: 𝝁 > 𝝁𝟎 ; 𝒑 > 𝒑𝟎 ; 𝜹𝟐 > 𝜹𝟎 𝟐

A left-tailed test when H1: 𝝁 < 𝝁𝟎 ; 𝒑 < 𝒑𝟎 ; 𝜹𝟐 < 𝜹𝟎 𝟐

• A 2-tailed test is used when we are testing for the possibility


of a relationship in both directions — either greater than or
less than a certain value

H1: 𝝁 ≠ 𝝁𝟎 ; 𝒑 ≠ 𝒑𝟎 ; 𝜹𝟐 ≠ 𝜹𝟎 𝟐
1- or 2-tailed tests
Hypothesis testing (1)

• A statistical method used to make decisions or inferences


about population parameters based on sample data

• The goal is to determine whether there is enough evidence in


a sample to support or reject the H0 about a population

• Significance level 𝜶 is the threshold for rejecting H0 used to


identify:
Critical value(s)

Reject and non-reject regions


Hypothesis testing (2)

• The critical value(s) is(are) the cutoff point(s) defining the boundary
between the reject and non-reject regions of the H0
➢ The reject region (shaded
area in the tails) corresponds
to extreme values where we
would reject H0 because the
test statistic falls far from
the mean of the distribution
➢ The non-reject region is the
area where we do not have
enough evidence to reject H0
Decision rules

p-value - the
probability of the Reject H0 if p-value ≤ 𝛼
observed result
occurring by random
Fail to reject H0 if p-value > 𝛼
chance if H0 is true
Test statistic Reject H0 if |test statistic|> critical value
value(s): z-score(s),
t-score(s), χ2 -score(s)… Fail to reject H0 if |test statistic|≤ critical value
* For one-tailed tests, adjust for the direction of the test
Reject/non-reject Reject H0 if the test statistic falls in the reject area(s)
areas, or critical Fail to reject H0 if the test statistic falls within the non-reject
regions
region
Hypothesis tests
*based on a collected sample with an identified or population number

• Test of hypothesis about population mean:


➢ Using z-test statistic, when:
𝜹 is known & the population is normal
𝜹 is known & the sample size is ≥ 30
➢ Using t-test statistic, when
𝜹 is unknown & the population is normal
• Test of hypothesis about population proportion
➢ Using binomial distribution, when sample size up to 500
➢ Using approximated normal z-distribution, when sample is too large ≥ 500
• Test of hypothesis about population variance
➢ Using chi-square test statistic
Hypothesis tests
*based on a collected sample with an identified or population number

• Test of hypothesis about population mean:


➢ Using z-test statistic: z-score = ഥ𝒙−𝝁
𝜹
𝟎

➢ Using t-test statistic: ഥ


𝒙−𝝁𝟎
t-score = 𝒔 ; with df = n-1
𝒏

• Test of hypothesis about population proportion


➢ Using binomial distribution: p-value at tail(s); with P X = 𝒏!
. 𝒑𝑿 . 𝒒𝒏−𝑿
𝑿!. 𝒏−𝑿 !

ෝ−𝒑𝟎
𝒑
➢ Using approximated normal z-distribution: z-score =
𝒑𝟎 .𝒒𝟎
𝒏

• Test of hypothesis about population variance


➢ Using chi-square test statistic: χ2 -score = 𝒏−𝟏 𝒔𝟐
; with df = n-1
𝜹𝟎 𝟐
A recent research claims that it takes an average of 28
minutes for melittin (bee venom) to form a blister.
Suppose that you want to carry out a hypothesis test of
this claim with significance level 0.1. 𝑛 = 100; 𝑥ҧ =
31.5; 𝑠 = 5.
An automatic machine fills vaccine into 2000µl vials. A
public health specialist wants to test the bull
hypothesis that the average amount filled by the
machine into a vial is at least 2000µl. A random sample
of 40 vials coming out of the machine was selected and
the exact content of the selected vials are recorded.
The sample mean was 1999.6µl. The population
standard deviation is known from past experience to be
1.30µl.

a/ Compute the p-value for this test.

b/ Test the null hypothesis at the 5% significant level.


A coin is to tested for fairness. It is tossed 25 times and
only 8 Heads are observed. Test if the coin is fair at an
𝛼 of 5% (significance level).
A shrimp provider claims that they control the weights
of the shrimp accurately so that the variance of the
weights is not more than 1g2. A random sample of 31
shrimps yields a sample variance of 1.62g2. Is that
sufficient evidence to reject the claim at an 𝛼 of 5%?
A researcher needs to test the null hypothesis that the
average weight of fat per person is 𝜇0 = 12 pounds,
versus the alternative hypothesis that the average
weight is not 12 pounds. The analyst wants to test the
null hypothesis at 𝛼 = 0.05. The sample has 𝑛 =
144, 𝑥ҧ = 14.6, 𝑠 = 7.8.
An analyst for Genscript Protein Company wanted to
test the hypothesis made by British experts that 70% of
all hard-to-make proteins used in the British market
were made in America. The analyst gathered a random
sample of 210 proteins in London and found that 130
were made by the U.S. At the 𝛼 = 0.05 level of
significance, is there evidence to reject the claim of
the British , is there evidence to reject the claim of the
British experts?
The EPA sets limits on the concentrations of pollutants
emitted by various industries. Suppose that the upper
allowable limit on the emission of vinyl chloride is set
at an average of 55 ppm within a range of two miles
around the plant emitting this chemical. To check
compliance with this rule, the EPA collects a random
sample of 100 readings at different times and dates
within the two-mile range around the plant The
findings are that the sample average concentration is
60ppm and the sample standard deviation is 20ppm. Is
there evidence to conclude that the plant in question is
violating the law?
The average lifetime of Vietnamese people is said by
WHO to be an average of 65 years. A researcher
believes that the average life of the Vietnamese is less
than that claimed by WHO above and sets out to prove
that the claim is false. A random sample of 21
Vietnamese individuals is chosen and shows that the
sample average lifetime is 62.5years and the sample
standard deviation is 3. Using 𝛼 = 0.01 , determine
whether there is evidence to conclude that the WHO’s
claim is false.

You might also like