Types of errors

SCORE PROJECT
Introductions

 Statistical hypothesis – a hypothesis that is testable on the

basis of observed data modelled as the realized values taken by Induction
a collection of random variables.
 Hypothesis – a proposed explanation for a phenomenon.
 Observable quantity (syn.: observable variable) – a variable that Test of prediction Hypothesis
can be observed and directly measured.
 Statistical model – mathematical model that is composed of a set
of statistical assumptions concerning the generation of sample data Test of Deduction
(and similar data from a larger population). prediction
 Random variable (random quantity, aleatory variable, or
stochastic variable) – variable whose values depend on the
outcomes of a random phenomenon
Prediction
Introduction

 Null hypothesis – a default hypothesis that a

quantity to be measured is zero (null).
 Hypothesis testing – collecting data and measuring
how likely the particular set of data is (assuming the
null hypothesis is true), when the study is on a
randomly selected representative sample.
 Result of test
 Corresponds with reality  correct decision has
been made.
 Does not correspond with reality  an error has
occurred
Statistical error

 Statistical error in statistical test theory – an integral part of hypothesis testing.

 The test is about: choosing two competing prepositions called:
1. Null hypothesis
2. Alternative hypothesis

There are two situations in which the decision is wrong:

3. The null hypothesis may be true, whereas we reject H0

4. The alternative hypothesis H1 may be true, whereas we do not reject H0.

 Testing the characteristic of a population

P-value < α  Reject H0 theory

𝑃
  ( 𝑠𝑡𝑎𝑡𝑖𝑠𝑡𝑖𝑐 | 𝐻 𝑂 𝑖𝑠 𝑡𝑟𝑢𝑒 ¿
P-value ≥ α  Fail to reject H0 theory

Reality
Population
sample H0 is true H0 is false
Reject the H0 Type I error Correct conclusion
Fail to reject the H0 Correct conclusion Type II error

Population
Types of errors

 Type I error – the mistaken rejection the null

hypothesis (false positive)
 Type II error – the mistaken acceptance of the
null hypothesis (false negative)
 Crossover error rate – the point at which Type I
and Type II errors are equal. It represents the best
way of measuring a biometrics’ effectiveness.
 A system with a lower CER value provides more
accuracy than a system with a higher CER value.
Examples

 A large nationwide poll recently showed an unemployment rate of 9% in the US. The mayor of a local town wonders if
this national result holds true for her town, so she plans on taking a sample of her residents to see if the unemployment
rate is significantly different than 9% in her town.
 Let p represent the unemployment rate in her town. The hypotheses are:
 H0: p=0,09
 HA: p≠0,09
a) Under which of the following conditions would the mayor commit a Type I and Type II error?
Scenarios:
1. She concludes the town’s unemployment rate is not 9%, when it actually is.
2. She concludes the town’s unemployment rate is not 9% when it actually is not.
3. She concludes the town’s unemployment rate is 9% when it actually is
4. She concludes the town’s unemployment rate is 9% when it actually is not.
Thank you!
‫شكراً لك‬
Grazie!
Faleminderit!