Textbook Notes (280,000)

CA (170,000)

York (10,000)

MGMT (200)

MGMT 1050 (70)

Olga Kraminer (9)

Chapter 11

This

**preview**shows half of the first page. to view the full**3 pages of the document.**Chapter 11

Defining Hypothesis Testing

- Hypothesis testing is a statistical procedure that is used to determine whether an

idea or a guess is correct or not

Two types of hypotheses

1. Null hypothesis

2. Alternate hypothesis

Hypothesis Testing Errors

- A type 1 error occurs when we reject a true null hypothesis (the defendant is

innocent and we convict them

- A type 2 error occurs when we not reject a false null hypothesis (ex. The defendant

is guilty and we do not convict them)

- The probability of type 1 error is denoted as α, the sigifiae leel

- The probability of a type 2 error is denoted as β

Writing Hypotheses

- The purpose of hypothesis testing is to verify if your guess about a population is true

- For instance, we use the value of a test statistic, to determine whether we should

reject the null hypothesis or not

Note the following properties about stating the hypothesis:

a) The null hypothesis always goes first and the alternate always goes second

b) The variable after the null hypothesis is always a parameter (since we are trying to

see if our conclusion about a population is correct, it is important we put a

parameter in the statement since parameters describe a population) – watch out for

tricks in m/c that use statistics and ask you if the hypothesis is correctly written

c) The null hypothesis always has the statement that is assumed to be true unless

otherwise proven while the alternative has what we are testing for (looking for

evidence to support)

d) The null hypothesis has an equality in it

e) The alternate hypothesis covers the range that the null hypothesis does not

(together they cover the entire number line so that they are mutually exclusive and

exhaustive)

The P-Value Approach

find more resources at oneclass.com

find more resources at oneclass.com

###### You're Reading a Preview

Unlock to view full version