LOS a Define/Describe/Interpret Hypothesis Testing

Steps in Hypothesis Testing

Quantitative Methods: 1.
2.
State the hypothesis—relation to be tested.
Select a test statistic.
Application 3. Specify the level of significance.
4. State the decision rule for the hypothesis.
Hypothesis Testing 5. Collect the sample and calculate statistics.
6. Make a decision about the hypothesis.
7. Make a decision based on the test results.
© Kaplan, Inc. 2

LOS a Define/Describe/Interpret Hypothesis Testing LOS b Distinguish Hypothesis Testing

Null and Alternative Hypotheses Two-Tailed Test

Null hypothesis (H0) – contains =, ≥, or ≤ H0: µ = 0 versus Ha: µ ≠ 0
1. The hypothesis to be tested 5% significance level of test
2. Researcher “wants” to reject it
3. Always includes the equal sign
2.5%
2.5% 95%
95% 2.5%
2.5%

Alternative hypothesis (Ha)

1. What the researcher would like to conclude ––1.96
1.96 1.96
1.96
2. What is concluded if the researcher rejects
the null hypothesis RejectHH0
Reject
0
Fail
Fail to RejectHH0
to Reject0 Reject
RejectH0H0

© Kaplan, Inc. 3 © Kaplan, Inc. 4

1
LOS b Distinguish Hypothesis Testing LOS c Explain Hypothesis Testing

One-Tailed Tests Test Statistic and Critical Values

H0: µ ≥ 0 versus Ha: µ < 0 or H0: µ ≤ 0 versus Ha: µ > 0 A test statistic is (1) calculated from sample data and
(2) compared to critical value(s) to test H0.
5% significance
level of test 95%
95%
5%
5% If the test statistic exceeds the critical value (or is
outside the range of critical values), the researcher
1.645
1.645
rejects H0.
Fail to
Fail toReject
RejectHH
0 0 Reject H
Reject H00
Critical values are similar to a confidence interval.
© Kaplan, Inc. 5 © Kaplan, Inc. 6

LOS c,d Explain Hypothesis Testing LOS d Explain Hypothesis Testing

Type I and Type II Errors Hypothesis Tests and

Type I Error: Confidence Intervals
Rejecting true null hypothesis (H0) If a hypothesized mean falls outside a confidence interval for
the population mean, the test statistic for a 2-tailed hypothesis
Significance level is Probability of Type I Error test will fall in the rejection region (at same significance level).
Example: Mean daily return on a portfolio over a 250-day
Type II Error: period has been 0.1%, and the sample standard deviation is
Failing to reject false null hypothesis (H0) 0.25%. Determine whether the mean daily return is different
from zero, using a 95% confidence interval and a
Power of a test is 1 – Probability of Type II Error hypothesis test at a 5% significance level.
© Kaplan, Inc. 7 © Kaplan, Inc. 8

2
LOS d Explain Hypothesis Testing LOS d Explain Hypothesis Testing

Hypothesis Tests and Hypothesis Tests and

Confidence Intervals Confidence Intervals
Hypothesis test: H0: μ = 0 versus Ha: μ ≠ 0
Standard error  s  0.25%  0.0158%
n 250 Large sample size, so we can use a z-statistic
95% confidence interval:
x – 0 0.1% – 0
0.1% ± 1.96(0.0158%) = 0.069% to 0.1310% z-statistic    6.33
s 0.25%
Hypothesized mean of zero falls outside this confidence interval. n 250

© Kaplan, Inc. 9- 4 © Kaplan, Inc. 10 - 2

LOS d Explain Hypothesis Testing

Hypothesis Tests and

Confidence Intervals
Hypothesis test: H0: μ = 0 versus Ha: μ ≠ 0

z-stat = 6.33
Reject H0

–1.96 0 1.96 6.33

© Kaplan, Inc. 11