710-12_Hypothesis_testing

710-12_Hypothesis_testing - Qing Liu Assistant Professor of...

Info iconThis preview shows pages 1–9. Sign up to view the full content.

View Full Document Right Arrow Icon
Qing Liu Assistant Professor of Marketing 1
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sampling and Inference Population Sample Inference on the population from the sample parameter μ statistic X A Parameter is a summary measure computed to describe a characteristic of the population Statistic is a summary measure computed to describe a characteristic of the sample
Background image of page 2
Statistical Inference μ σ π Population Parameter Sample Statistic mean s std deviation p proportion difference X 12 X X 2 1 μ−
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
What is a Hypothesis? A Hypothesis is a claim about a population parameter y Attitude toward Pepsi is different between heavy and light users y Sales volume is higher in markets with TV advertising than those without TV advertising y The proportion of males buying a Mini Cooper is higher than females Refers to population parameters ( ) μ
Background image of page 4
Null vs. Alternative Hypothesis Mutually exclusive and collectively exhaustive Alternative Hypothesis ( H a ) y Generally the hypothesis that the researcher claims Null Hypothesis ( H 0 ) y Opposite of the alternative hypothesis y May or may not be rejected based on empirical evidence
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Hypothesis Example y Sales volume will be different in markets with TV advertising than in markets without TV advertising H o : Sales volume is the same for markets with TV advertising than in markets without TV advertising H a : Sales volume is different in markets with TV advertising than in markets without TV advertising
Background image of page 6
Types of Errors Don’t reject H 0 Reject H 0 H 0 True No error Type I H 0 False Type II No error If it is better to let 1000 guilty men go free rather than imprison a single innocent man you want to minimize type I or type II error? (What is H0 in our system of justice?) Decision Truth
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Different Types of Hypotheses y Goodness of fit: Hypothesis about proportions of two (or more) groups y The proportion of women using a credit card that earns reward is different from the proportion of men using a credit card that earns reward.
Background image of page 8
Image of page 9
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 28

710-12_Hypothesis_testing - Qing Liu Assistant Professor of...

This preview shows document pages 1 - 9. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online