Research Hypothesis
What the researcher thinks will happen, or thinks the relationship between
variables really is. To test a research hypothesis, a researcher needs:
Statistical Hypotheses

Represent the mathematical relationship presumed to exist between 2 or more population
parameters. Before you begin a research project, researchers need a :
Null hypothesis,
and an
Alternative hypothesis

Null Hypothesis
states that there is no difference between groups in the
population. Any difference between groups is due to sampling error. When we assume that
sampling error is the cause for differences in samples, we fail to reject the null hypothesis.
Statistical symbol: H
0.
Example: Keeping customers on hold for ten seconds or less when they
call for service will have no impact on overall customer satisfaction. Null Hypothesis is H
0
: u
1
=u
2
.
Alternative Hypothesis
States that there is difference between the groups in the population.
More of a difference than we'd expect by chance. Statistical symbol: H
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '08
 Mendez
 Null hypothesis, Statistical hypothesis testing, researcher, Statistical significance

Click to edit the document details