c linical r esearch m anagement 512 leslie mcintosh lmcintosh at path.wustl.edu

CLINICAL RESEARCH MANAGEMENT 512

Leslie McIntoshlmcintosh at path.wustl.edu

PART ITables

PART IIHypotheses RevisitedExposure and Outcomes

NOTES ABOUT HYPOTHESES

A hypothesis is a specific conjecture (statement) about a property of population.

There is a null hypothesis and an alternative (or research) hypothesis.

Researchers often expect that evidence supports the alternative hypothesis.

HYPOTHESES: POINTS TO REMEMBER

A hypothesis should be specific enough to be falsifiable

A hypothesis is a conjecture about a population (parameter), not about a sample (statistic).

A valid hypothesis is not based on the sample to be used to test the hypothesis.

2004 by Jeeshim and KUCC625

ERROR TYPES

Decision

Reject H0Do not Reject

H0

H0

TrueType I Errorα: Sig. Level

1-α: Confidence Level

False 1-β: PowerType II Error

β

H0 = Null Hypothesis

PRIMARY INTERESTS

Exposures – what affected the person intentionally (intervention) or not

Outcomes – what happened to the person Clinical measures Non-clinical measures

ACTIVITY

Exposure Outcome

ERRONEOUS CONCLUSIONS

Correlation is not equal to causation;

it is only a requirement for it.

ERRONEOUS CONCLUSIONS

Young children who sleep with the light on are much more likely to develop myopia in later life.

Published from U of Pennsylvania Medical Center in the May 13, 1999 issue of Nature, the study received much coverage at the time in the popular press.

A later study at The Ohio State University did not find a link between infants sleeping with the light on and development of myopia.

It did find a strong link between parental myopia and the development of child myopia, also noting that myopic parents were more likely to leave a light on in their children's bedroom

ERRONEOUS CONCLUSIONS

Correlation does not prove causation

PART IIIPower

DEFINITION OF POWER

The power of a statistical test is the probability that it will correctly lead to the rejection of a false null hypothesis (Greene 2000).

The statistical power is the ability of a test to detect an effect, if the effect actually exists (High 2000).

Statistical power is the probability that it will result in the conclusion that the phenomenon exists (Cohen 1988) .

ANALOGY TO UNDERSTAND POWER

You ask your child to find a tool in the basement. The child returns saying: “I can’t find it.”

What is the probability the tool is in the basement?

If the tool is really in the basement, what is the chance your child found it?

Hartung, 2005

CONCERNS OF POWER

Sample Size Effect Size Variability (Scatter)

Time in basement Type of tool Cleanliness of

basement

Statistics Analogy