•Surface disinfection procedures within clinic type
LSU-HSC School of Public HealthBiostatistics
21
Randomized Experimental Designs
2. Sampling or Observation Design
Is observational unit = experimental unit ?
or,
is there subsampling of EU ?
LSU-HSC School of Public HealthBiostatistics
22
Randomized Experimental Designs
Sampling or Observation Design
For example,
•Is one measurement taken per mouth, or aremultiple sites measured?
•Is one blood pressure reading obtained or aremultiple blood pressure readings taken?
LSU-HSC School of Public HealthBiostatistics
23
Randomized Experimental Designs
3. Error Control Design
•concerned with actual arrangement ofthe expt’l units
•How treatments are assigned to eu’s
LSU-HSC School of Public HealthBiostatistics
24
Randomized Experimental Designs
3. Error Control Design
Goal: Decrease experimental error
LSU-HSC School of Public HealthBiostatistics
25
Randomized Experimental Designs
3. Error Control Design
Examples:
•CRD – Completely Randomized Design
•RCB – Randomized Complete Block Design
•Split-mouth designs (whole & incomplete block)
•Cross-Over Design
LSU-HSC School of Public HealthBiostatistics
26
Inferential Statistics
•Hypothesis Testing
•Confidence Intervals
LSU-HSC School of Public HealthBiostatistics
27
Hypothesis Testing
•Start with a research question
•Translate this into a testable hypothesis
LSU-HSC School of Public HealthBiostatistics
28
Hypothesis Testing
Specifying hypotheses:
•H0: “null” or no effect hypothesis
•H1: “research” or “alternative” hypothesis
Note:Only the null is tested.
LSU-HSC School of Public HealthBiostatistics
29
Errors in Hypothesis Testing
When testing hypotheses, the chance of making amistake always exists.
Two kinds of errors can be made:
•Type I Error
•Type II Error
LSU-HSC School of Public HealthBiostatistics
30
Errors in Hypothesis Testing
Reality
Decision
H0 True
H0 False
Fail to Reject H0
Type II ()
Reject H0
Type I ()
LSU-HSC School of Public HealthBiostatistics
31
Errors in Hypothesis Testing
•Type I Error
–Rejecting a true null hypothesis
•Type II Error
–Failing to reject a false null hypothesis
LSU-HSC School of Public HealthBiostatistics
32
Errors in Hypothesis Testing
•Type I Error
–Experimenter controls or explicitly sets this error rate -
•Type II Error
–We have no direct control over this error rate -
LSU-HSC School of Public HealthBiostatistics
33
Randomized Experimental Designs
When constructing an hypothesis:
Since you have direct control over Type I errorrate, put what you think is likely to happen in thealternative.
Then, you are more likely to reject H0, since youknow the risk level ().
LSU-HSC School of Public HealthBiostatistics
34
Errors in Hypothesis Testing
Goal of Hypothesis Testing
–Simultaneously minimize chance of making either error
LSU-HSC School of Public HealthBiostatistics
35
Errors in Hypothesis TestingIndirect Control of β
•Power
–Ability to detect a false null hypothesis
POWER = 1 -
LSU-HSC School of Public HealthBiostatistics
36
Steps in Hypothesis Testing
General framework:
•Specify null & alternative hypotheses
• Specify test statistic and -level
• State rejection rule (RR)
• Compute test statistic and compare to RR
• State conclusion
LSU-HSC School of Public HealthBiostatistics
37
Steps in Hypothesis Testing
test statistic
Summary of sample evidence relevant todetermining whether the null or the alternativehypothesis is more likely true.
LSU-HSC School of Public HealthBiostatistics
38
Steps in Hypothesis Testing
test statistic
When testing hypotheses about means, teststatistics usually take the form of a standardizedifference between the sample and hypothesizedmeans.
LSU-HSC School of Public HealthBiostatistics
39
Steps in Hypothesis Testing
test statistic
•For example, if our hypothesis is
•Test statistic might be:
LSU-HSC School of Public HealthBiostatistics
40
Steps in Hypothesis Testing
Rejection Rule (RR) :
Rule to base an “Accept” or “Reject” null hypothesisdecision.
For example,
Reject H0 if |t| > 95th percentile of t-distribution
LSU-HSC School of Public HealthBiostatistics
41
Hypothesis Testing
P-values
Probability of obtaining a result (i.e., test statistic) atleast as extreme as that observed, given the null istrue.
LSU-HSC School of Public HealthBiostatistics
42
Hypothesis Testing
P-values
Probability of obtaining a result at least as extremegiven the null is true.
P-values are probabilities
0 <p< 1 <-- valid range
Computed from distribution of the test statistic
LSU-HSC School of Public HealthBiostatistics
43
Hypothesis Testing
P-values
Generally, p<0.05 considered significant
LSU-HSC School of Public HealthBiostatistics
44
Hypothesis Testing
LSU-HSC School of Public HealthBiostatistics
45
Hypothesis Testing
Example
Suppose we wish to study the effect on bloodpressure of an exercise regimen consisting of walking30 minutes twice a day.
Let the outcome of interest be resting systolic BP.
Our research hypothesis is that following the exerciseregimen will result in a reduction of systolic BP.
LSU-HSC School of Public HealthBiostatistics
46
Hypothesis Testing
Study Design #1:Take baseline SBP (beforetreatment) and at the end of the therapy period.
Primary analysis variable = difference in SBP betweenthe baseline and final measurements.
LSU-HSC School of Public HealthBiostatistics
47
Hypothesis Testing
Null Hypothesis:
The mean change in SBP (pre – post) is equal to zero.
Alternative Hypothesis:
The mean change in SBP (pre – post) is different fromzero.
LSU-HSC School of Public HealthBiostatistics
48
Hypothesis Testing
Test Statistic:
The mean change in SBP (pre – post) divided by thestandard error of the differences.
LSU-HSC School of Public HealthBiostatistics
49
Hypothesis Testing
Study Design #2:Randomly assign patients to controland experimental treatments. Take baseline SBP(before treatment) and at the end of the therapy period(post-treatment).
Primary analysis variable = difference in SBP betweenthe baseline and final measurements in each group.
LSU-HSC School of Public HealthBiostatistics
50
Hypothesis Testing
Null Hypothesis:
The mean change in SBP (pre – post) is equal in bothgroups.
Alternative Hypothesis:
The mean change in SBP (pre – post) is different betweenthe groups.
LSU-HSC School of Public HealthBiostatistics
51
Hypothesis Testing
Test Statistic:
The difference in mean change in SBP (pre – post)between the two groups divided by the standard errorof the differences.
Interval Estimation
Statistics such as the sample mean,median, and variance are called
point estimates
-vary from sample to sample
-do not incorporate precision
Interval Estimation
Take as an example the sample mean:
X ——————>
(popn mean)
Or the sample variance:
S2 ——————> 2
(popn variance)
Estimates
Estimates
Interval Estimation
Recall, a one-sample t-test on thepopulation mean. The test statistic was