Midterm: Halfway through

Throwback . . .
Different types of data
Descriptive method of describing
data
Normal distribution of data

Introduction to hypothesis
testing: Paired t-test
Comparing two groups: the paired data situation
Hypothesis testing: the null and alternative hypotheses
Relationships between confidence intervals and
hypothesis testing when comparing means
p-values: definition, calculations, and more information
Section A

Are the population #means different?

(continuous data)
Paired design:
Before-after data
Twin data (Matched case-control)
Two independent sample design
Randomized trial

Paired design t-test

Paired DesignExample: Before vs. After
Why pairing?
- Control extraneous noise
- Each observation acts as a control
- Good way to get preliminary data/estimates
to be used to develop further research

Example of Paired design t-test

Ten non-pregnant, pre-menopausal women 1649
years old who were beginning a regimen of oral
contraceptive (OC) use had their blood pressures
measured prior to starting OC use and threemonths after consistent OC use1
The goal of this small study was to see what, if any,
changes in average blood pressure were associated
with OC use in such women

In essence, what we have done is reduce the BP

information on two samples (women prior to OC use,
women after OC use) into one piece of information:
information on the differences in BP between the
samples
This is standard protocol for comparing paired samples
with a continuous outcome measure

95% confidence interval for mean change in BP

in population of women taking oral
contraceptives, after starting OC use compared
to before OC use
Whats the Confidence interval?

Trace metals in drinking water affect the flavor and an unusually high
concentration can pose a health hazard. Ten pairs of data were taken measuring
zinc concentration in bottom water and surface water.
1.) Does the data suggest that the true average concentration in the bottom water
exceeds that of surface water?
2.) Calculate the 90% confidence interval of the data.

Zinc
concentration in
bottom water

.430

Zinc
concentration in
surface water

.415

.266 .567

.531

.707

.238 .390

.410

.605

Location
6

10

.716

.651

.589

.469

.723

.609

.632

.523

.411

.612

Twenty sixth graders were randomly selected from a school district.

Then, they were divided into 11 matched pairs, each pair having
equal IQ's. One member of each pair was randomly selected to
receive special training. Then, all of the students were given an IQ
test. Test results are summarized below.
Pair

Training

No training

95

90

89

85

76

73

92

90

91

90

53

53

67

68

88

90

75

78

10

85

89

11

90

95

1.) Does the special training effective?

2.) What is the 95% Confidence interval?

Two different physicians assessed the number

of palpable lymph nodes in 65 randomly
selected male sexual contacts of men with
AIDS or AIDS-related conditions

What is the 95% CI for difference in mean number of lymph

nodes of Doctor 2 compared to Doctor 1? Is it significant?
Provide a conclusion to your answer.

Type I error - Claim HA is true when in fact H0 is

true
The probability of making a Type I error
is called the alpha-level ( -level) or
significance level

Comparing Means
among Two (or More)
Independent
Populations

Comparing Two Independent Groups

A Low Carbohydrate as Compared with a Low

Fat Diet in Severe
Obesity*
-132 severely obese subjects randomized to
one of two diet groups
-Subjects followed for a six month period

Comparing Two Independent Groups:

Diet Types Study

T-test (UNPAIRED)

independent
groups w/smaller
sample size

< 2 independent
groups