STA 102: Commonly Used Statistical Tests in Medical Research (Part I)

1
STA 102 Commonly Used Statistical Tests in
Medical Research (Part I)

• Lecturer Dr. Daisy Dai
• Department of Medical Research

2
Who are biostatisticians?

• Ashley Sherman
• Phone [phone]
• aksherman_at_cmh.edu
• Daisy Dai
• Phone [phone]
• Email hdai_at_cmh.edu

• Consultation
• Experimental design and sampling plan
• Collaboration in presentation and publication of
  studies
• Education
• Research

3
Statistical Courses

• SPSS 201 Using SPSS to perform statistical tests
  I
• SPSS 202 Using SPSS to perform statistical tests
  II
• SPSS 204 Using SPSS to manage data
• SPSS 203 Summarize data with tables and graphs

• STA 101 Properly Setting up and Designing a
  Clinical Research Study Including Power Analysis
  for Proper Patient Numbers
• STA 102 Commonly Used Statistical Tests in
  Medical Research - Part I
• STA 103 Commonly Used Statistical Tests in
  Medical Research - Part II

4
Core Knowledge in Scholarly Activities
recommended by ABP

• Hypothesis testing
• Distinguish the null hypothesis from an
  alternative hypothesis.
• Interpret the results of hypothesis testing.

5
Core Knowledge in Scholarly Activities
recommended by ABP

• Statistical tests
• Understand the appropriate use of the chi-square
  test versus t-test
• Understand the appropriate use of analysis of
  variance (ANOVA)
• Understand the appropriate use of parametric (eg,
  t-test, ANOVA) versus non-parametric (eg,
  Mann-Whitney U, Wilcoxon) statistical tests
• Interpret the results of chi-square tests
• Interpret the results of t-tests

6
Core Knowledge in Scholarly Activities
recommended by ABP

• Statistical tests (Continued)
• Understand the appropriate use of a paired and
  non-paired t-test
• Determine the appropriate use of a 1- versus
  2-tailed test of significance
• Interpret a p-value
• Interpret a p-value when multiple comparison have
  been made
• Interpret a confidence interval
• Indentify a type I error
• Identify a type II error.

7
Statistical Testing Procedures

• Clarify study objectives.
• Establish hypotheses.
• Determine the outcome variables, treatment
  groups, risk factors and covariates.
• Perform appropriate statistical testing.
• Interpret results.

8
Misinterpretation Fluoridated water supplies

• Burke and Yiamouyannis (1975) considered 10
  fluoridated and 10 non-fluoridated towns in the
  USA. In the Fluoridated towns, the cancer
  mortality rate had increased by 20 between 1950
  and 1970, whereas in the non-fluoridated towns
  the increase was only 10. From this they
  concluded that fluoridation caused cancer.

9
Fluoridated water supplies (Continued)

• However, Oldham and Newell (1977), in a careful
  analysis of the changes in age-gender-ethnic
  structure of the 20 cities between 1950 and 1970,
  showed that in fact the excess cancer rate in the
  fluoridated cities increased by only 1 over the
  20 years, while in the un-fluoridated cities the
  increase was 4. They concluded from this that
  there was no evidence fluoridation caused cancer.

10
Continuous Variables

• Two or multiple treatment groups

11
Two samples t-test

• Compare the means of a normally distributed
  interval dependent variable for two independent
  groups.

12
Case Study FEV1 Changes

• A new compound, ABC-123, is being developed
  for long-term treatment of patients with chronic
  asthma. Asthma patients were enrolled in a
  double-blind study and randomized to receive
  daily oral or a placebo for 6 weeks.

asthmatic patients
Placebo
Test
FEV1 after 6-week treatment
13
FEV1 Data
Test Group Test Group Test Group
Patient ID Baseline week 6
101 1.35 n/a
103 3.22 3.55
106 2.78 3.15
108 2.45 2.3
109 1.84 2.37
110 2.81 3.2
113 1.9 2.65
116 3 3.96
118 2.25 2.97
120 2.86 2.28
121 1.56 2.67
124 2.66 3.76
Placebo Group Placebo Group Placebo Group
Patient ID Baseline week 6
102 3.01 3.9
104 2.24 3.01
105 2.25 2.47
107 1.65 1.99
11 1.95 n/a
112 3.05 3.26
114 2.5 2.55
115 1.6 2.2
117 .77 2.56
119 2.06 2.9
122 1.71 n/a
123 3.54 2.92
14
What is the difference between std and std error?
P-value
P-value
15
Mean and Error Bar

• Conclusion
• As compared to placebo, the new drug did not
  show any effect on FEV1.

16
Paired t-test

• Compare the means of a normally distributed
  interval dependent variable for two related
  groups.

Test Group Test Group Test Group
Patient ID Baseline week 6
101 1.35 n/a
103 3.22 3.55
106 2.78 3.15
108 2.45 2.3
109 1.84 2.37
110 2.81 3.2
113 1.9 2.65
116 3 3.96
118 2.25 2.97
120 2.86 2.28
121 1.56 2.67
124 2.66 3.76
17
Conclusion For subjects on the new drug, FEV1
at week 6 is significantly higher than baseline.
P-value
18
One-way ANOVA

• Test for differences of the means for continuous
  variables in multiple independent treatment
  groups.

19
Case Study HAM-A Scores in GAD
Patients with GAD

• A new serotonin-update inhibiting agent,
  SN-X95, is being studied in subjects with general
  anxiety disorder (GAD). Fifty-two subjects
  diagnosed with GAD were enrolled and randomly
  assigned to one of three treatment groups three
  treatment groups 25mg SN-X95, 100mg SN-X95 or
  placebo. After 10 weeks of once-daily oral dosing
  in a double-blind fashion, a test based on the
  Hamilton Rating Scale for Anxiety (HAM-A) was
  administered. This test consists of 14
  anxiety-related items (e.g. anxious mood,
  tension, insomnia, fear, etc.), each rated
  by the subject as no present, mild,
  moderate, severe, or very severe. HAM-A
  test scores were founded by summing the coded
  values of all 14 items using the numeric coding
  scheme of 0 for not present, 1 for . Are there
  any differenceds in means HAM-A test score among
  the three groups?

100 mg SN-X95
25mg SN-X95
Placebo
HAM-A Score after 10-week treatment
20
Data
Lo-Dose Hi-Dose Placebo
21 16 22
18 21 26
19 31 29
99 25 19
28 23 99
22 25 33
30 18 37
27 20 25
28 18 28
19 16 26
23 24 99
22 22 31
20 21 27
19 16 30
26 33 25
35 21 22
99 17 36
21
P-value
22
Mean and Error Bar

• Conclusion
• There is significant difference in mean HAM-A
  among three treatment at 95 confidence level.

23
Categorical Variables

• Two or multiple treatment groups

24
Fishers Exact Test

• A conservative non-parametric test about a
  relationship between two categorical variables.

Responders Non-responders Total
Group 1 N11 N12 N11N12
Group 2 N21 N22 N21N22
Combined N11N21 N12 N22 N
25
Case Study CHF Incidence in CABG after ARA

• A new adenosine-releasing agent (ARA), thought
  to reduce side effects in patients undergoing
  coronary artery bypass surgery (CABG), was
  studied in a pilot trial.

CHF No CHF Total
ARA 2 (6) 33 35
Placebo 5 (25) 20 25
Combined 7 53 60
Fishers exact test p0.0455
26
Chi-square test

• Test a relationship between two categorical
  variables. The chi-square test assumes that the
  expected value for each cell is five or higher.

27
Case Study ADR Frequency with Antibiotic
Treatment

• A study was conducted to monitor the incidence
  of GI adverse drug reactions of a new antibiotic
  used in lower respiratory tract infections.

Responders Non-responders Total
Test (new antibiotic) 22 (33) 44 66
Control (erythromycin) 28 (54) 24 53
Combined 50 (42) 68 118
Chi-square test p0.0252 Fishers exact test
p0.0385
28
Other tests

• One-way repeated measures ANOVA
• Repeated measures logistic regression
• Factorial ANOVA
• Friedman test
• Factorial logistic regression
• Simple Linear Regression
• Multiple Regression

• Factor analysis
• Multiple logistic regression
• Discriminant analysis
• One-way MANOVA
• Multivariate multiple regression
• Canonical correlation
• Analysis of covariance

29
In summary

• Use and abuse of statistics
• Five commonly used statistical testing
• case studies
• Results interpretation

30
Thank You

• For more information, visit my website
• http//www.childrensmercy.org/content/view.aspx?id
  9740
• Or go to Scope -gtResearch -gt Statistics

31
References

• Medical Statistics by Campbell et al.
• Common Statistical Methods for Clinical Research
  by Walker