Data Dictionary
for Datasets of HW exercises from ActivEpi Companion Textbook (2nd Edition, 2013)
By Kevin M. Sullivan & Minn M. Soe
Simple analyses
Lesson 12 Activity 01: Exposure Odds Ratio in a Case-Control Study
The data are from a case-control study designed to investigate the theory that a certain study factor is a determinant of some rare disease. A representative group of incident cases of the disease arising in a given population over a five-year period was identified. These cases were then compared to a random sample of an equal number of noncases from the same population. (Refer to ActivEpi Companion Textbook, Lesson 12, Homework-ACE-1 on page 374)
File Name: L12A01 Number of records: 100
Variable |
Label |
Values |
Description |
Freq |
Defines whether a person has a rare disease (case) or not (control). |
CASECONT |
case control |
Presence of rare disease Do not have rare disease |
50 50 |
Defines whether a person has exposed to a study factor or not. |
EXPOSED |
1. yes 2. no |
Exposed not exposed |
45 55 |
Lesson 12 Activity 03: Test of Hypothesis
Helicobacter pylori (HP) is a bacterium that infects the cells that line the stomach, causing acute and chronic inflammation. The organism is considered a causal factor in peptic ulcer disease and has been linked epidemiologically to the development of gastric adenocarcinoma. A group of investigators was interested in assessing the relationship between alcohol consumption and HP infection. They identified 300 subjects whose blood contained antibodies to HP, 63 of whom consumed alcohol. Of 267 subjects who were antibody-negative for HP, 91 consumed alcohol. (Refer to ActivEpi Companion Textbook, Lesson 12, Homework-ACE-3 on page 375)
File Name: L12A03 Number of records: 567
Variable |
Label |
Values |
Description |
Freq |
Defines whether a person has antibody to HP (case) or not (control). |
HP_AB |
case control |
Antibody positive Antibody negative |
300 267 |
Defines whether a person has been drinking alcohol (exposure) or not. |
ALCOHOL |
1. yes 2. no |
drink alcohol do not drink alcohol |
154 413 |
Lesson 12 Activity 04: Fisher’s Exact Test
The data come from a case-control study relating an exposure to a disease. (Refer to ActivEpi Companion Textbook, Lesson 12, Homework-ACE-4 on page 375)
File Name: L12A04 Number of records: 16
Variable |
Label |
Values |
Description |
Freq |
Defines whether a person has the disease (case) or not (control). |
CASE_CON |
case control |
Disease Do not have disease |
11 5 |
Defines whether a person has the exposure related to the disease or not. |
EXPOSED |
1. yes 2. no |
Exposed Not exposed |
8 8 |
Lesson 12 Activity 07: Sample Size: Case-control study.
The data are obtained from the Tricontinental Seroconverter Study for a case-control analysis of the potential association between HIV status and substance use. Recent HIV seroconverters were compared to subjects who tested negative for HIV; all subjects were asked about their substance use in the year prior to study enrollment. (Refer to ActivEpi Companion Textbook, Lesson 12, Homework-ACE-7 on page 376)
File Name: L12A07 Number of records: 690
Variable |
Label |
Values |
Description |
Freq |
A variable that defines whether a person has HIV infection (case) or not (control). |
HIV |
case control |
Presence of HIV No HIV infection |
345 345 |
A variable that defines whether a person has used amphetamine (exposure) or not. |
AMPHATAM |
1. yes 2. no |
use amphetamine do not use amphetamine |
113 577 |
Stratified Analysis
Lesson 14 Activity 01: Stratified Analysis
The data comes from a case-control study in order to assess the relationship between alcohol consumption and oral cancer, after stratifying on smoking status of study participants depending whether they are current, former or never a smoker. (Refer to ActivEpi Companion Textbook, Lesson 14, Homework-ACE-1 on page 462)
File Name: L14A01 Number of records: 506
Variable |
Label |
Values |
Description |
Freq |
Defines whether a person has oral cancer (case) or not (control). |
CANCER |
case control |
presence of oral cancer no cancer |
313 193 |
Defines whether a person has been drinking alcohol (exposure) or not. |
ALCOHOL |
1. yes 2. no |
drink alcohol do not drink alcohol |
476 30 |
Categorizes the smoking status of a person. |
SMOKE |
Current Former Never |
current smoker former smoker has never smoked |
56 155 295 |
Lesson 14 Activity 02: Stratified Analysis
The data come from a case-control study among ‘never smokers’, in order to assess the relationship between alcohol consumption and oral cancer, after stratifying on age of study participants. (Refer to ActivEpi Companion Textbook, Lesson 14, Homework-ACE-2 on page 463)
File Name: L14A02 Number of records: 607
Variable |
Label |
Values |
Description |
Freq |
Defines whether a person has oral cancer (case) or not (control). |
CASE_CON |
case control |
presence of oral cancer no cancer |
74 533 |
Defines whether a person has been drinking alcohol (exposure) or not. |
ALCOHOL |
1. yes 2. no |
drink alcohol do not drink alcohol |
117 490 |
Categorizes the age of a person. |
AGE_CATE |
<50 50-59 60+ |
less than 50 years old 50-59 years old 60 and above |
360 126 121 |
Lesson 14 Activity 03: Stratified Analysis
A case-control study was conducted to assess whether paternal radiation exposure on the job was associated with birth defects, after stratifying on maternal age, a potential confounder. (Refer to ActivEpi Companion Textbook, Lesson 14, Homework-ACE-3 on page 463)
File Name: L14A03 Number of records: 331
Variable |
Label |
Values |
Description |
Freq |
Defines whether a person has a birth defect (case) or not (control). |
CASE_CON |
case control |
Presence of birth defect No birth defect |
153 178 |
Defines whether a person has been exposed to radiation or not. |
RADIATIO |
1. yes 2. no |
exposed to radiation not exposed to radiation |
63 268 |
Categorizes the age of a mother. |
MAT_AGE |
≤35 >35 |
less than 36 years old 36 and above |
208 123 |
Lesson 14 Activity 04: Stratified Analysis
The following dataset is from a retrospective cohort study where the relationship between paternal occupational lead exposure and low birth weight was examined after maternal age at child’s birth was stratified. Low birth weight (LBW) was defined as a birth weight of <2500 grams. (Refer to ActivEpi Companion Textbook, Lesson 14, Homework-ACE-4 on page 464)
File Name: L14A04 Number of records:1185
Variable |
Label |
Values |
Description |
Freq |
Defines whether a child has LBW or not. |
CASE_CON |
case control |
<2500 gram ≥2500 gram |
191 994 |
Defines whether a person has been exposed to lead or not. |
BLD_LEAD |
1. yes 2. no |
exposed to lead never exposed to lead |
539 646 |
Categorizes the age of a mother at child’s birth. |
MAT_AGE |
<20 ≥20 |
less than 20 years old 20 and above |
458 727 |
Lesson 14 Activity 07: Stratified Analysis
The following dataset describes a case-control study conducted to assess the potential relationship between alcohol consumption and bladder cancer after stratifying on 3 race categories, White, Black and Asian. (Refer to ActivEpi Companion Textbook, Lesson 14, Homework-ACE-7 on page 465)
File Name: L14A07 Number of records:1018
Variable |
Label |
Values |
Description |
Freq |
Defines whether a person has bladder cancer or not. |
CANCER |
case control |
presence of bladder cancer no bladder cancer |
361 657 |
Defines whether a person has been drinking alcohol (exposure) or not. |
ALCOHOL |
1. yes 2. no |
drink alcohol do not drink alcohol |
530 488 |
A person’s race. |
RACE |
White Black Asian |
- |
324 373 321 |