In Class Exercise on Confounding_Answer Key

docx

School

Temple University *

*We aren’t endorsed by this school

Course

8202

Subject

Statistics

Date

Apr 3, 2024

Type

docx

Pages

Uploaded by CommodoreRhinoceros3559

In-Class Exercises - Confounding 1. Which of these variables are confounders? a. Age is a confounder – it is associated with both grey hair and stroke Age is a confounder - relationship between children and age is non-causal (having children does not increase your age) No confounders – Smoking and diet act independently; there is no relationship between smoking and diet (theoretically in this conceptual model) No confounders – Fibrinogen here is a mediator, because smoking promotes increased fibrinogen, which is then associated with CHD 2. You conduct a case-control study to examine the relationship between eating margarine and depression. You find that among the 185 patients who suffer from depression, 65 eat margarine, while 50 of the 230 controls eat margarine. Age Stroke Grey hair Fibrinogen CHD Smoking d. High cholesterol diet CHD Smoking c. Age Breast cancer # of Children b.

a. What is the crude OR? (65*180)/(50*120)=1.95 b. Among the 100 women in this group who suffer from depression, 25 eat margarine. Among the 50 female controls, 5 eat margarine. Among the 85 male cases, 40 eat margarine. Among the 180 male controls, 45 eat margarine. Build two separate 2x2 tables for each level of the confounder. c. Calculate separate ORs. What can you conclude based on the ORs? How do you interpret the results? OR = (25*45)/(5*75) = 3 OR = (40*135)/(45*45) = 2.67 The stratum-specific ORs are very similar (they don’t differ by >20%), but they differ from the crude OR. This is an example of confounding The relationship between eating margarine and depression is distorted by gender. You cannot report the crude (combined) OR because it falsely represents the risk! You need to control for gender. 3. A case-control study of the relationship between socioeconomic status (SES) and birth weight (BW) was conducted in a county hospital. All low birth weight infants born in 1970 were identified and compared to an equal number of normal birth weight infants from the same hospital. Tables give numbers of infants with normal birth weight (NBW) and low birth weight (LBW) by maternal age and maternal SES (Lo-SES or Hi-SES). Note : Maternal age (age ≤ 21) is independently associated with LBW and is also associated with socioeconomic status. First step is to check if confounder meets criteria! Maternal Age >21 LBW NBW Lo-SES 120 60 Hi-SES 40 20 >21 OR= (120*20)/(60*40)=1 Maternal Age ≤ 21 LBW NBW Depression + Depression - Eats margarine + 65 50 Eats margarine - 120 180 WOMEN Depression + Depression - Eats margarine + 25 5 Eats margarine - 75 45 MEN Depression + Depression - Eats margarine + 40 45 Eats margarine - 45 135

Lo-SES 40 80 Hi-SES 40 80 <21 OR= (40*80)/(40*80)=1 a. Construct overall 2*2 table and calculate crude OR a. Is there evidence of confounding by maternal age? OR = (160 x 100) / (80 x 140) = 1.42 There is evidence of confounding by maternal age 4. Complete the table below: Birth Weight LBW NBW Lo-SES 160 140 Hi-SES 80 100 Stratum Specific Estimates Crude RR Adjusted RR Is Race a Confounder? AA W 1.00 1.00 1.00 1.00 no 1.00 1.00 1.64 1.00 yes 2.00 1.00 1.43 1.43 No 2.00 1.00 2.44 1.67 yes

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

Note: in all demographic subgroups of the population, the incidence of cardiac arrests rises sharply with age The white population must be relatively older because once you account for age, their rate of cardiac arrests falls. This can only happen if the white population was older on average. 5. What conclusions can you draw from the crude vs adjusted RRs below? Insufficient total weight gain was associated with a lower risk of cesarean section (RR 0.78, 95% CI 0.68–0.91) and a higher risk of preterm birth (RR 1.45, 95% CI 1.00–2.11); confounded by weight gain by trimester 1. Occurrence of out-of-hospital cardiac arrest in New York City during 2002-2003 Can you draw any conclusion regarding the difference in age distribution between white and non-white residents of New York City ages 18 years and older during 2002-2003? If yes, how would you characterize the difference? If no, why not? Incidence per 10,000 person-years Population # Cardiac Arrests Crude Age-Adjusted Black 1,393,859 1,257 9.0 10.1 Hispanic 1,489,208 636 4.2 6.5 White 2,345,564 1,908 8.1 5.8 Other 829,378 253 3.0 4.8

excessive total weight gain was associated with higher risk of cesarean section (RR 1.17, 95% CI 1.04–1.33) For women with insufficient weight gain in the 2nd trimester, a lower risk of cesarean section (RR 0.82, 95% CI 0.71– 0.96) were observed. No association was found with insufficient weight gain in the final trimester. For women with excessive weight gain in the second trimester, we found a greater risk of pre-term birth (RR 1.70, 95% CI 1.08–2.70) and cesarean section (RR 1.21, 95% CI 1.03–1.44) when it occurred in the third trimester

Related Documents

Final Exam (dragged) 5.pdf

EA 3 ANSWER FORM.docx

Lab Instructions_ Data Analysis Mission Memo (Spring A 2024 Onward).pdf

bayseian.docx

Titanic Survival BUS352.pptx

WMAN 150 Homework #2.docx

Recommended textbooks for you

College Algebra

Algebra

ISBN:9781337282291

Author:Ron Larson

Publisher:Cengage Learning

Functions and Change: A Modeling Approach to Coll...

Algebra

ISBN:9781337111348

Author:Bruce Crauder, Benny Evans, Alan Noell

Publisher:Cengage Learning

Big Ideas Math A Bridge To Success Algebra 1: Stu...

Algebra

ISBN:9781680331141

Author:HOUGHTON MIFFLIN HARCOURT

Publisher:Houghton Mifflin Harcourt

Holt Mcdougal Larson Pre-algebra: Student Edition...

Algebra

ISBN:9780547587776

Author:HOLT MCDOUGAL

Publisher:HOLT MCDOUGAL

SEE MORE TEXTBOOKS

Recommended textbooks for you

College Algebra
Algebra
ISBN:9781337282291
Author:Ron Larson
Publisher:Cengage Learning
Functions and Change: A Modeling Approach to Coll...
Algebra
ISBN:9781337111348
Author:Bruce Crauder, Benny Evans, Alan Noell
Publisher:Cengage Learning
Big Ideas Math A Bridge To Success Algebra 1: Stu...
Algebra
ISBN:9781680331141
Author:HOUGHTON MIFFLIN HARCOURT
Publisher:Houghton Mifflin Harcourt
Holt Mcdougal Larson Pre-algebra: Student Edition...
Algebra
ISBN:9780547587776
Author:HOLT MCDOUGAL
Publisher:HOLT MCDOUGAL