1 Ecologic studies JF Boivin S:\BOIVIN\695\Winter 2006\Ecologic studies.ppt (December 5, 2015)

Post on 13-Dec-2015

220 views 3 download

Tags:

transcript

1

Ecologic studies

JF Boivin

S:\BOIVIN\695\Winter 2006\Ecologic studies.ppt (April 18, 2023)

2

Outline

1. Examples

2. Definition

3. Ecologic fallacy

• Definition

• Valid ecologic study

• Rate difference varies

• Reference rate varies

4. Ecologic confounder

5. Types of ecologic exposures

6. Rationale for ecologic studies

3

Percentage of children receiving measles-mumps-rubella immunization in second year of life and caseload of children with autism, by year of birth, California

(Dales et al., JAMA 2001)

4

5

(Goodman DC, et al. NEJM 2002)

6

Outline

1. Examples

2. Definition

3. Ecologic fallacy

• Definition

• Valid ecologic study

• Rate difference varies

• Reference rate varies

4. Ecologic confounder

5. Types of ecologic exposures

6. Rationale for ecologic studies

7

Ecologic study

A study in which the units of analysis are populations or groups of people, rather than individuals.

(Last. 2001)

8

Structure of an ecologic study: Counts

E+ E-

M1+

M1-

N1-N1+

D+

D-

?

?

?

?

Group 1

E+ E-

M2+

M2-

N2-N2+

D+

D-

?

?

?

?

Group 2

9

Person-years

E+ E-

M1+

PY1T

D+

PY

?

PY1+

?

PY1-

Group 1

E+ E-

M2+

PY2T

D+

PY

?

PY2+

?

PY2-

Group 2

10

Durkheim’s study

Protestant Other

10

1,000,000

Suicide

PY

?

300,000

?

700,000

Group 1 (provinces with protestant minority)

Protestant Other

20

1,000,000

Suicide

PY

?

800,000

?

200,000

Group 2 (provinces with protestant majority)

11

Actual study

? ?

Group 1

Group 2

? ?

? ?

Group 3

? ?

Group 4

12

Outline

1. Examples

2. Definition

3. Ecologic fallacy

• Definition

• Valid ecologic study

• Rate difference varies

• Reference rate varies across

4. Ecologic confounder

5. Types of ecologic exposures

6. Rationale for ecologic studies

13

Ecologic fallacy

“… the mistaken assumption that a statistical association observed between two ecologic (group-level) variables… is equal to the association between the corresponding variables at the individual level…”

(Encyclopedia of epidemiologic methods. 2000)

14

Ecologic fallacy

“…the ecologic fallacy is due to cross-level bias in estimating the biologic effect of an exposure on disease risk on the basis of ecologic data… In an ecologic analysis involving simple linear regression, cross-level bias arises when the disease rate in the unexposed (reference) population is correlated with exposure prevalence across groups or when the difference in rates between exposed and unexposed populations (biologic effect) varies across groups.”

(Encyclopedia of epidemiologic methods. 2000)

15

No ecologic bias

E+ E-

32

20,000

D+

PY

24

12,000

8

8,000

Group 2 (Ontario)

IE = 200/100,000

Io = 100/100,000

RD = 100/100,000

RR = 2

Group rate = 32/20,000 =160/100,000

% exposure = 12,000/20,000=60%

Adapted from Rothman-Greenland Table 23-2

E+ E-

28

20,000

D+

PY

16

8,000

12

12,000

Group 1 (Québec)

IE = 200/100,000

Io = 100/100,000

RD

RR

= 100/100,000

= 2

Group rate = 28/20,000 =140/100,000

% exposure = 8,000/20,000 =40%

16

No ecologic bias

110

120

140

130

150

160

170

180

190

200

100908070605040302010

RA

TE

(pe

r 10

0,00

0)

% EXPOSURE

IRR = = 2=IE

Io 100/100,000

200/100,000

17

Ecologic bias(rate difference varies across groups)

E+ E-

27

20,000

D+

PY

20

13,000

7

7,000

Group 2 (Ontario)

IE = 154/100,000

Io = 100/100,000

RD = 54/100,000

RR = 1.54

Group rate = 27/20,000 =135/100,000

% exposure = 13,000/20,000=65%

E+ E-

33

20,000

D+

PY

20

7,000

13

13,000

Group 1 (Québec)

IE = 286/100,000

Io = 100/100,000

RD = 186/100,000

RR = 2.86

Group rate = 33/20,000 =165/100,000

% exposure = 7,000/20,000 =35%

18

Ecologic bias

110

120

140

130

150

160

170

180

190

200

100908070605040302010

RA

TE

(pe

r 10

0,00

0)

% EXPOSURE

IRR = = 0.5=IE

Io 200/100,000

100/100,000

19

Ecologic bias(reference rate varies across groups)

E+ E-

46

20,000

D+

PY

40

16,000

6

4,000

Group 2 (Ontario)

IE = 250/100,000

Io = 150/100,000

RD = 100/100,000

RR = 1.67

Group rate = 46/20,000 =230/100,000

% exposure = 16,000/20,000=80%

E+ E-

28

20,000

D+

PY

16

8,000

12

12,000

Group 1 (Québec)

IE = 200/100,000

Io = 100/100,000

RD = 100/100,000

RR = 2

Group rate = 28/20,000 =140/100,000

% exposure = 8,000/20,000 =40%

20

Ecologic bias

0

100

150

200

250

100908070605040302010

RA

TE

(pe

r 10

0,00

0)

% EXPOSURE

IRR = = 5.5=IE

Io 50/100,000

275/100,000

21

Outline

1. Examples

2. Definition

3. Ecologic fallacy

• Definition

• Valid ecologic study

• Rate difference varies

• Reference rate varies

4. Ecologic confounder

5. Types of ecologic exposures

6. Rationale for ecologic studies

22

Ecologic confounder24-Mar-03

Ecologic studies simulation #2 (Adapted from Encyclopedia of Epidemiologic Methods, Table 3, Page 326)Age is not an individual level confounder; age creates ecological level bias that can be corrected by appropriate analysis

OLD

Ie= 600Region 1 E+ E- Total Io= 500Cases 18 60 78 RD= 100PY 3000 12000 15000 RR= 1.2

%exposure= 20 It= 520

Ie= 600Region 2 E+ E- Total Io= 500Cases 24 30 54 RD= 100PY 4000 6000 10000 RR= 1.2

%exposure= 40 It= 540

Ecologic analysis: y = a + bx Ie= 600 b= 1 Io= 500 a= 500 RD= 100

RR= 1.2

23

Ecologic confounder

YOUNG

Ie= 200Region 1 E+ E- Total Io= 100Cases 4 8 12 RD= 100PY 2000 8000 10000 RR= 2

%exposure= 20 It= 120

Ie= 200Region 2 E+ E- Total Io= 100Cases 12 9 21 RD= 100PY 6000 9000 15000 RR= 2

%exposure= 40 It= 140

Ecologic analysis: y = a + bx Ie= 200 b= 1 Io= 100 a= 100 RD= 100

RR= 2

24

Ecologic confounder

YOUNG + OLD

Ie= 440Region 1 E+ E- Total Io= 340Cases 22 68 90 RD= 100PY 5000 20000 25000 RR= 1.2941176

%exposure= 20 It= 360

Ie= 360Region 2 E+ E- Total Io= 260Cases 36 39 75 RD= 100PY 10000 15000 25000 RR= 1.3846154

%exposure= 40 It= 300

Ecologic analysis: y = a + bx Ie= 120 b= -3 Io= 420 a= 420 RD= -300

RR= 0.2857143

25

Outline

1. Examples

2. Definition

3. Ecologic fallacy

• Definition

• Valid ecologic study

• Rate difference varies

• Reference rate varies

4. Ecologic confounder

5. Types of ecologic exposures

6. Rationale for ecologic studies

26

Aggregate exposure

Attributes of individuals that are summarized at the group level

• Proportion of smokers• Median family income• Proportion of protestants • Prevalence of subjects who are immune

to measles

Scientific interest may lie in:• Individual effect• Contextual effect

27

Attributes of groups for which no distinct analog exists at the individual level

• Population density• Law • Health-care system• Social disorganization• Income discrepancy

Everybody is exposed!

Intrinsically population-level exposure

28

29

• Neighborhood social class as aggregate of individual social classes

Can differ from study subjects’ social class

• Neighborhood social class as contextual variable

Same contextual variable for all subjects

The variable is ecological, but the study is not!

30

31

Outline

1. Examples

2. Definition

3. Ecologic fallacy

• Definition

• Valid ecologic study

• Rate difference varies across groups

• Reference rate varies across groups

4. Ecologic confounder

5. Types of ecologic exposures

6. Rationale for ecologic studies

32

1. Low cost and convenience

2. Measurement limitation of individual-level studies

3. Design limitations of individual-level studies

4. Simplicity of analysis and presentation

? Interest in ecologic effects

33

Dales L, et al. Time trends in autism and in MRR immunization coverage in California. JAMA 2001; 285:1183-1185.

Durkheim E. Suicide: a study in sociology. London: Routledge & Kegan Paul Ltd, 1966.

Gail MH, Benichou J, eds. Encyclopedia of epidemiology methods. New York: John Wiley & Sons, Ltd. 2000.

Goodman DC, et al. The relation between the availability of neonatal intensive care and neonatal mortality. NEJM 2002; 346:1538-1544.

Last JM. A dictionary of epidemiology. Fourth edition. New York: Oxford University Press. 2001.

Rothman KJ, Greenland S. Modern epidemiology. Second edition. Philadelphia: Lippincott-Raven. 1998.

References