Descriptive Study design

Ecological and longitudinal Study design

Presentation outcome
After presentation, the audiences will be able to
Identify ecological study design
Determine longitudinal study design
Compare cross sectional and lontitudinal study design
Ecological Study design
• An ecological study is an observational study defined by the level at
which data are analyzed, namely at the population or group level,
rather than individual level.
• Ecological studies are often used to measure prevalence and incidence
of disease, particularly when disease is rare.
Ecological Study design
• Ecological study as defined by Porta: a study in which the
units of analysis are populations or groups of people rather
than individuals
• An Ecologic or Aggregate study focuses on the comparison
of groups rather than individuals
Ecological Study design
• Ecologic studies have been conducted by social scientists for more
than a century and have been used extensively by epidemiologists in
many research areas.
Ecological Study design
•  A study in which at least one variable, either an exposure or the
outcome, is measured at the group (not individual) level.
• Examples of group-level measures include the incidence rate of cancer
among a specific population, the mean level of blood pressure of
patients seen at a clinic, the average sunlight exposure at specific
geographic location on the earth, or even a preventive service included
in a health insurance plan.
• The occurrence of disease is compared between groups that have
different levels of an exposure, which affords this study design to have
at least one comparision group.
Examples of ecological studies:

• In this study, researchers wanted to study the relationship between

socioeconomic status (SES) and exposure to fast food outlets. They
gathered neighborhood level data about SES and fast-food density to
examine whether living in a low-SES area was associated with higher
exposure to fast food restaurants. Here, no individual level data was
collected; the researchers were interested in overall trends and how
exposure to fast food could pose as a greater risk for obesity in lower-
income neighborhoods. 
• Reidpath, D. D., Burns, C., Garrard, J., Mahoney, M., & Townsend, M. (2002). An
ecological study of the relationship between social and environmental determinants of
obesity. Health & Place,8(2):141-145. http://dx.doi.org/10.1016/S1353-8292(01)00028-4
Examples of ecological studies:
Examples of studies where this approach has been taken include:
• Studies of oral contraceptive sales and CVD in women (Valerie beral),
• incidence of endometrial cancer and prescription data for replacement
estrogens, and
• Motor vehicular fatalities and occupant restraint legislation or
enforcement.
Why carry out an ecological study?
• The purpose of the study is to monitor population health so that public
health strategies may be developed and directed;
• The purpose of the study is to make large scale comparisons, eg,
comparisons between countries;
• The purpose of the study is to study the relationship between
population-level exposure to risk factors and disease, or in order to look
at the contextual effect of risk factors on the population;
Why carry out an ecological study?
• Measurements at individual level are not available, eg. confidentiality
might require that individuals are anonymized by aggregation of data to
small area level; or
• The disease under investigation is rare, requiring aggregation of data
for any analysis to be carried out.
Types of ecological study
• Disease rates and exposures are measured in each of a series of
populations and their relation is examined. Often the information
about disease and exposure is abstracted from published statistics and
therefore does not require expensive or time consuming data
collection.   The populations compared may be defined in various
ways.
Geographical comparisons

• This type of study compares one geography with another by assessing

the health of the population of each.
• Exposures for geographies may also be measured and included in
analysis as well as other potential confounding variables such as
demographic and socioeconomic information.
Time trends

• A population is monitored to assess changes in disease over time.

Again, confounding factors are often included in analysis.
• Many diseases show remarkable fluctuations in incidence over time.
Rates of acute infection can vary appreciably over a few days, but
epidemics of chronic disorders such as lung cancer and coronary heart
disease evolve over decades.
Migration
• Data of migrant populations are collected and analyzed. The unit of
interest is neither time nor place, but population type.
• The study of migrant populations offers a way of discriminating
genetic from environmental causes of geographical variation in
disease, and may also indicate the age at which an environmental
cause exerts its effect.
 Causal inferences from ecological studies

Causal inferences from ecological studies can be made at three different

levels.
1. Biological
2. Ecological
3. Contextual
Biological causation
• Biological. Causation is only through a biological pathway.
• Among unvaccinated persons, low-income people have increased risk
of Hepatitis B because having a low-income increases a person's
stress which increases a person's risk for Hepatitis B.
Ecological causation
• Ecological. Causation is only through a group characteristic.
• Among unvaccinated persons, people living in a low-income
community have increased risk for Hepatitis B infection because low-
income communities have high levels of exposure to Hepatitis B.
Contextual causation
• Contextual. Causation is through both biologic and group
characteristics.
• Among unvaccinated persons, both high-income and low-income
people who live in a low-income community have increased risk for
Hepatitis B infection because of increased stress and increased
exposure.
 Types of ecological variables
• There are three types of ecological variables:
a) Aggregate variables
b) Environmental variables
c) Global variables (measure exposure)
Aggregate variables

• A summary or composite measure derived from values collected from

individuals. Examples would be the mean blood pressure or the rate of disease.
• In these cases, blood pressure is recorded for each individual in the study but
the data are collapsed to a mean summary meausure for all people in the study.
• Similarly, only individuals get a cancer, but the rate of cancer is a summary
measure for all the individuals in that population. Aggregate variables can
measure exposure (e.g., mean blood pressure) or outcome (e.g., rate of
disease) variables. One limitation with aggregate measures is that there is
variation within the population - not all the individuals in the population have
the average blood pressure.
Environmental variables
• A measure of the physical characteristics of the environment in which
people reside, work, recreate or attend school.
• For example, we might hypothesize that rainfall is a risk for a fungal
disease or the content of minerals in drinking water are protective
against a certain disease. Therefore, environmental variables would be
the mean rainfall in a geographic area or the mean level of minerals in
drinking water.
• Environmental variables measure exposure, not outcomes. One
limitation of an environmental variable is that there is variation in
exposure levels for individuals in the population.
Global Variables (Measure Exposure)
• A measure of the attributes of groups, organizations, or places for
which there is no analogue at the individual level.
• For example, the procedures or treatments that are covered in a health
insurance plan might affect the rate of disease or adverse health
outcome.
• Additionally, population density would be another global variable
because crowding might be an important exposure. There is no
individual population density! Global variables are used to measure
exposures, not outcomes.
Analysis of Ecologic Studies

• Analytic models in ecologic studies are of different forms:

Completely Ecologic: all variables (outcome, exposure and
covariates) are ecological.
Partially Ecologic: some, but not all, variables are ecological.
Multilevel: analyses may simultaneously include individual and
ecological variables on the same construct (e.g., income). This could
be called multilevel modeling, hierarchical regression, or a mixed
effects modeling.
Hypothetical example of ecological study
Conclusion of hypothetical figure
• States with high prevalence of obesity tends to have higher prevalence
of depression.
• Does this imply
a) Obesity causes depression in individual?
b) Depression causes obesity in individuals?
Ecological fallacy
• Associations on population level may not reflect associations on
individual levels.
• Example: Don’t know whether individuals who are obese tend also to
be depressed.
• Ecological Fallacy: Incorrect assuming that an association on a
population level reflects an association on an individual level.
 Ecological study for obesity and depression
in three different town
Town A
Depressed
Prevelance of obesity: 4/10=0.4
   
Prevelance of depression:
Obesity  Yes  No Total 4/10=0.4

Yes  1?? 3 ?? 4 

No  3?? 3 ???  6 At the individual level

Total  4  6  10
Odd ratio=1/3/3/3= 0.33
 Ecological study for obesity and depression
in three different town
Town B
 
Depressed
 
Prevelance rate of obesity=
5/10=0.5
Obesity  Yes No  Total
Prevalance rate of depression=
Yes  2  3 5  5/10=0.5

No  3 2   5
At the indivial level
Total  5  5  10 Odd ratio= 2/3/3/2=0.44
 Ecological study for obesity and depression
in three different town
Town C
Depressed
    Prevelance rate of obesity=
6/10= 0.6
Obesity  Yes No   Total
Prevelance rate of depression=
Yes  3 3  6  6/10=0.6

No  3 1   4
At the individual level
Total  6  4  10 Odd ratio=3/3/3/1=0.33
Interpretation
• At the population level; there is positive association between obesity
and depression which means the more obese state was the more
depressed state was.
• At the individual level; it is opposite association at the population
level. Which means there is no association between obesity and
depression (the odd ratio is less than one)
• This is ecological fallacy; that association we see on population level
is not necessarily imply the same association on individual levels
Longitudinal study
• Longitudinal studies employ continuous or repeated measures to
follow particular individuals over prolonged periods of time—often
years or decades.
• They are generally observational in nature, with quantitative and/or
qualitative data being collected on any combination of exposures and
outcomes, without any external influenced being applied
• Observations are repeated in the same population over a prolonged
period of time by means of follow up examinations.
Longitudinal study
• This study type is particularly useful for evaluating the relationship
between risk factors and the development of disease, and the outcomes
of treatments over different lengths of time.
• Similarly, because data is collected for given individuals within a
predefined group, appropriate statistical testing may be employed to
analyse change over time for the group as a whole, or for particular
individuals
• In a longitudinal study subjects are followed over time with
continuous or repeated monitoring of risk factors or health outcomes,
or both.
Longitudinal study
• Some authors like victor j. schoenbach 1999 (2) used the term “ follow
up” study designs:
• In a follow-up study, people without the disease are followed up to see
who develops it, and disease incidence in persons with a characteristic
is compared with incidence in persons without the characteristic.
Longitudinal study
• If the population followed is a defined group of people (a "cohort"),
then the study is referred to as a cohort study. alternatively, the
population under study may be dynamic (e.g., the population of a
geographical region).
• In hospital based longitudinal studies: patients with a specific disease
were monitored regularly through follow up examinations to generate
information about the progress and prognosis of their disease.
Example of longitudinal study
• A researcher planned to study the ischaemic cardiac changes
complicating diabetes mellitus. The researcher identified newly
diagnosed diabetic patients (150) in 5 hospitals and followed them for
two years. The follow up has been made through E.C.G. examination
every 3 months. In such design, the researcher can measure the
incidence of ischaemic cardiac changes among the diabetic patients
and as well the natural history of such complications can be
determined.
Longitudinal vs cross sectional study
• In contrast, cross-sectional analysis is another study type that may
analyze multiple variables at a given instance, but provides no
information with regards to the influence of time on the variables
measured—being static by its very nature.
• It is thus generally less valid for examining cause and-effect
relationships. Nonetheless, cross-sectional studies require less time to
be set up, and may be considered for preliminary evaluations of
association prior to embarking on cumbersome longitudinal-type
studies.
Longitudinal study designs
• Longitudinal research may take numerous different forms. They are
generally observational, however, may also be experimental. Some of
these are briefly discussed below:
(I) Repeated cross-sectional studies where study participants are largely
or entirely different on each sampling occasion;
(II) Retrospective studies are designed after at least some participants
have already experienced events that are of relevance; with data for
potential exposures in the identified cohort being collected and
examined retrospectively.
Longitudinal study designs
(III) Prospective studies where the same participants are followed over a
period of time. These may include:
a) Cohort panels wherein some or all individuals in a defined
population with similar exposures or outcomes are considered over
time;
b) Representative panels where data is regularly collected for a random
sample of a population;
c) Linked panels wherein data collected for other purposes is tapped
and linked to form individual-specific datasets.
Advantages
• Longitudinal cohort studies, particularly when conducted
prospectively in their pure form, offer numerous benefits. These
include:
(I) The ability to identify and relate events to particular exposures, and
to further define these exposures with regards to presence, timing
and chronicity;
(II) Establishing sequence of events;
(III)Following change over time in particular individuals within the
cohort;
Advantages
(IV) Excluding recall bias in participants, by collecting data
prospectively and prior to knowledge of a possible subsequent event
occurring, and;
(V) Ability to correct for the “cohort effect”—that is allowing for
analysis of the individual time components of cohort (range of birth
dates), period (current time), and age (at point of measurement)— and
to account for the impact of each individually.
Disadvantage
1. Attrition
2. Time consuming
3. Costly
References
• https://online.stat.psu.edu/stat507/book/export/html/641
• ECOLOGIC STUDIES IN EPIDEMIOLOGY: Concepts, Principles, and
Methods Annu. Rev. Public Health 1995. 16:611 Copyright e 1995 by Annual
Reviews b,c. All rights reserved.
• Kate Ann Levin. Study Design VI - Ecological Studies, Evidence-Based
Dentistry (2003) 7, 60-61. doi:10.1038/sj.ebd.6400454
• Caruana EJ, Roman M, HernándezSánchez J, Solli P. Longitudinal studies. J
Thorac Dis 2015;7(11):E537-E540. doi: 10.3978/j.issn.2072-1439.2015.10.63
• Nancy R. Cook, DESIGN AND ANALYSIS METHODS FOR
LONGITUDINAL RESEARCH, Ann. Rev. Public Health. 1983. 4:1-23
Copyright © 1983 by Annual Reviews Inc. All rights reserved