Difference between revisions of "Measures of strength of association"

From WikiVet English
Jump to navigation Jump to search
Line 7: Line 7:
 
Although correlation coefficients are commonly used in statistical studies, epidemiological investigations often deal with binary exposures and outcomes (such as presence or absence of a proposed risk factor for disease, and presence or absence of disease itself). Therefore, '''ratio measures''' such as the '''prevalence ratio''', the '''risk ratio''', the '''rate ratio''' and the '''odds ratio''' are commonly used as measures of strength of association in epidemiological studies.<br>
 
Although correlation coefficients are commonly used in statistical studies, epidemiological investigations often deal with binary exposures and outcomes (such as presence or absence of a proposed risk factor for disease, and presence or absence of disease itself). Therefore, '''ratio measures''' such as the '''prevalence ratio''', the '''risk ratio''', the '''rate ratio''' and the '''odds ratio''' are commonly used as measures of strength of association in epidemiological studies.<br>
  
Understanding how these measures are calculated is best approached using a contingency table (also known as a cross tabulation), as shown here. In the columns, the individuals are divided into exposed and unexposed, whilst in the rows, individuals are divided into those who are diseased and those who are not diseased.  
+
Understanding how these measures are calculated is best approached using a contingency table (also known as a cross tabulation), as shown below. In the columns, the individuals are divided into exposed and unexposed, whilst in the rows, individuals are divided into those who are diseased and those who are not diseased. Therefore, cell 'm<sub>1</sub>' represents all diseased individuals, cell 'n<sub>1</sub>' represents all exposed individuals, and cell 'a<sub>1</sub>' represents exposed individuals who are also diseased.
 +
 
 
{| class="wikitable"
 
{| class="wikitable"
 
|-
 
|-
 
| Disease status || Exposed || Unexposed || Total
 
| Disease status || Exposed || Unexposed || Total
 
|-
 
|-
| Diseased || a<sub>1</sub> || a<sub>0</sub> || Example
+
| Diseased || a<sub>1</sub> || a<sub>0</sub> || m<sub>1</sub>
 
|-
 
|-
| Non-diseased || b<sub>1</sub> || b<sub>0</sub> || Example
+
| Non-diseased || b<sub>1</sub> || b<sub>0</sub> || m<sub>0</sub>
 
|-
 
|-
 
| Total || n<sub>1</sub> || n<sub>0</sub> || n
 
| Total || n<sub>1</sub> || n<sub>0</sub> || n
 
|}
 
|}
  
 +
The measures of disease frequency which could be extracted from this table will depend on the [[Study design|study design]] used, which will be [[Analytic studies#Study design|analytic]] in nature, as data regarding exposure has been collected.<br>
 +
 +
In the case of a [[Cross sectional studies#Study design|cross sectional study]], the '''[[Prevalence#Measures of disease frequency|prevalence]]''' can be estimated amongst exposed individuals as (a<sub>1</sub>/n<sub>1</sub>), and amongst unexposed individuals as (a<sub>0</sub>/n<sub>0</sub>).<br>
 +
 +
In the case of a [[Cohort studies#Study design|cohort study]], the '''[[Incidence risk#Measures of disease frequency|incidence risk]]''' can be estimated amongst exposed individuals as (a<sub>1</sub>/n<sub>1</sub>), and amongst unexposed individuals as (a<sub>0</sub>/n<sub>0</sub>). Alternatively, the [[Incidence rate#Measures of disease frequency|incidence rate]] can be estimated as (a<sub>1</sub>/[total number of animal-time units in exposed group]) amongst exposed animals and (a<sub>1</sub>/[total number of animal-time units in unexposed group]) amongst unexposed animals.
  
  

Revision as of 16:41, 4 May 2011

Analytic studies are conducted in an attempt to identify whether the disease experience in a population differs between groups of animals within this population (defined by exposure to 'risk factors' of interest), in the hope that some indication of a causal association can be achieved. Therefore, methods are required in order to quantify any 'evidence' in support of a possible association. Epidemiologists commonly measure this using measures of strength of association and through the use of null hypothesis tests. It is important to use both of these measures whenever interpreting the results of an analytic study, as they measure different things. Measures of strength of association are an indication of the magnitude of the association, whereas the hypothesis test results give an indication of the probability of seeing the data obtained if there was no association between the exposure and outcome in the source population.

Correlation coefficients

Correlation coefficients are used when comparing two quantitative variables, and are based upon the covariance between these variables amongst the individuals in the study population. The covariance can be viewed as how the two variables of interest differ in individuals in relation to their mean values in the whole population, but put more simply, is a measure of how two different variables change in relation to each other. As the magnitude of this variable will depend upon the magnitudes of the variables in question, this value is 'standardised' in order to give a correlation coefficient, which lies between -1 (indicating a perfect negative correlation) and +1 (indicating a perfect positive correlation), with a coefficient of 0 indicating no correlation. Therefore, correlation coefficients measure how closely associated the two variables of interest are to each other.

Ratio measures

Although correlation coefficients are commonly used in statistical studies, epidemiological investigations often deal with binary exposures and outcomes (such as presence or absence of a proposed risk factor for disease, and presence or absence of disease itself). Therefore, ratio measures such as the prevalence ratio, the risk ratio, the rate ratio and the odds ratio are commonly used as measures of strength of association in epidemiological studies.

Understanding how these measures are calculated is best approached using a contingency table (also known as a cross tabulation), as shown below. In the columns, the individuals are divided into exposed and unexposed, whilst in the rows, individuals are divided into those who are diseased and those who are not diseased. Therefore, cell 'm1' represents all diseased individuals, cell 'n1' represents all exposed individuals, and cell 'a1' represents exposed individuals who are also diseased.

Disease status Exposed Unexposed Total
Diseased a1 a0 m1
Non-diseased b1 b0 m0
Total n1 n0 n

The measures of disease frequency which could be extracted from this table will depend on the study design used, which will be analytic in nature, as data regarding exposure has been collected.

In the case of a cross sectional study, the prevalence can be estimated amongst exposed individuals as (a1/n1), and amongst unexposed individuals as (a0/n0).

In the case of a cohort study, the incidence risk can be estimated amongst exposed individuals as (a1/n1), and amongst unexposed individuals as (a0/n0). Alternatively, the incidence rate can be estimated as (a1/[total number of animal-time units in exposed group]) amongst exposed animals and (a1/[total number of animal-time units in unexposed group]) amongst unexposed animals.