Professional Documents
Culture Documents
Two reasons :
random error
systematic error
B Vs A : random error
D Vs C: systematic error
The shots in both A and B are centered around the middle, but
in A the shots are less scattered and have less variability.
In C and D, the scatter is similar, but in target D the cluster of
shots is off center.
It is important to consider the
accuracy and precision of any
measurements made in the
medical setting.
Table: levels of variability
Levels Features
Individual Individual variability
Measurement variability
Manner of sampling
Size of sample
Sample Measurement variability
Variability within individual
Biological changes:
Occur on a minute-to-minute basis.
e.g., heart rate
Follow a regular diurnal pattern.
e.g., body temperature
Progress with normal development
e.g., height or weight
Variability within individual
Measurement:
sampling variability
Examples:
Two reasons :
random error
systematic error
Validity
Two reasons :
random error
systematic error
• Random error
Bias • Systematic error (bias)
It is important to discern whether the suspected bias is likely to make an association appear stronger or weaker than it really
is.
Bias Overestimate(stronger)
Study results
True value
Bias
Underestimate(weaker)
the selection bias leads to apparent
association.
The apparent association does not
exist in fact.
The cause: the way we select the
cases and the controls, the way we
select the exposed and nonexposed
individuals is not correct.
Selection bias
we could not recruite all the target
population, we can only select a sample.
If the sample could not represent the target
population, because of the significant differ
ences between the subjects chosen in the s
tudy and those not been chosen in the stud
y.
selection bias may exist:
when we use the volunteers as the sample;
when we use convenient sample;
or non-response;
or loss to follow up.
selection bias exist in descriptive study:
Exposure: cholesterol
Disease: coronary disease
2. Prevalence-incidence bias ( Neyman bias )
Prevalent (existing)cases: Have been diagnosed for
some time or been ill for some months or years;
in the case-control study or cross-sectional study
Newly diagnosed cases: just be diagnosed.
in the cohort study
1. Recall bias
common in the case-control study
the cases may try their best to recall their
exposure in the past, they are serious.
However, the controls may be not serious
about the investigation, and could not
remember their exposure in the past.
Example
Slewart found that in the study of risk factors of infant l
eukaemia 白血病 , patients’ mother had a higher
percentage of getting X-ray during pregnancy and befor
e pregnancy than those mothers in the control group.
Observed Association
{ }
Observed Association
Smoking
Risk of Risk of
Pancreatic Pancreatic
Cancer Cancer
F (age)
Control confounding in the analysis:
stratification
Case Control
OC Use Yes 39 24
No 114 154
Crude OR = 2.2
Stratified Data (Two 2 x 2 Tables)
OC Yes 21 17 OC Yes 18 7
Use Use
No 26 59 No 88 95
Stratum-specific Stratum-specific
OR = 2.8 OR = 2.8
After excluding the suspicious confounding fac
tor, the relation value is aRR(f) or aOR(f), or a
djusted RR/OR.
Using Mantel-Haenszel method