Biomedical Engineering Reference
In-Depth Information
value of 0.1 for the hazard. But is this the true value? How confident are we of
the value? Does this matter for a risk assessment?
For this, we need to calculate a confidence interval around the occurrence rate
determined for the potential hazard. For most cases, looking for a 95% confidence
interval is perfectly acceptable. This is shown as
95% CI
=
P
±
1.96
s
p
where
=
S
p
standard error of the estimate
=
P
occurrence rate sample probability
1.96
=
normal Z score for 95% confidence
So
95% CI
=
1
±
1.96
s
p
To calculate
S
p
†
, we use the following formula:
P (
1
−
P )
N
S
p
=
where
P
=
the occurrence rate sample probability
N
=
the number of samples taken
In this case, we know:
0.1
N
=
400
P
=
So,
0.1
(
0.9
)
400
S
p
=
=
0.015
Now
95% CI
=
0.1
+
1.96
s
p
=
0.1
±
1.96
×
0.015
95% CI
=
0.1
±
0.0294
So, we are 95% confident that the true occurrence rate is between
0.071 and 0.129
or
7.1% and 12.9%
†
S
P
gives us a standard error based upon the sample size,
N
,used.
Search WWH ::
Custom Search