Please wait while the transcript is being prepared...
0:00
In this talk, we turn
our attention to P values
in clinical research,
including what they represent
and how to interpret them.
We will discuss common
misconceptions,
the distinction
between statistical
and clinical significance
and the limitations of
using P values in research.
The lecture will also examine
the role of P values in
regulatory decision making and
emphasize the importance of
considering study design,
effect size, and
clinical context when
evaluating evidence.
P values are central to
statistical reasoning
in clinical research.
Hypothesis testing is used in
medical studies to determine
whether observed
outcomes are due to
chance or indicate
a real effect.
The P value, often reported in
scientific literature
is crucial for this.
In this lecture,
we'll explore what
a P value is, how
to interpret it,
common misconceptions,
its clinical limitations,
and its role in regulation.
In hypothesis testing,
clinical research typically sets
a null hypothesis H zero,
such as there is no
difference between
treatments or the new drug
is not more effective
than placebo.
After collecting data,
statistical analysis
determines if
the results are compatible
with this hypothesis.
The P value is the
probability under
the null hypothesis of
getting results as
extreme as observed.
It does not show
the chances that
the null or alternative
hypothesis is true.
A threshold like 0.05
often indicates a
statistical significance,
but this does not prove
the null hypothesis false.
