Sharp JX-9400 Technical Information Seite 178

  • Herunterladen
  • Zu meinen Handbüchern hinzufügen
  • Drucken
  • Seite
    / 211
  • Inhaltsverzeichnis
  • LESEZEICHEN
  • Bewertet. / 5. Basierend auf Kundenbewertungen
Seitenansicht 177
The confidence interval [c; c] of the normal distribution is obtained by
solving the equation:
P ¼ erfðc=
ffiffi
2
p
Þð7:57Þ
for a given value of P.
If the normalized variable:
c ¼
x
ð7:58Þ
is calculated using the estimate, s, of the standard deviation (based on N þ 1
measurements) instead of the exact value, , (which is not known in practice),
then this estimate of the normalized variable:
t ¼
x
s
ð7:59Þ
has a probability density function following the Student distribution (see Figure
7.4):
fðt; NÞ¼
N þ 1
2
ffiffiffiffiffiffiffi
N
p
N
2
1 þ
t
2
N
N þ1=2
t ð7:60Þ
where the gamma function ðx=2 Þ is:
if x is even: ðx=2Þ¼ðx=2 1Þðx=2 2Þ  3 2 1
if x is odd: ðx=2Þ¼ðx=2 1Þðx=2 2 Þ  1=2
ð7:61Þ
If n is large, the Student distribution tends to the normal distribution.
The confidence interval ½T; T where T ¼ TðP;Þ of the Student distri-
bution cannot be expressed analytically. It can be found in Table 7.6 (or in
0
0.1
0.2
0.3
0.4
0.5
-3 -2 -1 0 1 2 3
0
0.2
0.4
0.6
0.8
1
x – <x>
s
-3 -2 -1 0 1 2 3
x – <x>
s
Figure 7.3 Normal (or Gaussian) distribution (left) and its pr obabillity
function (right)
Common Methods and Techniques 157
Seitenansicht 177
1 2 ... 173 174 175 176 177 178 179 180 181 182 183 ... 210 211

Kommentare zu diesen Handbüchern

Keine Kommentare