# Bauhaus-Universität Weimar

### Volltext Experimental Psychology: A Manual of Laboratory Practice, Vol. II: Quantitative Experiments, part 2: Instructor's Manual (2 (2))

Titel:
Experimental Psychology: A Manual of Laboratory Practice, Vol. II: Quantitative Experiments, part 2: Instructor's Manual
Person:
Titchener, Edward B.
PURL:
https://digitalesammlungen.uni-weimar.de/viewer/image/lit11940/447/
```270
The Metric Methods
of observation; and if every error of observation may be ex¬
pressed in terms of D, may be considered as a plus or minus or
zero difference between r1 and r2,—in brief, is the equivalent of.
some D-magnitude ; then the error curves of the r, w and u cases
may be drawn as if hD and not hx were the i for the relative
number of cases in question. Let us see what data we require
for the drawing, and what the form of the curves is.
y zu u y
We know that --|---1—=i ; and that when D=DL. Now (it
n n n n " x >
for D=o, we have to assume an equal probability of r and w, so that
The terms r and w are, in this case, wholly arbitrary ; but the
assumption is the simplest and most reasonable that can be made.
(2) For a — D, the present w-cases become r-cases, and conversely.
It follows that the relative frequency of w for a negative D obeys the
same law of distribution as the relative frequency of r for a positive D.
The curves for r and w will therefore intersect at D=o, taking symmetri¬
cal paths in opposite directions. (3) The number of u-cases may be de-
u y zv
termined by the equation _ = I — —
n it
With these data
to guide us, we may
draw the three
curves as shown in
Fig. 35. The ordi¬
nates represent the
numbers of the
special cases, whose
Fig. 35.—Curves showing the distribution of w and u *°tal number is n ;
cases as determined by Gauss’ Law of Error. From tl>e abscissas are
Külpe, Grundriss d. Psych., 1893, 73. the values of t=hD
given in Fechner’s
Fundamental Table. Ordinates are shown for D=o and D=DL.
n
0-0 D = DL
We now have no difficulty in constructing formulæ whereby
we may calculate the DL from our results with a given D. These
formulae will contain h, which is our required measure of ac¬
curacy or precision.
(1) Suppose that D is DL: the relation is evidenced at once
```

### Nutzerhinweis

Sehr geehrte Benutzer,

aufgrund der aktuellen Entwicklungen in der Webtechnologie, die im Goobi viewer verwendet wird, unterstützt die Software den von Ihnen verwendeten Browser nicht mehr.

Bitte benutzen Sie einen der folgenden Browser, um diese Seite korrekt darstellen zu können.

Vielen Dank für Ihr Verständnis.