Bauhaus-Universität Weimar

Titel:
Experimental Psychology: A Manual of Laboratory Practice, Vol. II: Quantitative Experiments, part 1: Student's Manual
Person:
Titchener, Edward B.
PURL:
https://digitalesammlungen.uni-weimar.de/viewer/image/lit16066/146/
IOO 
The Metrie Methods 
By help of this Table we may write the equations 
tx={Dx—RL)h, 
t2 = (D2—RL)h, 
t7 — (D7—RL)h 
in numerical form, as follows : 
—0.9062 = (0.5 —RL)h, 
—0.7639 = ( i. o—RL)k, 
—0.1791 = (1.5 —RL)h, 
0.2725 = (2.0 ~RL)h, 
0-595 i = (3-°—RL)h, 
0.7965 = (4.0—RL)h, 
i.2Z79 = {S.o—RL)h. 
These equations can be solved, for RL and h, by the Method of 
Least Squares. 
So far, so good ! We are not yet, however, out of the mathe¬ 
matical wood. If we were to solve the equations as they stand, 
we should be making a mistake in theory, and a mistake which 
is by no means always negligible in practice. We should be pro- 
ceding as if 4, 4, etc., were observed values. Now the values 
really observed are not these /-values, but the «-values. We 
must, therefore, seek (so to say) to transform the lvalues into 
observed values ; and we may do this by compensating the error 
which their direct treatment as observed values would involve. 
We may do it, in other words, by weighting the /-values. 
Each of the values nx, n2, etc., has a weight w' proportional to 
the number of observations upon which it is based. This value 
w' must for our purposes be multiplied by a coefficient w", to 
be determined from the following Table. Then the products 
w\ w"u w'a w"t, etc., are the required weights of the values 
ti, 4, etc.
        

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.