Full text: XIXth congress (Part B7,1)

  
Dees, Matthias 
  
In simple random sampling, the mean is estimated by 
$= vIn (D 
k=l 
and the variance of the estimator is estimated by 
e ; 
V ie Mie he Yom Q) 
with y, - the value of the attribute y on element k, that is one of the elements out of the sample k=I..n of size n 
(Cochran, 1976). In simple random sampling the ratio is estimated approximately unbiased by 
  
R,, = P. = Yor 3) 
I z 
„STS 
rs 
where : is the symbol for sums and the variance of the estimator is estimated by 
  
VR.) -s * Rs? -2R,s,.] (4) 
with 
-N ny iA In) n (Q, -Y y, /mG, - Y 3, Im) 
2 -— k=1 . 2 = = k=l k=1 
SEA n-1 PST g^ n-1 (5. 2 y--] 
(Särndal et al, 1992, Dees, 1996) with z, -the value of the attribute z on element k and where 2. , 1$ defined according 
to e 
In stratified sampling with simple random sampling of n, elements (k—1..ny) within A strata (h— 1.. H) the mean is 
estimated as 
n, 
a H 
mW WI (5) 
h=1 =1 5g, 
with the strata specific weights W - [Area of Strata h] / [total area]. 
The variance of the estimated mean is estimated by 
x INS Ya) 
Rn H 
(E M AE on (6) 
n, 
(Cochran, 1976, Sárndal et al., 1992). 
In stratified sampling with simple random sampling within the strata, the ratio is estimated approximately unbiased as 
> 
^ 
= y,strat = Y errat (7) 
Z 
> 
~ 
strat 
et. 
z,strat strat 
The variance of the estimated ratio is estimated by 
  
358 International Archives of Photogrammetry and Remote Sensing. Vol. XXXIII, Part B7. Amsterdam 2000.
	        
Waiting...

Note to user

Dear user,

In response to current developments in the web technology used by the Goobi viewer, the software no longer supports your browser.

Please use one of the following browsers to display this page correctly.

Thank you.