of samples and directly with the square root of the unsampled part of 

 the total population. Hence, they can be controlled by altering either 

 the number of samples , the size of individual samples , or both. 



Since the percentage error increases with each subdivision of the total, 

 small acreages or volumes may have large errors and may therefore indi- 

 cate only relative magnitudes. 



Area 



Area estimates for the part covered by complete survey have no sampling 

 errors o For the part covered by samplings the probabilities are 2 out 

 of 3 that sampling errors are within the following limits i 



Estimated 



area Standard error 



Acres Acres Percent 



Commercial forest land ....... 5,733,000 +78,000 ± 1*3 



Noncommercial and reserved 



forest land. . ............. . ?14 s 000 +86 a OOO +12.0 ■ 



Total forest land ......... 6,497,000 +57,000 10.9 



For North Idaho as a whole, considering sampling and technique errors 

 for the sampled area and technique errors for the area covered by com- 

 plete survey, it is judged that actual areas lie between the following 

 limits s 



Thousand acres 



Commercial forest land ..... ............ . 7, 682- 7,838 



Noncommercial and reserved forest land 2,380- 2,552 



Total forest land ................. ..... . 10^169-10,283 



Volume 



Volume sampling errors, after properly adjusting for sampling errors in 

 area determination, are; 



G rowing stock Li ve sawt.imber 



Million cubic feet Percent Million board feet Percent 



+ 296 + 2.2 +_ 1687 + 2.8 



The true volumes for North Idaho are estimated to be within the follow- 

 ing limits? 



Growing stock ...... 12.9 -13.5 billion cubic feet 



Live sawtimber . .... 59.0 - 62.4 billion board feet 



30 



