Scribd
Upload
7 views4 pages

LECTURE 11b

The document discusses the standard errors of estimated population mean and total area, highlighting their use in various sampling methods and the finite population correction (fpc). It explains that fpc is applicable when sampling from finite populations, and can often be ignored if the sampling fraction is low. Additionally, it provides examples of sampling techniques and calculations related to population and sample means and variances.

Uploaded by

Jorams Barasa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
7 views4 pages

LECTURE 11b

The document discusses the standard errors of estimated population mean and total area, highlighting their use in various sampling methods and the finite population correction (fpc). It explains that fpc is applicable when sampling from finite populations, and can often be ignored if the sampling fraction is low. Additionally, it provides examples of sampling techniques and calculations related to population and sample means and variances.

Uploaded by

Jorams Barasa
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

In-Text Question

The standard errors of the estimated population mean and total area are used primarily for
these purposes except:

A. To compare the precision obtained by SRS with that given by other methods of
sampling;
B. To estimate the size of the sample needed in a survey that is being planned
C. To estimate the size of mean data
D. To estimate the precision actually attained in a survey that has been completed.
In-Text Question
C. To estimate the size of mean data

2.2.7 The Finite Population Correction


For a random sample of size n from an infinite population, it is well known that the variance
σ2
of the mean is . The only change in this result when the population is finite is the
n

N −n N −n N −n
introduction of the factor . The factors for variance and for the
N N N
standard error are called the finite population correction (fpc).

n
Provided that the sampling fraction remains low, these factors are close to unity, and the
N
size of the population as such has no direct effect on the standard error of the sample mean.
In practice, fpc can be ignored whenever the sampling fraction does not exceed 5% and for
many purposes even if it is as high as 10%. The effect of ignoring the correction is to
overestimate the stranded error of the estimate y.
Example:

Consider the weights at birth y, of a population of four babies delivered in one day in a
maternity clinic.

35
Ui 1 2 3 4

Yi 3.9kg 3.6kg 3.4kg 3.7kg

(a) Select all possible samples of size n = 2

(i) With replacement

(ii) Without replacement

(b) Obtain the population mean

(c) Obtain the sample mean

(d) Obtain the sample variance/population variance

Solution

ai) All samples of size 2 in SRSWr

Samples Sample units Probability Sample mean

1 (3.9,3.9) 1/16 3.9

2 (3.9,3.6) 1/16 3.75

3 (3.9,3.4) 1/16 3.65

4 (3.9,3.7) 1/16 3.8

5 (3.6,3.9) 1/16 3.75

6 (3.6,3.6) 1/16 3.6

7 (3.6,3.4) 1/16 3.5

8 (3.6,3.7) 1/16 3.65

9 (3.4,3.9) 1/16 3.65

10 (3.4,3.6) 1/16 3.5

36
11 (3.4,3.4) 1/16 3.4

12 (3.4,3.7) 1/16 3.55

13 (3.7,3.9) 1/16 3.8

14 (3.7,3.6) 1/16 3.65

15 (3.7,3.4) 1/16 3.55

16 (3.7,3.7) 1/16 3.7

Mean 3.65

aii) All samples of size 2 in SRSWor

Samples Sample units Probability Sample mean n

( N − n) ∑
(y − y)
2
i
i =1

N n(n − 1)

1 (3.9,3.6) 1/6 3.75 0.01125

2 (3.9,3.4) 1/6 3.65 0.03125

3 (3.9,3.7) 1/6 3.8 0.005

4 (3.6,3.4) 1/6 3.5 0.005

5 (3.6,3.7) 1/6 3.65 0.00125

6 (3.4,3.7) 1/6 3.55 0.00125

Mean 3.65 0.01083

b) The population mean is obtained using the weights of all the four babies.

3.9 + 3.6 + 3.4 + 3.7 14.6


Y = = = 3.65
4 4
σ 2 = 0.0325

37
c) From (ai) and (aii) we discover that the mean of the sample means, both for sampling with
replacement and without replacement, are equal to the population mean. Therefore, we say
that the sample mean is an unbiased estimator of the population mean.

d) i. The mean sample variance for SRSWr is given by

σ2 0.0325
σ y2 = V ( y ) = = = 0.01625
n 2

ii. The mean sample variance for SRSWor is given by

( N − n) S 2
V (y) =
N n
Where
n

∑( y − y)
2
i
S2 = i =1

n −1

See column 5 of table (aii).

2.2 Non-Random
Random Sampling (non probability)
Non probability sampling can be categorized into the following:

Judgement or Purposive
Sampling

Haphazard Sampling

Quota Sampling

Figure 2.4: Non Probability Sampling categories

38

You might also like