Sampling

 

GE 1702: Essential Academic English

Shinawatra University

What is Sampling? When undertaking a research project, a researcher has a question or set of questions that hoe or she wants to answer. For example, if the researcher would like to know the information technology needs of University students in Thailand, she would have to identify the ‘population’. In this case, the population would be all ‘university students’ at in Thailand. This illustrates a basic problem that all researcher’ have to face in their research project. There are hundreds of thousands of ‘university students’ in Thailand? . Clearly, the the researcher cannot study every university students students in Thailand. This is where sampling comes into the research process. Sampling can be defined as “….the process of selecting units (e.g., people, organizations) from a population of interest so that by studying the sample we may fairly generalize our results back to the population from which they were chosen (Trachoma, (Trachoma, 2006, n.p.).” It is  possible therefore to use sampling techniques to select a smaller group - or sample - from the  population that will statistically represent the whole population. It is often necessary to use sampling because researchers usually do not have the time, energy, money or resources to study the whole population. Sampling Methods Sampling methods are normally classified as either probability or non-probability. In  probability samples, each member of the population equal chance of being chosen chosen to be in the sample. According to StatPac (2012, n.p.) “The “The advantage of probability sampling is that sampling error can be be calculated. Sampling error is the degree degree to which a sample might differ from the population. When inferring to the population, results are reported plus or minus the sampling error.” Probability sampling methods include random sampling, systematic sampling, and stratified sampling.

In sampling, the sample group is selected from the population andmethods the how thenon-probability sample differs from the the population cannot be determined. Non-probability include convenience sampling, judgment sampling and quota sampling.

Selecting an Appropriate Sample Size In 1975 Roscoe (1975) proposed a number of rules of thumb that can be used to select an appropriate sample for behavioral research.. An abbreviated set of these rules are reproduced here 1. The use use of statistical statistical analyses analyses with samples samples less less than 10 is not not recommend recommended. ed. 2. In simple simple experimental experimental research research with with tight tight controls controls (eg. matched-p matched-pairs airs design), design), successful research may be conducted with samples as small as 10 to 20. 3. In most most experimental experimental research, research, samples samples of 30 30 or more more are recomme recommended. nded.

-1-

 

GE 1702: Essential Academic English

Shinawatra University

4. There is seldom seldom justificat justification ion in behavio behavioral ral research for sample sample sizes of less less than 30 30 or larger than 500. 5. Within Within these these limits (30 (30 to 500), 500), the use of of a sample about about 10% 10% size of the the parent  population is recommended.

In 1970 Krejcie & Morgan (p.608) produced a table for determining sample size based on work done by the National Education Education Association . According to this table, if you have a finite population of 380 an appropriate sample size would be 191.

Table One: Required Sample Size  N - n

N-n

N-n

N-n

N-n

 10 - 10

100 - 80

280 - 162

800 - 260

2800 - 338

15 - 14

110 - 86

290 - 165

850 - 265

3000 - 341

 20 - 19  25 - 24

120 - 92 130 - 97

300 - 169 320 - 175

900 - 269 950 - 274

3500 - 346 4000 - 351

30 - 28

140 - 103

340 - 181

1000 - 278

4500 - 354

 3  35 5 - 32

150 - 108

360 - 186

1100 - 285

5000 - 357

 4  40 0 - 36

160 - 113

380 - 191

1200 - 291

6000 - 361

 4  45 5 - 40

170 - 118

400 - 196

1300 - 297

7000 - 364

 5  50 0 - 44

180 - 123

420 - 201

1400 - 302

8000 - 367

 55  55 - 48

190 - 127

440 - 205

1500 - 306

9000 - 368

60 - 52

200 - 132

460 - 210

1600 - 310

10000 - 370

 65  65 - 56

210 - 136

480 - 241

1700 - 313

15000 - 375

 70  70 - 59

220 - 140

500 - 217

1800 - 317

20000 - 377

 75  75 - 63

230 - 144

550 - 226

1900 - 320

30000 - 379

 80  80 - 66

240 - 148

600 - 234

2000 - 322

40000 - 380

 85  85 - 70

250 - 152

650 - 242

2200 - 327

50000 - 381

 90  90 - 73

260 - 155

700 - 248

2400 - 331

75000 - 382

 95  95 - 76

270 - 159

750 - 254

2600 - 335

100000 - 384

(Given A Finite Population, Where N = Population Size Siz e and n = Sample Size)

-2-

 

GE 1702: Essential Academic English

Shinawatra University

References

Krejcie & Morgan (1970,) Determining Sample Size for Research Activities. Retrieved October 28. 2012 From: http://people.usd.edu/~mbaron/edad810/Krejcie.pdf  Trachoma, William William M.K. (2006). Sampling. Retrieved October 28. 2012 From: “http:// www.socialresearchmethods.net/kb/sampling.php StatPac. (2012). Survey Sampling Methods. Retrieved October 28. 2012 2012 From: http:// www.statpac.com/surveys/sampling.htm

-3-