Population Sampling 4th

Please download to get full document.

View again

of 10
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Document Description
Document Share
Documents Related
Document Tags
Document Transcript
  7-1 Populations and SamplingChapter 7  ©  4th ed. 2006 Dr. Rick Yount The Rationale of Sampling In Chapter One, we established the fact that inductive reasoning is an essentialpart of the scientific process. Recall that inductive reasoning moves from individualobservations to general principles. If a researcher can observe a characteristic ofinterest in all members of a population, he can with confidence base conclusions aboutthe population on these observations. This is perfect induction. If he, on the otherhand, observes the characteristic of interest in some members of the population, hecan do no more than infer that these observations will be true of the whole. This isimperfect induction, and is the basis for sampling. 1  The population of interest isusually too large or too scattered geographically to study directly. By correctly draw-ing a sample from a specific population, a researcher can analyze the sample andmake inferences about population characteristics. The Population A “population” consists of all the subjects you want to study. “Southern Baptistmissionaries” is a population. So is “ministers of youth in SBC churches in Texas.” Sois “Christian school children in grades 3 and 4.” A population comprises all thepossible cases (persons, objects, events) that constitute a known whole. 2 Sampling Sampling is the process of selecting a group of subjects for a study in such a waythat the individuals represent the larger group from which they were selected. 3  Thisrepresentative portion of a population is called a sample. 4 PopulationSamplingBiased SamplesRandomization 7 7 7 7 7  Populations and Sampling  The Rationale of SamplingSteps in SamplingTypes of SamplingInferential Statistics: A Look AheadThe Case Study Approach 1 Donald Ary, Lucy Cheser Jacobs, and Asghar Razavieh, Introduction to Research in Education, (NewYork: Holt, Rinehart and Winston, Inc., 1972), 160 2 Ibid., p. 125 3 L. R. Gay, Educational Research: Competencies for Analysis and Application, 3rd ed., (Columbus,Ohio: Merrill Publishing Company, 1987), 101. 4 Ary et. al., 125  7-2  Research Design and Statistical Analysis for Christian MinistryI: Research Fundamentals ©  4th ed. 2006 Dr. Rick Yount Biased Samples It is important that samples provide a representative cross-section of the popula-tion they supposedly represent. The sample should be a “microcosm” — a miniaturemodel — of the population from which it was drawn. Otherwise, the results from thesample will be misleading when applied to the population as a whole. If I select“Southern Baptist ministers” as the population for my study and select SouthernBaptist pastors in Fort Worth as my sample, I will have a biased sample. “Fort Worthpastors” may not reflect the same characteristics as ministers (including staff mem-bers) across the nation. Selecting people for a study because they are within conve-nient reach —members of my church, students in a nearby school, co-workers in thesurrounding region — yields biased samples. Biased samples do not represent thepopulations from which they are drawn. Randomization The key to building representative samples is randomization . “Randomization” isthe process of randomly selecting population members for a given sample, or ran-domly assigning subjects to one of several experimental groups, or randomly assigningexperimental treatments to groups. In the context of this chapter, it is selecting sub- jects for a sample in such a way that every member of the population has an equalchance at being selected. By randomly selecting subjects from a population, youstatistically equalize all variables simultaneously. Steps in Sampling Regardless of the specific type of sampling used, the steps in sampling are essen-tially the same: identify the target population, identify the accessible population,determine the size of the sample, and select the sample. Identify the Target Population The first step is the identification of the target population. In a study concerningprofessors in Southern Baptist seminaries, the target population would be all profes-sors in all Southern Baptist seminaries. In a study of job satisfaction of local churchstaff ministers, the target population is all staff ministers in all churches. Identify the Accessible Population Since it is usually not possible to reach all the members of a target population, onemust identify that portion of the population which is accessible. The nature of theaccessible population depends on the time and resources of the researcher. Given thetarget population of “Southern Baptist professors,” the accessible population might be“Southwestern Seminary professors.” Given the target population of “local churchstaff ministers,” the accessible population might be “Southern Baptist ministers ofeducation in Texas.”Notice that specifying the accessible populations reduces the scope of the twoexamples in the preceding paragraph. In most cases this is helpful because beginningresearchers tend to include too much in their study. Target Population Accessible PopulationSize of SampleSelect  7-3  Populations and SamplingChapter 7  ©  4th ed. 2006 Dr. Rick Yount Determine the Size of the Sample Student researchers often ask “How big should my sample be?” The first answeris “use as large a sample as possible.” 5  The reason is obvious: the larger the sample, thebetter it represents the population. But if the sample size is too large, then the value ofsampling — reducing time and cost of the study — is negligible.The more common problem, however, is having too few subjects, not too many. 6 So the more important question is, “What’s the minimum number of subjects I need?”The question is still difficult to answer. Here are some of the factors which relate toproper sample size.  Accuracy In every measurement, there are two components: the true measure of the vari-able and error. The error comes from incidental extraneous sources within eachsubject: degree of motivation, interest, mood, recent events, future expectations. All ofthese cause variations in test results. In all statistical analysis, the objective is to mini-mize error and maximize the true measure. As the sample size increases, the random extraneous errors tend to cancel each other out, leaving a better picture of the truemeasure of the population. Cost An increasing sample size translates directly into increasing costs: not only ofmoney, but time as well. Just think of the difference in printing, mailing, receiving,processing, tabulating, and analyzing questionnaires for 100 subjects, and then for1000 subjects.The dilemma of realistically balancing “accuracy” (increase sample size) with“cost” (decrease sample size) confronts every researcher. Inaccurate data is useless,but a study which cannot be completed due to lack of funds is not any better.“Cost per subject” is directly related to the kind of study being done. Interviewsare expensive in time, effort and money. Mailing out questionnaires is much lessexpensive per subject. Therefore, one can plan to have a larger sample with question-naires than with interviews for the same cost. The Homogeneity of the Population “Homogeneous” [from homo-genos , “like-kind”] means “of the same kind ornature; consisting of similar parts, or of elements of the like nature” (Webster, s.v.“homogeneous”). Homogeneity in a population means that the members of the popu-lation are similar on the characteristic under study. We can take a sample of twodrops of water from a 10 gallon drum, and have a good representative sample of theten gallons. This is because the water in a 10 gallon drum is an homogeneous solution(if we mix it up well before sampling). But if we take two people out of a group of 500,we will not have a good representative sample of the 500. “People” are much lesshomogeneous than a water solution!But even populations of people vary in homogeneity. The population “TexasBaptists” would have less variability on the issue of gambling than the more generalpopulation of “Texans.” The greater the variability in the population, the larger thesample needs to be. 5 Ary et. al., 167 6 Gay, 114  7-4  Research Design and Statistical Analysis for Christian MinistryI: Research Fundamentals ©  4th ed. 2006 Dr. Rick Yount Other Considerations Borg and Gall list several additional factors which influence the decision to in-crease the sample size (See pp. 257-261). These are 1. When uncontrolled variables are present.2. When you plan to break samples into subgroups.3. When you expect high attrition of subjects.4. When you require a high level of statistical power (see Chapter 17) . So, what is a good rule of thumb for setting sample size in a research proposal?Here are two suggestions Sample Size Rule of Thumb Dr. John Curry, Professor of Educational Research,North Texas State University (now retired), provided hisresearch students (fall, 1984) with the rule of thumb onsample size (see right). Using this rule, an adequate sampleof Southern Baptists’ 36,000 pastors would be a randomsample of 1%, or 360 pastors.L. R. Gay suggests 10% of large populations and 20%of small populations as minimums. 7  Using Gay’s sugges-tion, our sample of pastors would include 3,600. It is left tothe student to weigh the factors of accuracy, cost, homoge-neity of the accessible population, type of sampling andkind of study, and determine the best sample size for hisstudy. Select the Sample The final step is to actually select a sample of predetermined size from the acces-sible population. Types of Sampling There are several ways of doing this. We will look at four major types here: simplerandom, systematic, stratified, and cluster sampling. The basic characteristic of ran-dom sampling is that all members of the population have an equal and independentchance of being included in the sample. 8 Simple Random Sampling The most common method of sampling is known as simple random sampling: Pick a number out of a hat!  Gay provides a good example of this type of sampling. 9  A superintendent of schools wants to select a sample of teachers so that their attitudestoward unions can be determined. Here is how he did it: 1. The population is 5,000 teachers in the system.2. The desired sample size is 10%, or 500 teachers.3. The superintendent has a directory which lists all 5,000 teachers alphabetically. He assigns numbers SimpleSystematicStratifiedCluster  7 Gay, 114-115 8 Ary, 162 9 Gay, 105-7 foeziS noitalupoP g nilpmaS tnecreP 001-0 %001 000,1-101 %01 000,5-100,1 %5 000,01-100,5 %3 +000,01 %1
We Need Your Support
Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

Thanks to everyone for your continued support.

No, Thanks