| 
  • If you are citizen of an European Union member nation, you may not use this service unless you are at least 16 years old.

  • You already know Dokkio is an AI-powered assistant to organize & manage your digital files & messages. Very soon, Dokkio will support Outlook as well as One Drive. Check it out today!

View
 

Chapter 6  Selecting a Sample

This version was saved 18 years, 1 month ago View current version     Page history
Saved by PBworks
on May 6, 2006 at 8:05:36 pm
 

Home Page

Previous Chapter 4 Reviewing the Literature

 

****p. 163: #1(Compare the logic used in quantitative and qualitative research to generalize beyond the sample that was studied)****

Quantitative Research

1. "The general rule in quantitative research is to use the largest sample possible". Pg. 176

2. Large samples should be used in quantitative research particularly when measures with low reliability are to be used.

 

Research “rules of thumb” to guide estimates:

1. Survey - minimum of 100 participants

2. Correlational - minimum of 30 participants

3. Causal-comparative - minimum of 15 per group

4. Experimental & Quasi-experimental - minimum of 15 per group

Types of Sampling in Quantitative Research:

1. Simple random sampling (all have equal chance)

2. Systematic sampling (take every nth subject)

3. Stratified sampling (subgroups represented)

4. Cluster sampling (groups of individuals)

5. CONVENIENCE sampling (who you can get!)

6. Problem is population validity -- To what population can you generalize the findings? Who does the convenience sample really represent?

Qualitative Research:

Qualitative research is more flexible with regard to sampling techniques than quantitative. The flexibility reflects the emergent nature of qualitative research design with allows researchers to modify methodologies as data are collected.

 

The sampling techniques used in qualitative researcher are suggestive rather than prescriptive and they do not necessarily exhaust the possible ways in which a qualitative research sample might be selected.

Purposeful Sampling - Types of Purposeful Sampling:

 Extreme case sampling (special, exceptional cases)

 Intensity sampling (intensely but not extremely)

 Typical case sampling (the average case)

 Maximum variation sampling (illustrate the range of variations)

 Stratified purposeful sampling (at defined points of variation)

 Homogeneous sampling (all similar cases)

 Critical case sampling (if it works here…)

 Snowball sampling (well-situated people recommend)

 Etc. page 178-181 in Gall, Gall & Borg

 OPPORTUNISTIC sampling - use of findings from one case to guide selection of next case for study. Learn from your studied cases to decide what other types of cases should be studied to increase your “deep understanding.’

 

#2(Explain the meaning of population validity and replication logic)

Population Validity is the extent to which the results of an experiment can be generalized from the sample that participated in it to a larger group of individuals – a population. Inferential statistics contribute evidence to establish population validity of a set of research results. Population validity can only be achieved if the accessible population is logically representative of the target population.

 

Population Validity can be quantified if we compute a statistic for a sample and know the actual population from which the sample was drawn.

Sample => randomly selected from Experimentally Accessible Population =>logically selected from Target Population

Replication Logic is a strategy that uses theory to determine other cases to which the findings of one case can be generalized. The validity of the theory is tested through a series of empirical replications, each involving one or more case studies. If the theory is well supported by the replications, the theory will identify the population of individuals to whom a particular set of generalizations will apply. Replication logic is implied in the grounded theory approach.

Two Types of Replication

1. A literal replication predicts that the next case to be studied will yield results that are similar to those of similar cases that a researcher has studied.

2. A theoretical replication predicts that the next case to be studied will yield results that differ from those obtained for other cases that have been previously studies, in ways consistent with the theory that underlies the research.

 

#3(Explain the relationship between a sample, the target population, and the accessible population)

1. The sample in a study is randomly selected from the accessible population. The sample is the actual participants in your study.

2. The target population consists of all members of a set of persons to whom a researcher wishes to generalize the results of a study.

3. The accessible population represents all the individuals who could realistically be included in the sample.

 

 

#5(Describe the advantages of and procedures used in the sampling techniques: random sampling, systematic sampling, stratified sampling, and convenience sampling)

1. Simple random sampling (all have equal chance)

2. Systematic sampling (take every nth subject)

3. Stratified sampling (subgroups represented)

4. Cluster sampling (groups of individuals)

5. CONVENIENCE sampling (who you can get!)

 

#6(Identify seven factors that should be considered in determining sample size for a quantitative research study)

Adequate Sample Size (There are only five in PPT and in book p. 176-177 & 140-143)

1. Need to consider Subgroup Analysis if you want to analyze data of specific groups

2. Need to consider Attrition so you will have enough participants left at end of study

3. Need to consider Reliability of Measures -- low reliability means you need more participants

4. If you want to get REALLY sophisticated, you can perform a Statistical Power Analysis (G,G & B p. 140-43)

5. You can also use the Krejcie & Morgan formula for determining small samples {See handout!}

 

 

#7(Explain the rationale for purposeful sampling)

Purposeful sampling is justified when selecting information-rich cases related to the study goals. It is not designed to achieve population validity. The intent of purposeful sampling is to achieve an in-depth understanding of selected individuals, not to select a sample that will represent accurately a defined population.

Types of Purposeful Sampling:

Extreme case sampling (special, exceptional cases)

Intensity sampling (intensely but not extremely)

Typical case sampling (the average case)

Maximum variation sampling (illustrate the range of variations)

Stratified purposeful sampling (at defined points of variation)

Homogeneous sampling (all similar cases)

Critical case sampling (if it works here…)

Snowball sampling (well-situated people recommend)

Etc. page 178-181 in Gall, Gall & Borg

OPPORTUNISTIC sampling - use of findings from one case to guide selection of next case for study. Learn from your studied cases to decide what other types of cases should be studied to increase your “deep understanding.’

 

#10(Describe typical differences between volunteers and nonvolunteers as research participants, and how the influence of volunteers on research results can be tested)

Characteristics of Research Volunteers:

1. Volunteers tend to be better educated than non-volunteers, especially when personal contact between investigator and respondent is not required.

2. Volunteers tend to have higher social-class status than non-volunteers, especially when social class is defined by respondents' own status rather than by parental status.

3. Volunteers tend to be more intelligent than non-volunteers when volunteering is for research in general, but not when volunteering is for somewhat less typical types of research, such as hypnosis, sensory isolation, sex research, small group research, or personality research.

4. Volunteers tend to be higher in need for social approval than non-volunteers.

5. Volunteers tend to be more sociable than non-volunteers.

6. Volunteers tend to be more arousal-seeking than non-volunteers, especially when volunteering is for studies of stress, sensory isolation, and hypnosis.

7. Volunteers tend to be more unconventional than non-volunteers, especially when volunteering for studies of sex behavior.

8. Females are more likely than males to volunteer for research in general, but less likely than males to volunteer for physically and emotionally stressful research (e.g., electric shock, high temperature, sensory deprivation, interviews about sex behavior).

9. Volunteers tend to be less authoritarian than non-volunteers.

10. Jews are more likely to volunteer than Protestants, and Protestants are more likely to volunteer than Roman Catholics.

11. Volunteers tend to be less conforming than non-volunteers when volunteering is for research in general, but not when subjects are female and the task is relatively "clinical" (e.g., hypnosis, sleep, or counseling research). Pg. 183

#11(Describe several techniques for improving the rate of volunteering for participation in a research)

 

#11(Describe several techniques for improving the rate of volunteering for participation in a research)

Improving the Rate of Volunteering:

1. Make the appeal for volunteers as interesting as possible to the group you are trying to enlist for the study.

2. Make the appeal for volunteers as non-threatening as possible.

3. Make explicit the theoretical and practical importance of the study.

4. Make explicit how the group you are trying to enlist represents a target population that is particularly relevant to the study.

5. Emphasize that, by volunteering for the study, individuals have the potential to benefit others.

6. Offer to potential volunteers, when possible, not only payment for participation, but small courtesy gifts simply for taking the time to consider whether they want to participate.

7. Have the request for volunteering made by a person of high status.

8. Try to avoid research tasks that can be psychologically or biologically stressful.

9. Try to communicate the fact that volunteering is the normal thing to do.

10. In situations where volunteering is regarded by the target population as the normal thing to do, ask each individual to make a public commitment to volunteer. Where non-volunteering is regarded as the normal thing to do, create a situation where each individual can volunteer in private.

11. After a target population has been defined, have someone known to that population make the appeal for volunteers. Pg. 185

 

 

 

Home Page

Next Chapter 7 Collecting Research Data with Tests and Self-Report Measures

Planning Page for this Wiki Check here to see who is doing what!

Comments (0)

You don't have permission to comment on this page.