Presentation on theme: "Allyn & Bacon 2003 Social Work Research Methods: Qualitative and Quantitative Approaches Topic 8: Sampling Why all the Fuss about Including."— Presentation transcript:
Copyright @ Allyn & Bacon 2003 Social Work Research Methods: Qualitative and Quantitative Approaches Topic 8: Sampling Why all the Fuss about Including Women and Minorities in Social Work Research?: http://ohrp.osophs.dhhs.gov/humansubjects/ guidance/hsdc94-01.htm This multimedia product and its contents are protected under copyright law. The following are prohibited by law: any public performance or display, including transmission of any image over a network; preparation of any derivative work, including the extraction, in whole or in part, of any images; any rental, lease, or lending of the program.
Copyright @ Allyn & Bacon 2003 Topic 8: Sampling What is Nonprobability Sampling? What are some types of Non-probability Samples? What is Probability Sampling? What are the basic terms? Why random selection? What are some types of Probability Samples? How large should a sample be?
Copyright @ Allyn & Bacon 2003 What is Nonprobability Sampling? Haphazard or Convenience – select whomever is handy or bumped into. Quota – select a certain number that are handy based on prior decisions about how many are needed Purposive or Judgmental – seek out certain individuals known to be available Snowball – ask each selected case to refer you to another
Copyright @ Allyn & Bacon 2003 Nonprobability Sampling continued… Extreme Case – select cases based on their unusualness or difficulty of finding Sequential – select cases based on some preset order of selection Theoretical – select cases according to theory
Copyright @ Allyn & Bacon 2003 What are some Types of Nonprobability Sampling? Haphazard samples are cases gotten in any manner. Quota samples are designed to get a preset number of cases, i.e. half men, half women. Purposive samples use as many possible cases that fit a particular criteria as can be gotten, with various methods. Snowball samples get cases using referrals from prior cases.
Copyright @ Allyn & Bacon 2003 Nonprobability samples continued… Extreme case samples get cases that substantially differ from the dominant pattern. Sequential samples get cases until there is no additional information from new cases. Theoretical samples get cases that will help reveal features that are important to a theory.
Copyright @ Allyn & Bacon 2003 What is Probability Sampling? Population, elements and frames. Why is it random? Types of probability samples. Hidden populations. How large should a sample be?
Copyright @ Allyn & Bacon 2003 What are the basic terms? Populations (sometimes also called universes) are sets or pools of elements from which a sample is to be selected. Elements are units of analysis such as persons, groups, organizations or agencies. Sampling Frames are lists of population elements that are intended to be exhaustive, that contain no duplicates, or foreign or missing elements.
Copyright @ Allyn & Bacon 2003 Why Random Selection? The word random refers to a process that generates a mathematically random result, one in which no humanly generated pattern exists. Social work researchers select their cases using a random procedure in order to assure that no human bias exists in the selection process. They hope that the inferences they draw from their study will be maximally generalizable, statistically accurate, and useful.
Copyright @ Allyn & Bacon 2003 What are the basic Types of Probability Samples? Simple Random Sample is the easiest sample to draw; it is based on a randomly numbered table of select cases from a sampling frame from a reasonably small population. Systematic Sample is a selection of cases from a sampling frame by taking every xth case after a random start (i.e. if 3 cases were needed out of 30, we could take each 10 th case after selecting the first case randomly).
Copyright @ Allyn & Bacon 2003 Probability samples continued… Stratified sample is taken such that, prior to the random selection of cases, the social work researcher separates the population into two or more categories or strata. Then the researcher selects cases separately and randomly, and combines the separately selected cases into one final sample. Cluster Samples take advantage of geographic proximity (i.e. patients in hospitals, persons who are homeless in shelters). A social work researcher select from a list of similar places, and then studies each case in the proximity in the final smallest cluster.
Copyright @ Allyn & Bacon 2003 Probability Sampling continued... Random-Digit Dialing - a special sampling technique used with the general public when interviewing by telephone. Hidden Populations - hard to reach people who may not want to be identified may be able to be sampled by combining both qualitative and quantitative methods such as snowball sampling or asking currently identified persons to recruit others who are similar.
Copyright @ Allyn & Bacon 2003 How Large Should a Sample Be? Sample size can be determined following a formula that statisticians have created that figures a sample size depending on how confident the social work researcher wants to be (usually 95%), how much error she or he can tolerate (usually between 2-5%), an estimate of how much variability (or heterogeneity) exists in the population, and the size of the actual population to be studied. Another strategy considers the number of variables being examined and the number of hypotheses being tested. In general, a good rule of thumb is that the more details that are involved and under study, the larger the sample needs to be.