CRJU 202 005
CRJU 202 005 CRJU 202 005
Popular in Research Methods in Criminology and Criminal Justice
Popular in Criminology and Criminal Justice
This 5 page Class Notes was uploaded by Alexis M. on Sunday October 2, 2016. The Class Notes belongs to CRJU 202 005 at University of South Carolina taught by Brian Fuleihan in Fall 2016. Since its upload, it has received 3 views. For similar materials see Research Methods in Criminology and Criminal Justice in Criminology and Criminal Justice at University of South Carolina.
Reviews for CRJU 202 005
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 10/02/16
9/26/2016 Chapter 5: Sampling What is a sample & why would we want to use one? Generalizability or External Validity Population the entire set of elements (individuals or other entities) Sample a subset of elements from the population Sample generalizability ability to generalize from a subset (sample) of a larger population to that population itself Crosspopulation generalizability ability to generalize from one population, or setting—to other populations, or setting Basic Sampling Types Probability sampling Known probability of selection into sample Produces the most generalizable sample Nonprobability sampling Unknown probability of selection into sample Frequently used in qualitative research, which populations is not well defined Sampling Methods Probability Sampling Methods Sampling methods that allow us to know in advance… how likely it is that any element of a population will be selected for the sample. The probability is known and not zero (requires a sampling frame) Allows researchers to select study subjects … to be statistically representative of population they want to learn about (generalize to) Representative= aggregate characteristics of the sample closely approximate those characteristics in the population Even when a random selection process is used, two common problems can result in bias… (1) Incomplete sampling frame E.g., In a study of campus drug use, our list of enrolled students may not reflect recent withdrawals (dropouts) If sampling frame is incomplete, it is not truly a random sample of population (2) Nonresponse An inability to contact a good number of subjects or having a high refusal rate can result in biasness. Why? Opinion varies, but a 60% response rate is ‘acceptable’; strive for at least 70% Even so, there is still error associated with every probability sample taken Even IF sampling frame and response rate are good, there is still error associated with every probability sample taken. Important kinds of probability samples Simple Random Sample Identifies cases strictly on the basis of chance True random sample is obtained through the equal probability of selection method (EPSEM) All members of population have equal chance of being sampled Some methods of selecting a SRS: coin flip, roll of dice, random number table, random digit dialing, computer generated random numbers. How to obtain a Simple Random Sample (SRS) Assign a number to all the elements listed in the sampling frame. 1 John 11 Tina 21 Ronald 2 Kelli 12 John 22 Dave 3 Joan 13 Bobby 23 Taylor 4 Stephen 14 Jeff 24 Ashley 5 Sharon 15 Katie 25 Thomas N= 30 students 6 Robert 16 Mike 26 Jack n = 6 students (20% sample) 7 Mark 17 Megan 27 Lisa 8 Laura 18 Pamela 28 Anna 9 Andrew 19 Kathy 29 Martin 10 Rachel 20 Lindsey 30 Lola Consult a random number table (AE) 74088 65564 39634 62349 16379 19713 39153 69459 17986 24537 40469 27478 14595 35050 44526 67331 93365 54526 22356 93208 83722 79712 30734 71571 25775 65178 07763 82928 31131 30196 91254 24090 64628 89126 25752 03091 39411 73146 06089 15630 43511 42082 42831 95113 15140 34733 68076 18292 69486 80468 41047 26792 80583 70361 78466 03395 17635 09697 82447 31405 99457 72570 00209 90404 42194 49043 24330 14939 09865 45906 HOWEVER, WE NOW HAVE COMPUTER PROGRAMS WHICH GENERATE LISTS OF RANDOM NUMBERS FOR SAMPLING PURPOSES Systematic Random Sample Determine the number to sample, for example, a sample of 125 from a population of 700 Calculate sampling interval population / sample size. Round to next lowest whole number 700 / 125 = 5.6 5 Select first element randomly (usually from a list), and then select every n element. Here, select every 5 member of population In almost all sampling situations, systematic random sampling yields what is essentially a simple random sample Unless this occurs…... Periodicity – the sequence of elements of the population varies in some regular, periodic pattern Stratified Random Sample Strata – layers, levels, groups (singular is stratum) Purpose: to ensure that various groups will be included in the sample. Useful when researcher needs to make sure that small groups are included 1. Distinguish all elements in the population (i.e., in the sampling frame) according to their value on some relevant characteristic (e.g., police officer rank: captains, lieutenants, sergeants, patrol officers, etc.). That characteristic forms the sampling strata. Each element must belong to one and only one stratum 2. Sample elements randomly from within each strata: e.g., 25 captains, 25 sergeants, etc. Types of Stratified Sampling Imagine that you plan to draw a sample of 500 from an ethnically diverse neighborhood. The neighborhood population is 15% black, 10% Hispanic, 5% Asian, and 70% white. A simple random sample might, for example, end up with no Asians and very few Hispanics. In proportionate stratified sampling, you create sampling strata based on a characteristic of interest (e.g., ethnicity) and randomly select cases from each stratum, in exactly the same proportions. In disproportionate stratified sampling, the proportion of each stratum that is included in the sample is intentionally varied from what it is in the population. Here, you might select an equal proportion from each ethnic group. Cluster Sampling Cluster naturally occurring, mixed group of elements of the population; each element (person, for instance) appears in one and only one cluster at one time Prisons are clusters for sampling inmates City blocks are clusters for sampling residents Useful when sampling frame (a definite list of elements) is not available or too expensive to cover Larger populations spread out across a wide geographic area “Hidden” populations Also called “multistage cluster sampling” because cluster sampling is at least a twostage procedure. Draw a random sample of clusters. (A list of clusters should be much easier to obtain than a list of all the individuals in every cluster in the population). Draw a random sample of elements within each selected cluster. NonProbability Sampling Nonprobability sample Kinds of nonprobability samples Convenience sampling a.k.a., sampling of available subjects; selection of cases on the basis of ease of availability to researcher Quota sampling Like stratified sampling, but selection of subjects within strata is nonrandom (left to interviewer judgment) Sample unlikely to be representative of the population on other characteristics Purposive sampling a.k.a., judgmental sampling Use your expertise to sample units/subjects Purposive & probability sampling Snowball sampling Selection of cases on the basis of referrals from sampled individuals Proceeds in two stages Useful for sampling cases within a network Goal of sampling To generalize to population, sample must be as representative as possible Random sampling error Refers to the difference between a sample statistic and the true value in the population due solely to chance Sampling error or bias Statisticians estimate the probability that a sampling result is representative of the population using sampling distribution Systematic sampling error Refers to differences between the sample and population due to some problem with the sampling method Units of Analysis
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'