Study Guides (238,096)
United States (119,676)
CJ 2601 (2)

Study Guide for Intro to CJ Research Test 2

4 Pages
Unlock Document

Temple University
Criminal Justice
CJ 2601
Erin Kerrison

Intro to Criminal Justice Research Study Guide #2 Chapter 5-Sampling 1. 2. Stratified sampling can result in less sampling error than random sampling in certain studies such as ones conducted in ethnically diverse neighborhoods. Stratified random sampling uses information known about the total population prior to sampling to make the process more efficient.All elements in the population are differentiated on the basis of their value on some relevant characteristic (such as race). This step forms the sampling strata- and the elements within the strata are then sampled randomly. Within each racial category selected for the strata, individuals are then sampled randomly. An example of it’s efficiency compared to random sampling could be displayed in a sample of 500 from an ethnically diverse neighborhood. (use percentages of races) If you draw a random sample, one would probably end up with disproportionate numbers of each group. However, if you created sampling strata based on race and ethnicity using stratified sampling, you can randomly select cases from each stratum and eliminate any possibility of error in the sample’s distribution of ethnicity. Each stratum would be represented exactly in proportion to its size in the population from which the sample was drawn. 3. Generalizability has two aspects: Sample generalizability and cross-population generalizability. Sample gen. refers to the ability to generalize from a sample of a larger population to that population itself (most common). Cross-population gen. refers to the ability to generalize from findings about one group, population, or setting to other groups, populations, or settings. Generalizability is an important concept because we rarely have the resources to study the entire population of interest to us, so we must select cases to study that will allow our findings to be generalized to the population of interest. If a study lacks generalizability it is not valid because the researcher is projecting their theories onto groups or populations much larger or different from those they actually studied. Their results would not apply to their target population and would thus be invalid. Chapter 6-Causation and Research Design 4. Association alone is not sufficient to establish causation between the two variables: early release, and inmate’s probability to recidivate/ higher crime. The mechanism is the lack of punishment, which the politician says creates the connection. First, the two variables must have an empirical association, meaning that the relationship must be observable/have concrete evidence.Another criteria that must be established is time order, meaning the early release must occur before the inmates recidivism. Lastly, correlation does not prove causation!Aresearcher has to prove nonspuriousness, meaning that the relationship between the two variables is not due to variation in a third variable. This is where the relationship goes wrong in this case- the researcher can’t prove that the reason for the high recidivism rate is because the inmates are inadequately punished. It could be because the released prisoners have no families to go home too, no housing, no friends, no money, and actually want to be back in prison. The researcher isn’t able to observe that the real cause of this high crime rate is due to lack of sufficient punishment for these inmates. In addition, the politician fails to acknowledge the possible contextual effect between the two variables such as differences in women recidivism rates, inmates with family, ect. If she had acknowledged the larger context, she would have known that there are many other reasons for recidivism.An alternative explanation for recidivism that does not involve early release as a cause, but does allow for its association would be: the inmate lacks the legitimate means to live in normal society (employment, family, money, education, friends) and thus resorts to crime to achieve these means, or resorts to crime simply to be put back in their comfort zone with a place to eat, sleep, and live amongst others. Their early release leaves them simply unprepared for life in society. 5. Across sectional research design is when all the data are collected at one point in time- to study the relation between attendance at boot camp and recidivism I could retrieve records of re-admitted inmates/crime records of people who went to boot camp and re- admitted inmates/crime records of people who did not and compare the two groups. A longitudinal research design is when data are collected at two or more points in time- time order is straight-forward. One of these designs is a repeated cross-sectional design or trend study, in which data are collected at two or more points in time from different samples of the same population. To study the relationship I could retrieve data from a jail and determine the percentage of the re-admitted inmates that have been to boot camp before.After a few years, I would return to the same prison and determine a new percentage of inmates who have been to boot camp before, and compare the two numbers. This could help me determine a trend/relationship between the two variables. Another longitudinal design is a fixed-panel design, where one follows the same sample of the population at 2 different periods in time. To study the relationship I could retrieve data from a boot camp to determine the percentage of attendees who have been involved in crime.After a couple of years or so, I could retrieve criminal data about the same individuals who were once involved in crime, and compare the percentages to determine a negative or positive relationship. The last longitudinal research design is an event-based design or cohort study, where one doesn’t follow up the same sample of a population, but a population that includes those who have all experienced a similar event or common starting point (birth cohort, school cohort, seniority cohort). To study the relationship using this design I would retrieve data from a number of prisons to determine the percentage of re-admitted inmates who have been to boot camp before. After a time period I would collect data again to determine a new percentage of re-admitted inmates who have been
More Less

Related notes for CJ 2601

Log In


Don't have an account?

Join OneClass

Access over 10 million pages of study
documents for 1.3 million courses.

Sign up

Join to view


By registering, I agree to the Terms and Privacy Policies
Already have an account?
Just a few more details

So we can recommend you notes for your school.

Reset Password

Please enter below the email address you registered with and we will send you a link to reset your password.

Add your courses

Get notes from the top students in your class.