Term
|
Definition
| the complexity of the mathematical mean that can be used to express the relationship between a variables values. |
|
|
Term
| Nominal level of measurement |
|
Definition
| (categorical or qualitative) identifies variables whose values have no mathematical interpretation, they can vary in kind or quality not not in amount. |
|
|
Term
| Mutually exclusive attributes |
|
Definition
| a variable's attributes or value are __________________ if every case can have only one attribute |
|
|
Term
|
Definition
| A variable's attributes or values are ________________ when every case can be classified into on of the categories |
|
|
Term
| Example- Nominal level of measurement |
|
Definition
| Measure of nationality/ measure of females and males by giving males the number 1 and females the number 2 |
|
|
Term
|
Definition
|
|
Term
| Example of Interval level of measurement |
|
Definition
| measurement of the temperature in degrees fahrenheit |
|
|
Term
| Example of Ratio level of measurement |
|
Definition
| measurement of group size |
|
|
Term
|
Definition
| values having only two values, are a special case from the standpoint of levels of measurement |
|
|
Term
|
Definition
| asked to indicate an answer by checking none, one, twice, 3 to 5 times, 6 to 9 times or 10 or more times. The use of these categories make the level of measurement ordinal |
|
|
Term
|
Definition
| a subset of the population ( group that actually gets studied) |
|
|
Term
| Elements (or/ elementary units) |
|
Definition
| individual members of the sample group |
|
|
Term
|
Definition
| the list from which elements are selected and interviewed from |
|
|
Term
|
Definition
| Sample households are terms as this so you can identify the adult individual in the households |
|
|
Term
|
Definition
| unit actually selected in each stage of sampling |
|
|
Term
|
Definition
| (Sampling schools for survey) school would be this selected for the 1st stage and they are the element of the study |
|
|
Term
|
Definition
| (Sampling schools for survey) the teachers are this because they are not the element they are just used to provide information about the entire school. |
|
|
Term
|
Definition
| this exist when a conclusion based on a sample, or subset, or a larger population holds true for that population |
|
|
Term
| Cross-population generalizability (external) |
|
Definition
| exist when finding about on group, population, or setting holds true for other groups, population, or settings |
|
|
Term
|
Definition
| any difference between the characteristics of a sample and the characteristics of the population from which it was drawn. |
|
|
Term
|
Definition
| set of elements larger than or different from the population that was sampled and to which the researcher would like to generalize any study findings |
|
|
Term
|
Definition
| a sample that looks like the population from which it was selected from in all respects that are potentially relevant to the study. |
|
|
Term
|
Definition
| sample method that allows us to know in advance how likely it is that any element of the populate will be selected for the same. (example- head or tails is 1 out of 2 or .5) |
|
|
Term
| Nonprobability sampling methods |
|
Definition
| sampling methods that do not let us know the likelihood in advance |
|
|
Term
|
Definition
| every element of population has a known and independent chance of being selected into the sample |
|
|
Term
|
Definition
| this is a major hazard in survey research because people that do not respond are likely to differ systematically from those who take the time to participate |
|
|
Term
|
Definition
| requires a procedure that generates numbers or identifies cases strictly on the basis of chance |
|
|
Term
|
Definition
| researcher would use this when he numbers all the elements in the sample frame and then uses a systematic procedure for picking corresponding numbers from this ________ |
|
|
Term
|
Definition
| a machine that dials random numbers within the phone prefixes corresponding to the area in which the survey is being conducted |
|
|
Term
|
Definition
| each element is returned to the sample frame from where it was selected to that it might be selected again from the frame |
|
|
Term
|
Definition
(used during systematic random sampling ) the total number of the population divided by the number of cases required for the sample
(if you need 50 samples) out of 1000 the ___________ is 20 because 1000/50=20 |
|
|
Term
|
Definition
elements that are selected because they are available or easy to find. (this type of sample is not generalizable, but is often appropriate in research for using as an example)
Reporter might do this on the street by using person-on-the-street interview |
|
|
Term
|
Definition
| type of sampling that is much like stratified sampling but is less rigorous and precise in the selection process. this type ensures that the sample represents certain characteristics in population |
|
|
Term
|
Definition
| a hypothetical distribution of statistic (e.g., proportion, mean) across an infinite number of random samples that could be drawn from a population |
|
|
Term
|
Definition
| Mathematical tools for estimating how likely it is that a statistical result based on data from random sample is representative of the population from which the sample was selected |
|
|
Term
|
Definition
| Its graph looks like a bell with one hump in the middle, centered around the population mean and the number of cases tapering off on both sides of the mean |
|
|
Term
| Systematic sampling error |
|
Definition
| overrepresentation or underrepresentation of some population characteristics in a sample due to the method uses to select the sample (biased sample) |
|
|
Term
|
Definition
| difference between the population and the sample that are die only to chance factors, not to systemic sampling error. This may or not result in an unrepresentative sample |
|
|
Term
|
Definition
| an estimated statistic from the one sample we actually selected from a population |
|
|
Term
|
Definition
| the range defined by the confidence limits for a sample statistic |
|
|
Term
|
Definition
| the upper and lower bounds around an estimate of population parameter base on a statistic. the confidence limits shows how much confidence can be placed in the estimate. |
|
|
Term
|
Definition
| levels of social life on which the research questions is focused, such as individuals, groups, towns or nations |
|
|
Term
|
Definition
| data collected from individuals |
|
|
Term
|
Definition
| when a researcher draws conclusions about individual level processes from group level data |
|
|
Term
|
Definition
| when data about individuals are used to make inference about group level processes |
|
|
Term
| Nomothetic causal explanation |
|
Definition
| involving the belief that variation in an independent variable will be followed by variation in the dependent variable, when al other things are equal. |
|
|
Term
| Causal Effect (nomothetic perpective) |
|
Definition
| when variation in one phenomenon (independent variable) leads to or results, on average in variation in another phenomenon (the dependent variable) |
|
|
Term
| Example of a Nomothetic causal effect |
|
Definition
| individuals arrested for domestic assault tent to commit fewer subsequent assaults than do individuals who are accused in the same circumstance but not arrested |
|
|
Term
| Idiographic causal explanation |
|
Definition
| the concrete, individual sequence of events, thoughts, or actions that result in a particular outcome for a particular individual that led to a particular event |
|
|
Term
| Example of an idiographic causal effect |
|
Definition
| individual is neglected by his parents.. he comes to distrust other, has trouble maintaining friendships, has trouble in school, and eventually get addicted to heroin. to support his habit he starts selling drugs and he is ultimately arrested and convicted for drug trafficking |
|
|
Term
|
Definition
| to conclude that causation was involved we must see that that cases were exposed to variation in the independent variable before variables in the dependent variable |
|
|
Term
|
Definition
| the relationship between two variables is no due to variation in a third variable |
|
|
Term
|
Definition
| this is the 3rd variable that cause variation between the first two variables. |
|
|
Term
|
Definition
| when a extraneous variable cause variation between the independent and dependent variable. |
|
|
Term
|
Definition
| some discernible mean of creating a connection |
|
|
Term
|
Definition
| when relationship amount variables differ across geographic units like counties or across other social settings |
|
|
Term
| True experiment must have these 3 things |
|
Definition
1) two comparison groups one experimental one control
2)random assignment
3) assessment of change in the dependent variable for both groups after experimental condition has been received |
|
|
Term
|
Definition
| When a method utilizes the condition of an experimental method in a real world setting |
|
|
Term
| Cross-sectional research design |
|
Definition
| all data are collected at one point in time; identifying the time order of the effects what happened first and so on. |
|
|
Term
| Longitudinal research design |
|
Definition
| data are collected at two or more pouts in time and so identification of the time order of effects can be quite straightforward |
|
|
Term
|
Definition
| this helps respondents recall events in their past by displaying each month of a given year along with key dates noted with the calendar such as birthdays, arrest, holidays, anniversaries and so on. |
|
|
Term
|
Definition
| key dates which are placed inside of a life calendar |
|
|
Term
| Arrestee drug abuse Monitoring (ADAM) |
|
Definition
| the life calendar instrument is based on this type of interview schedule |
|
|
Term
| Lo, Kim, and Cheng (2008) |
|
Definition
Do offenders specialize in different crimes?
Used the life calendar instrument |
|
|
Term
|
Definition
the other name for
Repeated cross-sectional design |
|
|
Term
| Repeated cross-sectional design |
|
Definition
| type of longitudinal study in which data are collected at two or more points in time from different samples of the population |
|
|
Term
| How repeated cross-sectional surveys are conducted |
|
Definition
1- sample is drawn from a populations at time 1 and data are collected from the sample
2- as time passes some people leave the population and others enter it
3- at time 2 a different sample is drawn from the population |
|
|
Term
| Fixed-sample panel design (panel study) |
|
Definition
| type of longitudinal study in which data are collected from the same individuals- the panel- at two or more points in time |
|
|
Term
| How fixed-sample panel designs are conducted |
|
Definition
1- a sample(the panel) is drawn from the population at time1 and data is collected from the sample
2- as time passes some panel members become unavailable for follow up and the population changes
3 at time2, data is collected from the same people as time1, with the exception of those people who could not be located |
|
|
Term
|
Definition
used a fixed-sample panel design
investigated the effects of childhood deviance on adult crime |
|
|
Term
|
Definition
| panel members may grow weary of repeated interviews and drop out of the study or may become so used to answering standard question that they start giving stock answers rather than actually thinking about their current feeling or actions, which is called |
|
|
Term
|
Definition
called cohort study
The follow-up samples are picked from people who have experienced a similar event or a common sating point |
|
|
Term
|
Definition
| people who have experienced a similar event or a common starting point |
|
|
Term
|
Definition
event-based design- study individual from the same cohort
-Birth cohort( people who share common period of birth (1940s 1950s, etc)
-Seniority cohort (people working in the same place for about 5 years, about 10 years)
-School Cohort (freshmen, junior, senior, etc) |
|
|
Term
|
Definition
| a technique used in non experimental research to reduce the risk of spuriousness, one variable is held constant so the relationship between two or more other variables can be assessed without the influence of variation in the control variable. |
|
|
Term
| Example of statistical control |
|
Definition
| Sampson found that the relationship between rates of family disruption and violent crime held true for cities with similar levels of joblessness (the control variables) so the rate of joblessness could not have cause the association between family disruption and violent crime. |
|
|
Term
|
Definition
| variables that are influenced by an independent variable and in turn influence variables in a dependent variable, thus helping to explain the relationship between the independent and dependent variable |
|
|
Term
|
Definition
| measurement of the outcome in both groups after the experimental group has received the treatment |
|
|
Term
|
Definition
| measures the dependent variable prior to the experimental intervention |
|
|
Term
| When do experiments not require a Pretest |
|
Definition
when random assignment is used-
because the groups score on the dependent and other variables will most likely be similar |
|
|
Term
|
Definition
pairing of persons basis on similarity of gender, age, year in school etc
Problems- only match by few characteristic so it might influence the outcome |
|
|
Term
| Quasi-experimental design |
|
Definition
this is usually the nest alternative to an experimental design, maximizing internal validity
the comparison group is predetermined to be comparable to the treatment group uncritical ways, such as eligibility for the same service or attendance at the same school cohort |
|
|
Term
| 3 major types of quasi-experimental design |
|
Definition
-Nonequivalent control group-
-Before and After design-
-Ex post facto control group design- |
|
|
Term
| -Nonequivalent control group |
|
Definition
| have experimental and comparison group designed before the treatment occurs and are not created by random assignment |
|
|
Term
|
Definition
| have a pretest and posttest but no comparison group, in other words the subjects are exposed to the treatment served at an earlier time as their own control |
|
|
Term
| -Ex post facto control group design |
|
Definition
| like nonequivalent control group design, have experimental and comparison groups that are not created by random assignment. but unlike the groups in nonequivalent control groups design , the groups in ex post facto designs are designated after the treatment or intervention has occurred. for this reason some researchers consider this design to be non experimental, not even quasi-experimental |
|
|
Term
| Nonequivalent control group designs |
|
Definition
Individual matching- individuals cases in the treatment groups are matched with similar individuals in the comparison groups
Aggregated matching- matching in the aggregated means finding a group with similar distribution on key variables such as same ages, same percentage of females and so on. comparison group is identified by the ones that matches the treatment group in the aggregated rather than individuals |
|
|
Term
| Fixed sample panel design |
|
Definition
the simplest type of before and after design-
a panel design involve only one pretest and posttest, and does not qualify as a quasi-experimental design because comparing subjects to themselves at one earlier point does not provide adequate comparison groups |
|
|
Term
|
Definition
(time series design)
this design typically includes many pretest and posttest observations that allow the researcher to study the process by which the intervention or treatment has an impact over time |
|
|
Term
| Carrington and Schulenburgs |
|
Definition
studied the effect of the youth criminal justice act (YCJA) of 2002 in canada on police discretion with apprehending young offenders by using
Repeated measure panel design |
|
|
Term
| 5 basic sources of internal invalidity |
|
Definition
-selection bias
-endogenous change
-external events or history effect
-contamination
-treatment misidentification |
|
|
Term
|
Definition
| when characteristics of the experimental and comparison group subject differ |
|
|
Term
|
Definition
| when the subject develop or change during the experiment as part of an ingoing process independent of the experimental treatment |
|
|
Term
| External event or history effect |
|
Definition
| when something occurs during the experiment, other than the treatment, that influences outcome scores |
|
|
Term
|
Definition
| when either the experimental group or the comparison group is aware of the other group and is influenced in the posttest as a result |
|
|
Term
| Treatment misidentification |
|
Definition
| when variation in the independent variable (the treatment) is associated with variation in the observed outcome, but the changes occurs though a process that the researchers has not identified |
|
|
Term
|
Definition
group can differ over time because of this and it can be though of as deselection.
Groups become different because of various reasons subjects are more lively to drop out of a group |
|
|
Term
| endogenous changes include 3 specific threats to internal validity |
|
Definition
Testing- (people may answer different since they are asked the some question in the pre and posttest)
maturation- (may age)
Regression- (someone who got a low score might change because they were just having a bad day) |
|
|
Term
| Compensatory rivalry or the John Henry effect |
|
Definition
| when the comparison group members become aware that they are being denied some advantage, they may increase their efforts to compensate |
|
|
Term
| Treatment misidentification has at least three sources; |
|
Definition
1) expectancies of experimental staff
2) placebo effect
3)Hawthorne effect |
|
|
Term
| expectancies of experimental staff |
|
Definition
staff can deliver the treatment in a enthusiasm that makes the subject create a self-fulfilling prophecy
Double-blind procedures - where the staff that is delivering the treatment doesn't know |
|
|
Term
|
Definition
| When you give someone a fake treatment but they start to feel better because the have an expectation that it will make them better. but the treatment actually has no medical effect |
|
|
Term
|
Definition
| members of the treatment group may change in terms of the dependent variable because their participation in the study may make them feel speical |
|
|
Term
|
Definition
periodic measures are taken throughout the experiment to assess whether the treatment is being delivers as planned .
use this to avoid treatment misidentification |
|
|
Term
|
Definition
| the applicability of a treatment effect (or non effect) across subgroups within an experiment and/or across different population, times, or settings. |
|
|
Term
| Solomon four-group design |
|
Definition
| randomly assigns subjects to at least two experimental groups and a least two comparison groups (1 experiment and 1 comparison will have a pretest then the other experiment and comparison group will not have a pretest) |
|
|
Term
| Ethical issues in experimental research |
|
Definition
| deception and distribution of benefits |
|
|
Term
| Ordinal level of measurement |
|
Definition
| What type of measurement is likely to use words like, strongly agree, agree, neutral, disagree, and strongly disagree |
|
|
Term
| Ordinal level of measurement |
|
Definition
| What type of measurement is likely to use words like, strongly agree, agree, neutral, disagree, and strongly disagree |
|
|
Term
|
Definition
| simple random sampling and complex random sampling |
|
|
Term
|
Definition
| random sampling error produces this |
|
|
Term
|
Definition
this type of sampling has to use equal probability selection methods like
Random number table
computer
systematic random sampling |
|
|
Term
| Systematic random sampling |
|
Definition
| a unit is randomly selected from a list then every nth element is chosen to use |
|
|
Term
| Sample error decline when |
|
Definition
you-
have a large sample size
sample to the population is greater than .25
the use of random selection procedure |
|
|
Term
|
Definition
| this is eliminated when nothing but change affects the selection of the element |
|
|
Term
|
Definition
| correlation does not prove causation |
|
|
Term
|
Definition
| latin word for - there things are equal |
|
|
Term
|
Definition
| cyclical or episodic change that results in different posttest scores/ (maybe the person was having a bad day) and will do better time |
|
|
Term
|
Definition
| outcome that would have occurred if subject who was exposed to the treatment was actually not |
|
|
Term
|
Definition
| involves the collection of information from a sample of individuals through their responses to questions |
|
|
Term
| Self-administered questionnaires |
|
Definition
respondent completes and submits survey instrument
- mail survey
- email/ internet survey
-classroom type survey |
|
|
Term
|
Definition
researcher ask respondent questions and respondents answers to theses questions
- face to face
- telephone |
|
|
Term
-Versatility (popularity)
-efficiency
- generalizabiliy |
|
Definition
| attractive features of survey research |
|
|
Term
| issues in survey research |
|
Definition
selection bias
measurement error
overemphasis on minor forms of offending
panel studies |
|
|
Term
| Selection bias (survey research) |
|
Definition
| response rate (not sure what the majority opinion is) |
|
|
Term
| Measurement error (survey research) |
|
Definition
| more error is likely if someone says they have have committed a higher amount of crime rather than someone who says they committed a small number |
|
|
Term
| Overemphasis on minor forms of offending |
|
Definition
| knowing different between a kid get lunch money stole and armed robbery |
|
|
Term
| Panel study (survey research) (testing effect) |
|
Definition
| person learn the way to answer question in a way that will make the survey shorter |
|
|
Term
|
Definition
| this type of survey is likely to have low contamination rates and high control over sample selection |
|
|
Term
| fenced-sitting (questions problems) |
|
Definition
| survey respondent that sees themselves as being neutral on an issue and choose to answer a middle (neutral) response |
|
|
Term
|
Definition
| when substantive answers are given even when subject does not know it |
|
|
Term
| Contingency questions (example) |
|
Definition
| Example- if answered yes on Q12, please answer Q15 and Q16 if you answered no please skip to Q17 |
|
|
Term
|
Definition
| media violence and aggression (violent video) |
|
|
Term
|
Definition
| police strength increase substantially on days when the terror alert level rises |
|
|
Term
| Klick and tabarrok (type of study, other) |
|
Definition
| Non-experimental study w/ high internal validity |
|
|
Term
|
Definition
(Prison condition and recidivism)
Policy goal- lower security = lower cost of confinement |
|
|
Term
| Gaes and Camp (type of study, validity) |
|
Definition
| this is a Randomized experiment with high internal validity and reasonably credible external validity |
|
|
Term
|
Definition
juvenile recidivism (2 years)
Residential or community placement |
|
|
Term
| 1945 philadelphia birth cohort study |
|
Definition
retrospective event based, cohort design
By age t what fraction of individuals in the population get arrest at least once |
|
|
Term
| Carrington and schulenberg |
|
Definition
studied the effect of the youth criminal justice act in canada on police discretion with young offenders
Times series design---> repeated measure panel design |
|
|
Term
|
Definition
Matched teens
1) reported having been arrest in last 3 years
2)reported committing at least 4 offenses |
|
|
Term
|
Definition
labling
did not compare apples to apples |
|
|
Term
|
Definition
federal inmate classification system
- different security levels corresponds tp different security levels |
|
|
Term
|
Definition
| number of units that responded out of the number of units contacted |
|
|
Term
|
Definition
how serious a problem is crime
had no response rate, so you don't know what the majority opinion actually is |
|
|
Term
|
Definition
| this type of response generally ask respondent to indicate to the extent to which they agree or disagree with the statement |
|
|
Term
|
Definition
| occurs when individuals response vary because of their reaction to particular words or ideas in the question |
|
|
Term
|
Definition
| helps researchers decide whether responses are consistent |
|
|
