03 03 2014 Exam 2 Study Guide UCR Uniform Crime Reporting UCR purpose UCR content of the data source Crimes known to police Supplemental Homicide Report Crimes cleared by police UCR Hierarchy rule Data collection Part 1 offenses collected and compiled by FBI Large coverage and voluntary participation deals with highest offense first and ignores all others UCR factors affecting reporting of crime Seriousness Type of Crime non reporting UCR factors affecting recording of crime Organizational pressure Organizational changes crack downs different interpretations professionalism discretion police are usually good judges of it something will turn into something more serious down the line Acceptable uses of UCR Homicides Auto Theft and local agencies Unacceptable uses of UCR Comparison across jurisdiction NCVS National Crime Victimization Survey NCVS purpose More reliable estimates Situational factors Demographic data o Victims o Offenders NCVS screening questions the idea is when you re asking someone about victimization you ask them a lot of follow up questions Tabulate what types of crime they were a victim of Panel Design Interviews households overtime every 6 months same people every 6 months For 3 years NCVS survey design NCVS reference period 6 months bounding interview Bounding is achieved by comparing incidents reported in an interview with incidents reported in a previous interview and deleting duplicate incidents that were reported in the current reference period The very first interview is unbound not usually used in the sample telescoping telescoping refers to a respondent s misspecification of when an incident occurred in relation to the reference period short ques NCVS data content Problems with NCVS Hawthorne effect part 1 UCR offenses besides homicide add simple assault boring and long interviews social desirability lack of ability to remember rare occurrences and phone interviews are a big part the fact that human beings will act differently when they know they are being studied population the entire set of elements individuals cities states countries prisons school etc in which we are interested in the list from which the elements of the population are selected the people who were actually selected and interviewed from that list are the the proportion of elements in the population that are selects 1 10 sampling frame sampling element sampling ration parameter vs statistic A parameter is a numerical value that is equivalent to an entire population while a statistic is a numerical value that represents a sample of an entire population sampling error Any difference between the characteristics of a sample and the characteristics of the population from which it was drawn The larger the sample error the less representative the sample is of the population non probability sampling sampling in which the probability of selection of population elements is unknown 4 non probability sampling methods frequently used in Criminology Research availability quota purposive and snowball sampling Also haphazard accidental convenience and judgmental are also non probability sampling methods haphazard judgmental sampling Characterized by lack of order or planning A form of convenience sampling in which the population elements are purposively selected based on the judgment of the researcher method whereby each person interviewed may be asked to suggest additional people for interviewing Elements are selected to ensure that the sample represents certain characteristics in proportion to the population allows us in advance to know how likely it is that any element of a population will be selected for the sample snowball sampling quota sampling probability sampling simple random sample systematic sampling A sample selected in such a way that every element in the population or sampling frame has an equal probability of being chosen A procedure in which the selected sampling units are spaced regularly throughout the population that is every n th unit is selected stratified sampling A type of probability sampling in which the population is divided into groups with a common attribute and a random sample is chosen within each group cluster sampling Breaks population down into non overlapping groups called clusters certain clusters are chosen as the sample randomness EPSEM used to randomly assign subjects they all have the same chance Equal Probability of Selection Method everyone in population has the same change of getting picked Probability proportionate to size PPS A improved form of cluster sampling in which the probability of being selected as the sampling category differs according to how much case each category holds ecological fallacy an error in reasoning in which incorrect conclusions about individual level processes are drawn from group level data criteria of causation deterministic vs probability Association Time Order Non spuriousness Mechanism Context deterministic means that is A causes B then A must always be followed by B We know that to not always be true so we turn to probability which means A probabilistically causes B if A s occurrence increases the probability of B ex smoking cigs causes cancer necessary vs sufficient Necessary something that must be met Sufficient something that may be done to meet requirements but doesn t have to be done temporal order In establishing causation the cause must come before the effect aka time order association a change in the independent variable is associated with a change in the dependent variable ex kids watching violent tv a relationship between two variables that is not due to a relation in non spuriousness a third variable cross sectional vs longitudinal designs within a cross secional design all data is collected at one point in With longitudinal data is collected at two or more points in time easy to identify the time order of effects time time series study a type of longitudinal study in which data is collected 2 or more points in time from different samples of the same population repeated cross sectional panel study cohort don t collect data for many time points and the same people unless they couldn t be contacted fixed sample people who all have experienced a similar event or starting point birth cohort event based design case study true experiments quantitative small of cases 3 or 4 and observe them over the time of 2 years Not discrete observations its pretty constant subjects are assigned randomly to an experimental group that
View Full Document
Unlocking...