Statistical measurements are very important in a wide range of studies. Qualitative and quantitative data is collected, estimated, systematized, and analyzed. This is the basis for prediction, projecting, and forecasting. Time series analysis is vital as it can make a significant impact and help to save lives or paint a clear picture of future trends. It is employed within environmental studies to calculate the rates of the development of global warming, it is used to predict earthquakes in seismology, or measure sunspots in astrophysics. Basically, every study that works with quantitative and qualitative data required time series analysis. This paper is designed to discuss the use of time series analysis in my specialization, criminal justice, in order to measure the rates of recidivism or re-offending.
My specialization is criminal justice. It is a complex system developed to maintain order within the society. It protects the average individuals from those who violate the law and harm other people in various ways or damaged properties. Criminal justice has a system of penalties for the law violators. These penalties include monetary fines, rehabilitation labor, and imprisonment or isolation of the dangerous individuals from the rest of the society for a certain period of time. In criminal justice, the offenders have rights and freedoms, they may be protected, and the penalties assigned to them have limitations.
In criminal justice, it often happens that the law violators who had been sentenced and undergone various penalties choose to follow the same path after the punishment is over. This tendency is called recidivism or re-offending. In criminal justice, reoffending is one of the basic concepts. The measurements recidivism include such variables as repeated conviction and re-arrest, and the return of an offender to the prison soon after the previous conviction (Recidivism, 2014). Based on all of these variables, it is possible to create and estimate patterns of re-offending for certain types of individuals within particular periods of times and in different locations.
Since recidivism patterns are the therapeutic outcome under analysis the estimation should be directed at the patterns of its re-appearance after the intervention. This way, the best time series design to use in this case is quasi-experimental research design. The intervention therapy should target the imprisoned offenders who are to be released soon. The results of offending among the participants of the research need to be estimated prior to the implementation of the therapy.
They should include patterns registered three years before the imprisonment. This way, the main objective of the quasi-experimental research design will be to compare and demonstrate the difference of re-offending patterns before and after the therapy (Time Series Design, n. d.). For more detailed analysis, the participants of the therapy can be divided into groups based on their past re-offending patterns, for example, the number of convictions can be the variable to divide the individuals, or the kinds of their sentences.
The post-therapy data also should be measured within three years after the release of the participants. This way, the analysis will show if the therapy is more effective for any particular type of convicts. This research may help to develop better understanding of autocorrelation patterns of recidivism and the catalysts of this phenomenon, and to estimate if there is a connection between past and future re-offending (Nash, Murphy, Moore, Shaw, & O’Neil, 2008).
In conclusion, quasi-experimental research design was selected for the documentation and analysis of recidivism patterns in criminal justice due to the need for the estimation of the efficiency of an intervention therapy. The specific group of individuals is analyzed before and after the treatment implementation and the effect it produced is measured.
Reference List
Borckardt, J., Nash, M., Murphy, M., Moore, M., Shaw, D., & O’Neil, P. (2008). Clinical practice as natural laboratory for psychotherapy research: A guide to case-based time-series analysis. American Psychologist, 63(2), 77–95.
Recidivism. (2014). NIJ. Web.
Time Series Design. (n. d.). Academy Health. Web.