In this study quantitative data will be captured in order to compare the use of various interventions for the treatment of conduct disorders in adolescents as a means of reducing incarceration rates. This will include collecting variables to define each subject’s characteristics, their treatment situations and the outcomes for that subject. Data processes will guide the organization of data and the level of measurement will direct how that data is described in descriptive statistics. Data will be inspected and validated, and the level of measurement that is used will reflect the small sample size and the type of result.
Data processes
Processes to be used to organize the data in preparation for analysis would include a table which lists each individual subject which would be given an identification number, the treatment condition of that subject, the age, gender and other similar demographic variables. This will provide variables which can be used to determine trends and other findings of interest in relation to the outcomes of the various treatment conditions. This table will provide the necessary information so that the descriptive statistics can be mapped and graphed and the total numbers, ranges of data, means, and medians can be determined.
Level of measurement
Scales of measurement define how descriptive statistics are grouped and presented, and this can have an impact on the findings and results of a study. The level of measurement that will be used is whole numbers representing the actual figures. Grouping and categorization will only occur for non-numerical data, as the sample size will be small enough that it is possible to summarize statistics without the need for the development of measurement scales (Pedhazur & Schmelkin, 2013). These figures may be further grouped if the resulting data shows a trend of significant clustering of data results in terms of outcomes.
Validating and inspecting the data
Processes to be used in order to inspect the data would include looking for outlier data, ensuring that data is only entered once, looking for typographical errors and ensuring that in terms of categories that the same terms are used throughout so that the data can be accurately summarized and described (Rahman et al., 2014). Ways of doing this include summarizing the data through pivot tables to see if non-numerical data categories present in more than one manner. Failing to validate and inspect the data could result in errors in the summary statistics which could otherwise affect the results.
Descriptive statistics
. Descriptive statistics are those that provide an understanding of the population that was used in the research study (Haslam & McGarty, 2014, 127). Descriptive statistics which would be graphed and compute for this data would include the total subjects in the sample, the total number of subjects in each intervention type, and various demographic characteristics of the subjects such as the number of each gender, the age range and the type of conduct disorder(s) that have been diagnosed and the outcome of the intervention. The DSM-5 will be used for the categorization of the conduct disorders (American Psychiatric Association, 2013). For example, the table below provides a guide which will be used for the summary of data provided in the descriptive statistics:
- American Psychiatric Association. (2013). Diagnostic and statistical manual of mental disorders (DSM-5). Washington, DC: American psychiatric association.
- Haslam, S. A., & McGarty, C. (2014). Research methods and statistics in psychology. Sage.
- Pedhazur, E. J., & Schmelkin, L. P. (2013). Measurement, design, and analysis: An integrated approach. Psychology Press.
- Rahman, F. A., Desa, M. I., Wibowo, A., & Haris, N. A. (2014). Data Cleaning in Knowledge Discovery Database (KDD)-Data Mining. International Conference on Advance in Computer Science and Electronics Engineering(CSEE).
