Data Analysis Plan for Quantitative Research

Topic: Predictors of Employment Success Among Foreign Prisoners

Many foreign prisoners experience challenges after release in finding meaningful employment. Different personal and situational factors affect their employability and lead to lower or higher employment rates. Individual factors such as race, ethnicity, health status, offense type, length of sentence, and owing debt affect the employability post-prison. Contextual factors include the connection to employers before release, consistent work experience that may have existed before incarceration, established family relationships, re-entry experiences, and activities or experiences in prison. Therefore, this study aims to identify predictors of employment success among foreign prisoners.

Research Questions

Does pre-prison experience determine employment success among foreign prisoners?

Does in-prison experience determine employment success among foreign prisoners?

Does post-prison experience determine employment success among foreign prisoners?

Data Analysis Plan

Descriptive statistics

Before employing inferential statistics, we will conduct descriptive statistics to summarize and visually display the collected data. Frequency tables, charts and histograms will be utilized to visually describe the data. Descriptive statistics will be performed on the following variables: attributes that existed before incarceration (race, country of origin, age at release, worked pre-prison; proficiency in Italian); attributes that were experienced that during incarceration (education in prison; prison work experience; mental health condition) attributes that exemplify circumstances prisoners faced after release (drug use, married; children; family support). Both descriptive and inferential analysis will be done using SPSS statistical analysis tool

Inferential statistics

For the inferential statistics, the following hypothesis will be tested

H₀ Prison time affects the employability of former foreign prisoners.

H_A Prison does not affect the employability of former foreign prisoners.

To better understand why some former prisoners experience greater employment success than others, multivariate analysis will be conducted using regression analysis to identify predictive factors while controlling for theoretical variables of interest such as race, age at release, education, drug use and marital status. Additionally, inverse probability weights will be utilized to account for selection bias (Gayle & Lambert, 2021).

For the study, there will be several screening tools required to collect the data on the experience of the prisoners after re-entry into the community. The analysis will be carried out just before release to 12 months after release from prison. There will be a need to correct the differences between the final sample analyzed and the original sample interviewed before release. Inverse Probability Weights will be used to correct for difference the final sample and the original sample interviewed before release (Liu, 2016).

The dependent variable in this analysis is the percentage of time employed since release in months (something like 0%; 1–25%; 26–50%; 51–75%; 76–99%; 100%), as of the last post-release survey at twelve months.  The independent variables will include the various attributes that existed prior to incarceration, the attributes experienced during imprisonment and attributes that exemplify circumstances prisoners faced after release. Multivariate analysis will be conducted using regression analysis to identify predictive factors. In addition, R-square statistic correlation will be used to analyze the dependent variable’s variance as explained by the independent variables (Taguchi, 2018).  High percentage of R-Square statistic indicates that the independent variables greatly explain the dependent variable.

Conclusion

In conclusion, statistical analysis for the longitudinal study must account for all factors that may lead to variances within the population and reflect on the data collected from the survey. The data reflect the multiple attributes of the data while still enabling a complete and rough analysis to develop statistical significance that can inform the researcher on the shortcomings that prisoners face in finding employment when they reenter society. Understanding these characteristics can help make programs exhaustively inclusive of prisoners’ needs and improve their experience after re-entry into the community.

 

References

Gayle, V., & Lambert, P. (2021). Quantitative longitudinal data analysis: research methods. http://public.eblib.com/choice/PublicFullRecord.aspx?p=6379885.

Liu, X. (2016). Methods and applications of longitudinal data analysis. London Wall, UK, Academic Press.

Taguchi, N., (2018). Description and explanation of pragmatic development: Quantitative, qualitative, and mixed methods research. System, 75, pp.23-32.