Reflection Entry

Looking back on this semester, the best way to summarize the takeaways of IS301 Intro to Computer Analysis is gaining a better understanding for data collection and analysis. We began the semester by looking at the basic definitions for a research study. We studied Thyne’s book, Political Analysis for the Rest of Us, and had to identify variables, hypotheses and null hypotheses, theories, research methods, resources utilized, and conclusions in already published works to identify these definitions outside of the textbook. We reviewed specific rules on how to construct causal theories which would be later implemented in our research project. We then progressed to developing hypotheses from the construction of theories which required more simplified definitions of what we wanted to study in the project. We also discussed different methods of analysis to use in our studies and ways to compare variables and identifying statistical significance.

After obtaining a basis of political science analysis and research, the class shifted gears in learning how to use IBM’s SPSS program for political analysis. Pollock began by demonstrating how to download the program and editing data. After gaining a basis for how SPSS works, we actually began running tests and comparing variables in problems on the worksheets in the back of each chapter. This practice really reinforced the concepts and made it easier to learn how to analyze political and social research. We learned how to interpret measures of central tendency and variation, the different types of variables, and how to interpret different case summaries. After this introduction, we practiced recoding, binning, and computing. We learned how to do both cross-tabulation analysis and mean comparison analysis along with graphing various relationships into a line, bar, and pie chart and even box plots. We learned how to utilize control variables and their significance in a given analysis. Sample means were significant in making conclusions in the worksheets through one-sample T tests and independent-samples T test in order to compare relationships between variables and make generalizations. We dove into measures of association and statistical significance by defining chi-square and correlation and putting them into practice. Bivariate Regression, scatterplots, regression, and interaction effects were later practiced once we became more comfortable with the software. Pollock’s book on SPSS concluded with application to political analysis scenarios and placing all we learned throughout the semester into context. Overall, SPSS was good practice in this course but I don’t think I would have been very successful with conducting political analyses on my own for the project without my group, Prof. Sanborn, and Pollock’s walkthrough on how to work the software.

I was fully expecting this class to be statistics-based and out of reach regarding my comprehension and liking. But throughout the semester I gained a betting appreciation for the research practices and statistical analysis that goes into political science. One must do groundwork before concluding any type of theory and generalization. I realized this the most when we began conducting surveys for the research project; I never fully understood all the time and effort that goes into putting in data and finding the best way to compare variables. The amount of times I had to go back into SPSS to find the best way to verify our hypothesis, which ended up being statistically insignificant, was innumerable.

My favorite thing that I learned in this course would be the different tests to run on SPSS so you don’t have to compute correlation, regression, mean, median, standard deviation, and other measures on your own. I always hated statistics in high school and even during my first year here because in those classes you had to memorize all the equations in order to conduct any sort of data analysis. With SPSS, all you have to do is plug in the numbers and it does everything else for you. It is definitely IS Major-dummy proof.

My least favorite thing that I learned in this course would have to be the application of all that we went over this semester to our own data analysis. I guess I didn’t like it much because I wasn’t too confident on my knowledge of these skills, therefore making the research project very difficult to figure out.

All of this being said, this was only wetting my feet in data analysis, for I would be lost in the dark without Prof. Sanborn walking us through worksheets or if I didn’t have Pollock’s SPSS Companion to Political Analysis to reference when analyzing our surveys. This course definitely taught me different ways of data analysis but I would require a more in-depth course with individual work with SPSS in order to fully develop these technological skills to apply in political science during my education and even beyond in the work force.

Poster Presentation

Today we will present our findings in poster format during class and learning about other analyses conducted in class. This will allow my group to further simplify our findings and generalize our conclusion of no statistical significance found between extracurriculars and cumulative GPA at VMI. We still need to finish our research paper and reflective essays but once those two items are solidified, the significance of this study and, overall, the course will be more apparent.

Analyzing Data

After plugging in the results of the survey, my group found that there is no statistical significance of extracurriculars both currently and in high school with cumulative GPA at VMI. This proves the null hypothesis of our study and justifies the possible theory that more free time may provide individuals with the means to get work done in comparison to those who are involved within the corps. Further analysis should include specific majors and application requirements for these extracurriculars at VMI.

Steps towards Research

As we begin our research project and get our IRB application approved, my group and I will begin applying the statistical and data analysis presented in the homework towards the data we will collect. The following presents what will be analyzed in our research:
Research Q: Why do some VMI cadets have higher GPAs than others?

Theory: Those who are not as involved in the corps will have lower GPAs than those involved with extracurricular activities also lack in time commitment and work ethic. One can assume that being involved does not let cadets slack on their work, but in reality the correlation is more closely linked to the actual involvement in extracurriculars; they have the effect of development, career aspirations, school attendance, social standing among peers, reduced delinquency, lower dropout rates, reduced drug use, and most significantly future success. Being involved with extracurriculars thus promotes time-management skills and ambitions which can cause students to strive for better grades and put the time into studying.

Hypothesis:

HYP 1- time management/involvement in extracurriculars – If a cadet is highly involved
within activities in the corps such as clubs, rank, extracurricular activities, etc; the cadet will have a higher GPA compared to a cadet who is not as involved in the corps.

HYP 2- If a cadet spends more time (hours) studying per day, then they will have a higher GPA.

HYP 3- If a cadet has better natural abilities at retaining knowledge, then they will have a higher GPA.

Method: random sample of 100 cadets (90 males, 10 females to accommodate the representation of the population) between the classes of 2021, 2020, and 2019.Collecting extracurriculars, major, and GPA.

We will be handing out the surveys today and analyze the data after all 100 samples are collected and combined. I’m interested to see what the correlation between the variables will present.