Data visualization techniques mod 5

Data Analysis for English Reading and Mathematics Pass Rates Your Name Subject and Section Professor’s Name May 4, 2024 This paper delves into a comparative analysis of educational outcomes between the Hampton Division and state-level data across two academic years, focusing on English: Reading, Mathematics, and Sciences. The study applies data from "Div by Subject by Subgroup" and "State by Subject by Subgroup" data from the Virginia Department of Education. Our objective is to dig out the disparity and identify trends that enable us to develop the best target for improving educational equity and effectiveness. Data Preparation and Cleaning Methodology Looking more into the contents of the one dataset, it was shown that both of the "2019-2020 Pass Rate" columns were void. It is already transparent and consistent with recommendations by Kitchin (2014). However, these columns were removed to make the analysis breezy and focus only on comparative outcomes for the 2020-2021 and 2021-2022 school years. Moreover, many entries from those who had taken examinations online and who needed to be completed were excluded. It adopts one of the best data management practices, recommending the elimination of variables that bring biases due to incomplete data (Little & Rubin, 2002). Cleaning Process The reason behind not considering remotely tested subjects in our analysis is quite apparent: they did not still need to register an entry for the 2020-2021 and 2021-2022 academic years. These data points were not accidental, but rather the gaps in the administrative data that represented a systematic absence of what could substantially affect the overall analysis outcomes. Their omission would introduce significant bias. Solely based on the data points without actual figures in the assessment of educational achievement trends also can lead to wrong conclusions. The deletions of these data make the analysis dataset more reliable or robust by following the principles of the best missing data handling. Schafer and Graham (2002) assert that the conclusiveness of data is of utmost importance if they are to be reliable at all. Moreover, Enders (2010) suggests that methodological decisions regarding data exclusion should include mainly the reflection on the possible influence of missing data on the research results (Schrijvers et al., 2020). Correspondingly, we must have data subjects in the remotely tested group for this study. If this were the case, we would end up biasing our analysis, which would be based on the results of in-person education. Next, it was the most important thing to do to make the results of our analysis as close to reality as the in-person school outcomes were. In essence, this depicts the point raised by Bennett (2001) that a complete or robust data set can be undermined entirely because of the inclusion of variables with elevated missing data, especially when such is systematic (Woods et al., 2024). By adding these variables, we had to eliminate that part of the research that would have increased our findings' reliability and diminished the risk of type I and type II errors in our following statistical tests. Data Analysis Comparative Metrics In order to conduct a de facto comparison, we calculated an Average Pass Rate for every item by averaging the "2020-2021 Pass Rates" and "2021-2022 Pass Rates". This indicator uncovers the actual meaning by supplying the value (for the two different years taken together as a whole, along with the corresponding figure). This established figure is enough to compare the Hampton Division and the state average. Observations and Critical Analysis Gender Difference...