STUDENTS’ COMPETENCE AND PROBLEMS ENCOUNTERED

IN PERFORMING STATISTICAL ANALYSIS

PSYCHOLOGY AND EDUCATION: A MULTIDISCIPLINARY JOURNAL

Volume: 17
Issue 10
Pages: 1057-1061
Document ID: 2024PEMJ1631
DOI: 10.5281/zenodo.10826638
Manuscript Accepted: 02-16-2024
 Psych Educ, 2024, 17(10): 1057-1061, Document ID:2024PEMJ1631, doi:10.5281/zenodo.10826638, ISSN 2822-4353
Research Article

Students’ Competence and Problems Encountered in Performing Statistical Analysis

Arneil V. Kadusale, * Jimmy D. Bucar, Victor L. Ompad, Renalyn S. Bohol
For affiliations and correspondence, see the last page.
Abstract
Statistical analysis, crucial in quantitative research for data interpretation and hypothesis testing, poses significant
challenges for many students. Hence, this study assessed the level of competence in relation to the problems
encountered by the grade 12 students of BIT International College – Main Campus in Tagbilaran City Division for
the school year 2023-2024 using descriptive correlational research design. One hundred sixty students (160)
participated in the study and were identified using simple random sampling. The data gathered were treated using
frequency count, percentage, and Pearson r. The results revealed that the respondents exhibited a commendable level
of significance, indicating a “Competent” proficiency; however, a noteworthy area of improvement pertains to the
execution of chi-square tests, which was rated moderately competent. The respondents encountered problems in
performing statistical analysis, and the most difficult was determining the pertinent data to collect. A statistically
significant yet negligible positive correlation emerged between competence in statistical analysis and encountered
problems. Hence, the study recommended offering specialized training programs or workshops on improving
statistical competence and developing strategies to help students overcome difficulties.
Keywords: teaching mathematics, level of competence, problems encountered, statistical analysis,
descriptive-correlational design, Tagbilaran city, Bohol, Philippines

Introduction
Statistics is indispensable in quantitative research as a critical tool for data analysis and interpretation in various disciplines (Denzin &
Lincoln, 2011; Creswell, 2014; Murphy, 2021). This field of study is fundamental in turning raw data into meaningful information,
enabling researchers to validate their hypotheses and draw conclusions based on empirical evidence. In a data-driven era, applying
statistical principles is vital across various disciplines, providing a structure for understanding trends and making informed decisions
(Grove, 2018). Hence, the precision and objectivity offered by statistics lend credibility and rigor to research findings, making it an
essential component of scholarly work.
Despite the critical role of statistics in research, many in the academic and professional fields need help in employing statistical methods
effectively. Sarmento (2019) and Harraway (2005) both emphasize the gap between theoretical knowledge and practical application,
with the latter suggesting the expansion of statistical service courses and the development of intensive workshops. Kenaszchuk (2011)
and Rashid (2021) further highlight the importance of selecting and using statistical methods in service of research questions and the
need for clear understanding and presentation of statistical methodology. Collectively, they point to the need for enhanced statistical
education and support to bridge the gap between theory and practice.
Meanwhile, in the case of senior high school students, this challenge is often rooted in a little understanding of statistical concepts or
a need for basic skills in applying these concepts to real-world data. This is not surprising because even graduate school students have
negative perceptions regarding statistics due to its level of difficulty and perceived relevance (Elder, 2023). Anggara et al. (2018)
reported that SHS students primarily struggle with probability concepts at a basic understanding level, facing difficulties in forming
sample spaces, applying probability principles, and constructing mathematical models. Similarly, Calma et al. (2022) showed that these
students perform unsatisfactorily in Statistics and Probability, emphasizing that they have a gap in fundamental understanding and
application of the subject. The result is frequently an inability to properly analyze and interpret data, potentially leading to erroneous
conclusions and diminished research value. The difficulty and advancing nature of statistical methodologies necessitate a continuous
learning approach, which can be daunting for many secondary school students.
Implementing the K-12 curriculum has introduced a new dimension in secondary education, particularly with the inclusion of research
writing in the curriculum (Bucar, 2022). This significant reform aims to equip students with essential skills in critical thinking, problem-
solving, and inquiry-based learning (Gallos, 2017). Tabuena and Hilario (2021) noted that in the K-12 curriculum, senior high school
learners are expected to develop their critical thinking by engaging in actual research and undertaking data analysis (e.g., statistical
analysis for quantitative research). Moreover, including research as a mandatory component in senior high school education serves as
a platform to nurture analytical and research skills, enabling students to collect, analyze, and interpret data as valuable assets in their
academic and future professional endeavours (Tabuena and Hilario, 2021). However, integrating these advanced research components
into the curriculum has surfaced challenges, especially in quantitative research, where statistical analysis is central.
Interestingly, the reality persists that many students engaging in quantitative research often need more knowledge and skills in
performing statistical analysis. This is even though prior to enrolling in quantitative research, they are required to enroll and pass
Statistics and Probability- a course offered in Grade 11. Statistics and Probability engage students in solving problems and making
decisions using various data analysis tools and techniques (Ruz & Domanias, 2022). The research conducted by Desamparado et al.

Kadesale et al. 1057/1061

 Psych Educ, 2024, 17(10): 1057-1061, Document ID:2024PEMJ1631, doi:10.5281/zenodo.10826638, ISSN 2822-4353
Research Article

(2019) indicates that a significant portion of 12th-grade students in Senior High School experienced high and average stress levels
across various dimensions, including content understanding, skills/performance, and attitudes towards research.
Recent studies have shown that senior high school students frequently need help with statistical analysis in their research due to weak
mathematical foundations (Kandeel, 2019; Risqi & Rini Setianingsih, 2021). These difficulties highlight the essentiality of statistical
literacy for problem-solving and decision-making. Despite the complexity of statistical analysis emphasized by Tabuena (2021),
students often need to improve in basic statistics and probability concepts. Dumale and Gurat (2023) note meager retention rates in
these areas, suggesting a need for educational interventions to enhance understanding and application of statistical principles in
research. It implies the critical need for improved statistical education to support students in effectively conducting and understanding
research.
Meanwhile, the problem with the use of statistics in quantitative data analysis is particularly evident in BIT International College Main
Campus in Tagbilaran City, Bohol, Philippines. Teachers in this school have noted that Grade 12 students frequently need help with
fundamental statistical analysis in their research projects, significantly hindering their overall performance in the said discipline. This
observation implies the pressing need to evaluate the student's understanding and application of statistical concepts and to identify the
specific challenges they encounter in their research work.
In the context of this school, more research is needed to explore the specific difficulties students face in statistical analysis within their
research projects. This lack of investigation into the students' competencies in this area represents a significant research gap. Addressing
this gap is crucial, as it could provide valuable insights into how educational systems can better prepare students for the demands of
research work, particularly in statistics. Along this line, this research study evaluated the level of competence and problems encountered
in performing statistical analysis among Grade 12 students of BIT International College Main Campus, Tagbilaran City, Bohol,
Philippines, for the school year 2023-2024.
Methodology
The study employed descriptive-correlational design via survey-method. Descriptive-correlational design is appropriate in the study
because it aimed to establish the relationship between the students’ competence and problems encountered in performing statistical
analysis. A sample size of 160 out of 256 Grade 12 students of BIT International College, Main Campus, Tagbilaran City, Bohol served
as the respondents of the study. They were selected via simple random sampling technique using Cochran formula with 95% degree of
confidence and 0.05 margin of error an online randomizer to ensure proper distribution.
Moreover, regarding the survey-instrument used, the researcher used the Curriculum Guide for Statistics and Probability as basis for
the indicators. It underwent validation by statisticians and expert evaluators at Cebu Technological University, Cebu, Philippines. It
also underwent pilot testing in the neighboring school and was analyzed for its internal reliability. It resulted to a Cronbach’s alpha
result of 0.85 which means that the tool is reliable. The research data gathering involved three phases: preliminary (obtaining
permissions and scheduling), data collection (administering and supporting the questionnaire process), and post-data collection (data
processing and analysis).
Regarding the statistical treatment of data, the researchers employed descriptive statistics and inferential statistics. Tests confirmed the
normality of the datasets and the equality of variances, prerequisites for using parametric test. This statistical method was employed to
determine the relationship between students' statistical analysis competencies and the challenges they encountered. The use of Pearson
r, supported by the data's normality and homogeneity, enhanced the reliability of the findings, providing a thorough understanding of
the statistical analysis skills of the respondents.
Results and Discussion
Level of Competence in Performing Statistical Analysis
Table 1 provides a comprehensive assessment of the level of competence of the respondents in performing statistical analysis.
Table 1. Level of Competence in Statistical Analysis
Indicators WM Verbal Description
I can illustrate random sampling. 3.94 Competent
I can define and identify different random sampling techniques 4.00 Competent
I understand the concept of null and alternative hypotheses. 4.20 Competent
I can conduct t-tests for independent and dependent samples. 4.00 Competent
I am proficient in conducting analysis of variance (ANOVA). 3.36 Moderately Competent
I can carry out chi-square tests for categorical data. 2.89 Moderately Competent
I understand the assumptions of various inferential statistics tests. 3.19 Moderately Competent
I can use confidence intervals to estimate population parameters. 3.17 Moderately Competent
I can conduct a correlation and regression analysis. 3.40 Moderately Competent
I understand the difference between Type I and Type II errors. 3.83 Competent
I can interpret p-values and significance levels. 3.43 Competent

Kadesale et al. 1058/1061

 Psych Educ, 2024, 17(10): 1057-1061, Document ID:2024PEMJ1631, doi:10.5281/zenodo.10826638, ISSN 2822-4353
Research Article

I can use statistical software to conduct inferential statistics. 3.16 Moderately Competent
Aggregate Weighted Mean 3.55 Competent
Legend: 4.21-5.00: Very Competent; 3.41-4.20: Competent; 2.61-3.40: Moderately Competent; 1.81-2.60: Less Competent 1.00-1.80: Not Competent

As clearly presented, while respondents feel confident in understanding theoretical concepts, there's a noticeable decline in confidence
when applying these concepts to more specialized or complex analyses, such as ANOVA and chi-square tests. This pattern suggests
that practical application and the transition from understanding to executing statistical tests might be areas where further education or
training could be beneficial. The competence in using statistical software, with a WM of 3.16, further supports this, indicating a
potential barrier in translating statistical knowledge into practical analysis through software tools.
While there is a competent foundation in statistical analysis, there is room for improvement, especially in applying complex statistical
methods and leveraging statistical software. Enhancing skills in these areas could significantly impact the quality of data analysis,
research outcomes, and decision-making processes in various disciplines.
Interestingly, previous studies show that senior high school students often struggle with statistical analysis in their research projects, a
challenge highlighted by Kandeel (2019) who noted that many students face difficulties due to a weak mathematical and statistical
background. This issue is further explored by Risqi, & Rini Setianingsih (2021), who studied the capacity of high school students to
apply statistical literacy in resolving real-world problems. Their research, focusing on students with varying levels of initial statistical
abilities, emphasized the importance of statistical literacy for understanding and decision-making in daily challenges.
Notably, Tabuena (2021) describes statistical analysis as a complex and crucial phase in research, requiring a methodical approach to
handle and interpret extensive data. However, students often show poor performance in statistics and probability, especially in basic
concepts. Dumale and Gurat (2023) further confirm this trend, pointing out the low retention rates in statistics and probability among
students. While some learning competencies like understanding random variables and sampling showed better retention, the overall
grasp of statistics and probability topics remains weak. They suggest that interventions such as problem-posing and student-centered
active learning techniques could enhance student achievement and retention in these areas.
Level of Problems Encountered in Performing Statistical Analysis
Table 2 shows the level of difficulties encountered by the respondents in performing statistical analysis based on 12 indicators.
Table 2. Level Difficulties Encountered by the Respondents in Performing Statistical Analysis
Indicators WM Verbal Description
Determining what data to collect for your analysis. 3.53 Difficult
Dealing with missing or incomplete data. 3.50 Difficult
Arranging data in a way that is easy to understand and analyze. 3.44 Difficult
Managing large data sets. 3.42 Difficult
Creating clear, understandable charts, graphs, or other visual data representations. 3.44 Difficult
Selecting the right statistical tools or methods for your data analysis. 3.32 Moderately Difficult
Understanding or applying complex statistical concepts during analysis. 3.38 Moderately Difficult
Validating your analytical results. 3.27 Moderately Difficult
Accurately interpreting the results of your data analysis. 3.31 Moderately Difficult
Making meaningful conclusions from your data. 3.36 Moderately Difficult
Translating statistical results into actionable insights or recommendations. 3.41 Difficult
Validating your interpretations against the original research or business question. 3.34 Moderately Difficult
Composite Mean 3.39 Moderately Difficult
Legend: 4.21-5.00: Very Competent; 3.41-4.20: Competent; 2.61-3.40: Moderately Competent; 1.81-2.60: Less Competent 1.00-1.80: Not Competent

The table reveals a composite mean of 3.39, categorizing the overall difficulty as "Moderately Difficult." The highest rated difficulty
faced by respondents is "Determining what data to collect for your analysis" with a weighted mean (WM) of 3.53, falling into the
"Difficult" category. Conversely, the least rated problem is "Validating your analytical results" with a WM of 3.27, which is considered
"Moderately Difficult." This distribution of ratings across 12 indicators illustrates that while there are varying degrees of difficulty
encountered in different aspects of statistical analysis, none of the tasks were rated as "Very Difficult" or below "Moderately Difficult,"
indicating a general consensus on the challenges faced but also suggesting that these challenges are not insurmountable.
Remarkably, tasks involving the initial stages of statistical analysis such as determining data to collect, dealing with missing data, and
arranging data present slightly higher difficulties compared to those involved later in the process like validating results or making
meaningful conclusions. This might suggest that the early stages of preparing and managing data are perceived as more challenging,
possibly due to the foundational impact these stages have on the quality of the entire analysis. Furthermore, the transition from
"Difficult" to "Moderately Difficult" across the indicators suggests a nuanced understanding of statistical tasks, where the complexity
of applying statistical methods and interpreting results is acknowledged but viewed with slightly less apprehension.
Clearly, the respondents face significant challenges across various phases of statistical analysis, with particular emphasis on the
preparatory stages. This could indicate a need for enhanced training or resources focused on data collection and management strategies

Kadesale et al. 1059/1061

 Psych Educ, 2024, 17(10): 1057-1061, Document ID:2024PEMJ1631, doi:10.5281/zenodo.10826638, ISSN 2822-4353
Research Article

to mitigate these difficulties. Also, the overall classification of problems as "Moderately Difficult" suggests that while statistical
analysis poses considerable challenges, they are not perceived as overly daunting, potentially reflecting a baseline level of competence
or familiarity among the respondents with statistical methods and their application. This insight could guide the development of targeted
interventions aimed at areas identified as most challenging, thereby improving the efficiency and effectiveness of statistical analysis
practices.
Similarly, the study of Padmavathy (2021) showed that even post-graduate students have below average overall statistical competence.
The study revealed alarmingly low levels of statistical proficiency in postgraduate students. More than 50% demonstrated weaknesses
in grasping and applying fundamental concepts like measuring and interpreting correlation coefficients, employing various parametric
and nonparametric methods. The situation worsens when it comes to interpreting results, with a staggering 81% of students exhibiting
shortcomings in this area. Moreover, a significant 61% struggled with both selecting appropriate statistical methods and explaining
their findings coherently.
Correlation of Competence and Problems Encountered in Performing Statistical Analysis
Table 3 presents the results of a statistical test for a significant relationship between respondents' competence and the problems they
encountered in performing statistical analysis.
Table 3. Correlation of Competence and Problems Encountered in Statistical Analysis
r p Decision on Ho Result

0.187* 0.018 Reject Significant

*Significant at p<0.05 (two-tailed)

The correlation analysis between competence in statistical analysis and the level of problems encountered yields a correlation
coefficient (r) of 0.187, which is significant at the p-value of 0.018. This significance is determined under the condition that the p-value
is less than 0.05, as indicated by the asterisk marking the correlation as significant in a two-tailed test. The decision to reject the null
hypothesis (Ho) suggests that there is a statistically significant relationship between these two variables. However, the correlation
coefficient of 0.187 indicates a weak positive correlation. This means that as competence in statistical analysis increases, the level of
problems encountered slightly increases as well, though the strength of this relationship is not strong.
This result may seem counterintuitive at first glance since one might expect that higher competence in statistical analysis would
correlate with fewer problems encountered. However, the weak positive correlation could indicate several underlying dynamics. For
example, individuals with higher competence might be undertaking more complex analyses, which inherently come with more
challenges and problems. Alternatively, those with greater competence may have a higher awareness of the problems encountered in
statistical analysis, leading to more accurate reporting of these issues compared to less competent individuals who might not fully
recognize or articulate their difficulties.
Interpreting these findings, it is important to consider the context in which statistical analysis is being performed and the nature of the
problems encountered. The significance of the correlation, despite its weak strength, highlights the intricate relationship between
competence and challenges faced in statistical analysis. It suggests that enhancing statistical competence does not necessarily eliminate
problems but may change the nature of the challenges encountered. This insight is crucial for teachers and professionals in developing
strategies to improve statistical analysis skills, indicating that alongside competence development, there should be a focus on problem-
solving skills and strategies to navigate the complexities of statistical analysis effectively. On the other hand, Stanisavljevic et al. (2018)
reported a strong correlation between cognitive competence in statistics and statistical achievement, emphasizing that higher perceived
competence correlates with improved performance. This contrast implies that while increased competence in statistics might marginally
raise the problems encountered, it more significantly enhances overall academic success, underscoring the multifaceted nature of
learning and performance in statistical education.
Conclusion
The results of this study suggest that the respondents generally possess a commendable level of competence in statistical analysis,
signifying a "Competent" proficiency. However, there is a need for improvement in the execution of chi-square tests, which received
a moderately competent rating. Simultaneously, the respondents encountered challenges in statistical analysis, particularly in
determining relevant data to collect. These findings imply the need for targeted interventions to enhance competence in specific areas,
such as chi-square tests. Moreover, providing support to address data collection and analysis challenges is crucial. These interventions
can ultimately lead to the developing a more robust aptitude for statistical analysis among the respondents, which is vital for research
and decision-making processes.
In the light of the findings and conclusions drawn, it is recommended that there is a need to enhance senior high school students’
competence in performing statistical analysis by providing specialized training programs or workshops focused on improving
competence to address the problems they encountered in performing statistics in their research work. Establishing a resource center or

Kadesale et al. 1060/1061

 Psych Educ, 2024, 17(10): 1057-1061, Document ID:2024PEMJ1631, doi:10.5281/zenodo.10826638, ISSN 2822-4353
Research Article

support system where students can seek guidance and assistance when encountering challenges in statistical analysis wherein, they can
access to statistical software tutorials, expert consultation, and online forums for knowledge sharing. Additionally, implementing a
progressive training approach that considers the observed correlation between competence and challenges.

References
Anggara, B., Priatna, N., & Juandi, D. (2018, May). Learning difficulties of senior high school students based on probability
understanding levels. In Journal of Physics: Conference Series (Vol. 1013, No. 1, p. 012116). IOP Publishing.
Ashaari, N. S., Judi, H. M., Mohamed, H., & Wook, M. T. (2011). Student's attitude towards statistics course. Procedia-Social and
Behavioral Sciences, 18, 287-294.
Bucar, J. (2022). Teachers and Students’ Readiness in Conducting School-Based Research. Psychology and Education: A
Multidisciplinary Journal, 4(3), 267-280. http://bit.ly/3H37M73
Calma, J. D., Salvador, I. G. O., & Supan, A. M. (2022). Knowledge and Attitude towards Statistics and Probability of Senior High
School Students. Asia Pacific Journal of Educational Perspective, 9(1).
Coomans, M., Peeters, M., Koekkoek, J., Reijneveld, J., Taphoorn, M., & Dirven, L. (2020). Research objectives, statistical analyses
and interpretation of health-related quality of life data in glioma research: a systematic review. Cancers, 12(12), 3502.
https://doi.org/10.3390/cancers12123502
Desamparadoa, C. G. A., Mendozab, S. J., Minguitoc, T. K., & Monevad, J. C. Stress Levels Among the Senior High School Students
in Practical Research 2.
Dumale, C., & Gurat, M. (2023). Grade 12 Students’ Retention in Statistics and Probability amidst Covid-19.
Elder, A. (2023). Statistics Attitudes After Using Guided Project-Based Learning As An Andragogical Strategy In A Graduate Statistics
Course. Statistics Education Research Journal, 22(3), 4-4.
Grove, S. K. (2018). Understanding Statistics in Research. Understanding Nursing Research E-Book: Building an Evidence-Based
Practice, 292.
Kandeel, R. A. A. (2019). Students' academic difficulties in learning a statistics and probability course: The instructors' view. Journal
of Education and Practice, 10(9), 43-52. https://doi.org/10.7176/JEP/10- 9-05
Murphy, K. R. (2021). In praise of Table 1: The importance of making better use of descriptive statistics. Industrial and Organizational
Psychology, 14(4), 461-477.
Padmavathy, R. D. (2021). Assessing the Statistical Competency among University level Postgraduates. International Journal of
Mechanical Engineering. http://tinyurl.com/3v4cxun8
Risqi, E. N., & Rini Setianingsih. (2021). Statistical Literacy Of Secondary School Students In Solving Contextual Problems Taking
Into Account The Initial Statistical Ability . Pi Mathematics Education Journal, 4(1), 43–54. https://bit.ly/48qSzZg
Ruz, J. O., & Domanais, M. (2022). Design, Development And Validation Of A Readiness Test For Statistics And Probability. Ioer
International Multidisciplinary Research Journal.
Tabuena, A. C., & Hilario, Y. M. C. (2021). Research data analysis methods in addressing the K-12 learning competency on data
analysis procedures among senior high school research courses. International Journal of Recent Research and Applied Studies, 8(3), 1.
Affiliations and Corresponding Information
Arneil V. Kadusale
BIT International College, Tagbilaran – Philippines
Jimmy D. Bucar
Bilar National High School
Department of Education – Philippines
Victor L. Ompad
Zosimo E. Fabroa Memorial National High School
Department of Education – Philippines
Renalyn S. Bohol
Pilar National High School
Department of Education – Philippines

Kadesale et al. 1061/1061