Home⇛DAVAO RESEARCH JOURNAL⇛vol. 14 no. 2 (2023)

Bridging the gap: A comparative analysis of traditional and neural network regression methods for predicting university entrant performance in SUAST examination

Nikka A Singh | Diether C Montejo

Discipline: environmental sciences

 

Abstract:

In developing countries like the Philippines, access to free and high-quality tertiary education is crucial for better job opportunities. The State University Aptitude and Scholarship Test (SUAST) is used as a college admission examination by Davao Oriental State University (DOrSU). However, the passing rate for SUAST was only 54% for the academic year 2018-2023, and non-passers were still accepted due to policy changes, which undermine the purpose of the examination. This study aimed to identify the factors that influence the performance of university entrants in the SUAST examination using a researcher-made survey questionnaire administered online, utilizing both multiple-layer perceptron neural network (MLPNN) and multiple linear regression analysis (MLR) methods. A sample size of 359 was recommended, and the study found that family income, senior high school general weighted average (SHSGWA), library entry, intrinsic goal, openness and intellect, and behavioral reaction were significant predictors of SUAST exam scores. MLPNN analysis further identified library access and resources, family income, and academic self-belief as the most important predictors of SUAST exam scores, and MLPNN outperformed MLR. This study provides recommendations for DepEd and HEI’s to enhance the preparation and performance of students taking the SUAST exam, such as offering study materials and test-taking strategies, evaluating alternative admission tests, and reviewing the content validity of the questionnaire. The study also suggests looking at other indicators of student readiness for university, such as high school grades and extracurricular activities, and conducting future research on the impact of financial aid and scholarships on academic achievement and performance disparities between male and female students.



References:

  1. Abbasi, N., and Ghosh, S. (2020). Construction and   standardization   of   examination anxiety  scale for adolescent  students. International    Journal    of    Assessment    Toolsin Education, 7(4), 522-534.
  2. Bai,  C.  E.,  Chi,  W.,  and  Qian,  X.  (2014).  Do  college          entrance          examination          scores   predict   undergraduate   GPAs?   A    tale    of    two    universities.    China Economic       Review,       30,       632-647.
  3. Çakır,  Y.,  Kırcı,  M.,  and  Güneş,  E.  O.  (2014, August).    Yield    prediction    of    wheat    in    south-east    region    of    Turkey    by    using  artificial  neural  networks. In 2014 The  Third International  Conference  on Agro-Geoinformatics   (pp. 1-4).
  4. IEEE.Cochran,       W.       G.       (1977).       Sampling       techniques.     john     wiley     &     sons.
  5. Deary,    I.    J.,    Strand,    S.,    Smith,    P.,    and    Fernandes,      C.      (2007).      Intelligence and           educational           achievement.Intelligence,               35(1),               13-21.
  6. Djeddou,  M.,  Zhao,  X.,  Hameed,  I.  A.,  and  Rahmani,   A.   (2021,   August).   Hybrid   Improved             Empirical             Mode             Decomposition  and  Artificial  Neural Network    Model    for    the    Prediction    of     Critical     Heat     Flux     (CHF).     In     International   Conference   on   Nuclear   Engineering    (Vol.     85253,     p.     V002T07A026). American       Society       of       Mechanical Engineers.
  7. Dulock,    M.    V.    (2003).    Research    Design.    The     SAGE     Handbook     of     Human     Resource   Management   (pp.   269-285).   Sage FoundationDuncan,   G.   J.,   and   Murnane,   R.   J.   (Eds.).   (2011).   Whither   opportunity?:   Rising   inequality,       schools,       andchildren’s       life  chances.  Russell  Sage  Foundation.
  8. Eisa,   A.   A.,   and   Al-Khalifa,   H.   S.   (2018).   Prediction    of    academic    success    for    university   students   using   multilayer   perceptron    neural    network.    Journal of Information Science  and   Engineering, 34(1), 205-215.
  9. Elliot,  A.  J.,  and  Harackiewicz,  J.  M.  (1996).  Approach               and               avoidance               achievement      goals      and      intrinsic      motivation:    A    mediational    analysis.    Journal     of     personality     and     social     psychology, 70(3), 461.
  10. Farkas,  D.,  Osterweil,  S.,  and  Greenberg,  J.  (2021).    Library    use    and    academic    performance  among  college  students.  Journal    of    Academic    Librarianship, 47(3), 102282.
  11. Fazeli,  S.,  Mirbagheri,  A.,  and  Naeini,  M.  R.(2020).     A     comparative     study     of     artificial  neural  network  models  for predicting      academic      achievement.      Computers   &   Education,   146,   103763.  
  12. Fowler,     S.     (2007).     The     motivation     to     learn   online   questionnaire   (Doctoral   dissertation,    University    of    Georgia).
  13. Fox,     J.     (2019).     Regression     diagnostics:     An    introduction.    Sage   publications.
  14. Gignac,    G.    E.,    and    Bates,    T.    C.    (2017).    Brain   volume   and   intelligence:   The   moderating      role      of      intelligence      measurement      quality.      Intelligence, 64, 18-29.
  15. Hess,     R.     K.,     and     McAvoy,     R.     (2018).     Socioeconomic     status     and     college     entrance    exams:    A    review    of    the    literature. Educational           Policy,           32(5), 657-684.
  16. Hosseini,       M.,       Khezerloo,       M.,       and       Khojastehpour,  M.  (2021).  An  Analysis  of  Influential  Factors  on  Tourists’ Hotel  Selection  Using  the  Artificial Neural    Network    Approach.    Journal of    Travel    Research,    60(2),    275-292.
  17. Huang,  G.  H.,  and  Anderson,  R.  E.  (2020).  The     predictive     validity     of     high     school    grades    and    test    scores    in    college       admissions.       Journal       of       College       Admission,       249,       26-34.
  18. Hyman,   J.   (2017).   ACT   for   all:   The   effect   of    mandatory    college    entrance    ex-ams     on     postsecondary     attainment     and       choice.       Education       Finance       and          Policy,          12(3),          281-311.
  19. Katz,  I.,  and  Assor,  A.  (2007).  When  choice  motivates    and    when    it    does    not.    Educational        Psychology        Review,        19(4), 429-442.
  20. Kim,  K.  H.,  and  Hull,  M.  F.  (2015).  Effects  of        motivation,        ACT/SAT,        GPA,        and     SES     on     college     choice     for     academically        advanced        students        and  other  students.  World  Journal  of  Educational    Research    (Online),    2(2).
  21. Koenig,   K.   A.,   Frey,   M.   C.,   &   Detterman,   D.     K.     (2008).     ACT     and     general     cognitive           ability.           Intelligence,36(2), 153-160.
  22. Kuncel,  N.  R.,  Credé,  M.,  and  Thomas,  L.  L.  (2005).   The   validity   of   self-reported   grade    point    averages,    class    ranks,    and  test  scores:  A  meta-analysis  and  review   of   the   literature.   Review   of   educational     research,     75(1),     63-82.
  23. Kutner,   M.   H.,   Nachtsheim,   C.   J.,   Neter,   J.,    and  Li,  W.  (2005).  Applied  linear  statistical         models.         McGraw-hill.
  24. Langdon,   C.   K.   (2021).   College   admissions   and    the    predictive    value    of    high    school    GPA:    A    systematic    review.    Educational     Research     Review,     34,     100386.
  25. Letukas,     L.     (2016).     College     admissions     testing:         Current         understanding         and     future     implications.     Sociology Compass, 10(1), 98-106.
  26. Li,   J.,   Zhang,   C.,   Sun,   Y.,   and   Wang,   Y.   (2020).   Comparison   of   MLPNN   and   MLR    in    forecasting    soil    moisture    content. Journal    of    Earth    Science,31(5), 956-962.
  27. Paris,     J.     and     Heiser,     R.     (2022).     An     examination       of       the       predictive       validity    of    a    measure    of    college    admissions     applicants’     attributions     of    success    and    failure.    Journal    of    Postsecondary         Student         Success,         1(4), 112-140.
  28. Patel,   N.   V.,   and   Patel,   D.   R.   (2019).   The   predictive      validity      of      Advanced      Placement           and           International           Baccalaureate      examination      scores      for    college    admission    test    scores.    Journal of College Admission, 244, 12-20.
  29. Pekrun,   R.,   Elliot,   A.   J.,   and   Maier,   M.   A.    (2009).    Achievement    goals    and    achievement     emotions:     Testing     a     model   of   their   joint   relations   with   academic     performance.     Journal     of     educational    Psychology,    101(1),    115.
  30. Poropat, A. E. (2009). A    meta-analysis    of  the  five-factor  model  of  personality and academic  performance.  Psychological    bulletin,    135(2),    322.
  31. Putwain,  D.  W.,  Woods,  K.  A.,  and  Symes,  W.   (2010).   Personal   and   situational   predictors  of  test  anxiety  of  students  in          post-compulsory          education.          British       Journal       of       Educational       Psychology,              80(1),              137-160.
  32. Reardon,  S.  F.,  Kalogrides,  D.,  and  Shores,  K.   (2019).   The   geography   of   racial/ethnic     test     score     gaps.     American Journal  of  Sociology,  124(4),  1164-1221.
  33. Reyes,     J.     D.     C.     (2019).     Mathematical     Performance   of   Freshman   Students’   vis-à-vis:      Admission      test      Results.      International    Journal    of    Humanities    and            Education            Development            (IJHED), 1(3), 115-127.
  34. Rojstaczer,     S.,     and     Healy,     C.     (2012).     Where   A   is   ordinary:   The   evolution   of   American   college   and   university   grading,           1940-2009.           Teachers College         Record,         114(7),         1-23.
  35. Pontes-Neto,   O.   M.,   Silva,   G.   S.,   Feitosa,   M.   R.,   De   Figueiredo,   N.   L.,   Fiorot   Jr,  J.  A.,  Rocha,  T.  N.,  and  Leite,  J.  P.  (2008).   Stroke   awareness   in   Brazil:   alarming    results    in    a    community-based   study.   Stroke,   39(2),   292-296.
  36. Shamseldin,   A.   Y.,   O’connor,   K.   M.,   and   Nasr,  A.  E.  (2007).  A  comparative  study  of    three    neural    network    forecast    combination   methods   for   simulated   river  flows  of  different  rainfall—runoff   models.   Hydrological   Sciences   Journal, 52(5), 896-916.
  37. Strayhorn,   T.   L.   (2018).   College   students’   sense     of     belonging:     A     key     to     educational success   for  all  students. Routledge.
  38. Stricker,   L.   J.   (2019).   Motivation   and   test   performance of college-bound students. College  Student  Journal,  53(2),  211-220.
  39. Valverde-Berrocoso,       J.,       Garrido-Arroyo,M.     D.     C.,     Burgos-Videla,     C.,     and     Morales-Cevallos,  M.  B.  (2020).  Trends  in    educational    research    about    e-learning:      A      systematic      literature      review      (2009–2018).      Sustainability,12(12), 5153.
  40. Van  Yperen,  N.  W.,  Blaga,  M.,  and  Postmes,  T.    (2014).    A    meta-analysis    of    self-reported      achievement      goals      and      nonself-report      performance      across      three   achievement   domainsm   (work,   sports,        and        education).        PloS one, 9(4), e93594.
  41. Wu,   T.-T.,   and   Tsai,   M.-J.   (2016).   Applying   artificial    neural    networks    for predicting academic achievement of  college  students. Journal      of      Educational              Technology  & Society, 19(3), 47-60
  42. Yang,  S.  J.,  Lu,  O.  H.,  Huang,  A.  Y.,  Huang,  J.  C.,  Ogata,  H.,  and  Lin,  A.  J.  (2018).  Predicting          students’          academic          performance    using    multiple    linear    regression   and   principal   component   analysis. Journal      of      Information      Processing, 26, 170-176.
  43. Zaidman-Zait, A., and Roth, R. (2015). The BigFive   personality   traits   and   academic   achievement. Journal     of     Research     in           Personality,           56,           21-33.
  44. Zhong,  S.,  Zhang,  K.,  Bagheri,  M.,  Burken,  J.   G.,   Gu,   A.,   Li,   B.,   and   Zhang,   H.   (2021). Machine  learning:    new    ideas and   tools   in   environmental   science   and        engineering.        Environmental Science        &        Technology,        55(19),        12741-12754.

Tools


Copyright © 2024  KITE Digital Educational Solutions |  Exclusively distributed by CE-Logic