Comparative Sensitivity Performance of the Discriminant Function and Logistic Regression under Different Training and Test Samples for Predicting Birth Outcomes

Main Article Content

K. A. Asosega
K. Opoku-Ameyaw
D. Otoo
M. K. Mac-Ocloo
R. Ayinzoya

Abstract

Population increases with time through birth, and researchers have often used either Logistic regression model or Discriminant analysis to study and classify birth outcomes. In this paper, the authors sought to investigate the sensitivity of the two methods used separately to explain and classify birth outcomes under different training and test samples. Out of 5000 birth outcomes data comprising of 1250 stillbirth cases and 3750 live births and with four test samples (50%, 40%, 30% and 25%). The Discriminant Analysis averagely correctly classified 89.8% of birth outcome cases compared to 82.4% for the logistic regression. The Discriminant analysis on the average correctly predicted 94.2% of live births compared to 83.1% for the Logistic regression. On stillbirth, 75.7% and 80.9% success rates were recorded for Discriminant Analysis and Logistic regression respectively. All predictors (Maternal Age, Gestational period, fetus weight, parity and Gravida) were statistically significant (p-value < 0.01) in determining birth outcomes of pregnancies in both methods. The results showed that, both techniques are almost similar in predicting birth outcome. However, the Discriminant analysis is preferred for the 25% and 50% test samples whiles, the logistic regression performed well under the 30% and 40% test sample data.

Keywords:
Classifications, sensitivity, performance, logistic regression, birth outcomes

Article Details

How to Cite
Asosega, K. A., Opoku-Ameyaw, K., Otoo, D., Mac-Ocloo, M. K., & Ayinzoya, R. (2020). Comparative Sensitivity Performance of the Discriminant Function and Logistic Regression under Different Training and Test Samples for Predicting Birth Outcomes. Asian Journal of Probability and Statistics, 6(3), 47-60. https://doi.org/10.9734/ajpas/2020/v6i330163
Section
Original Research Article

References

Froen JF, Cacciatore J, McClure EM, Kuti O, Jokhio AH, Islam M. Stillbirths: Why they matter. Lancet. 2011;377:1353±66.

Available:https://doi.org/10.1016/S0140-6736 (10)62232-5

[PMID: 21496915]

World Health Organization. Department of maternal, newborn, child and adolescent health (MCA): progress report 2014–15. World Health Organization; 2016.

Vinolia R, Bant DD. A study on the major risk factors of stillbirth in the rural areas of Dharwad district: A prospective study. International Journal of Community Medicine and Public Health. 2018;5 (6):2232-2236.

McClure EM, Pasha O, Goudar SS, Chomba E, Garces A, Tshefu A, Moore J. Epidemiology of stillbirth in low‐middle income countries: A Global Network Study. Acta obstetricia et gynecologica Scandinavica. 2011;90(12):1379-1385.

Lawn JE, Blencowe H, Pattinson R, Cousens S, Kumar R, Ibiebele I, Lancet's Stillbirths Series Steering Committee. Stillbirths: Where? When? Why? How to make the data count? The Lancet, 2011;377 (9775):1448-1463.

Bendon RW. Review of some causes of stillbirth. Pediatric and developmental pathology. 2001;4(6): 517-531.

Gardosi J, Madurasinghle V, Williams M, Malik A, Francis A. Maternal and fetal risk factors for stillbirth, population based study. British Medical Journal; 2013, 346: f108.
Available:https://doi.org/10.1136/bmj.f108
[PMID: 23349424]

Gordon A, Rayes-Greenow C, Mc Geechan K, Morris J and Heather J. Risk factors for antepartum Stillbirth and the influence of maternal age in New South Wales, Australia, a population based study. Bio Medical Central Pregnancy and Childbirth. 2013;13:12.

Gordon A, Raynes-Greenow C, Bond D, Morris J, Rawlinson W, Jeffery H. Sleep position, fetal growth restriction, and late-pregnancy, stillbirth: The Sydney stillbirth study. Obstetrics & Gynecology. 2015;125(2):347-355.

Lin Wang and Xitao Fan 1999. Comparing linear discriminant function with logistic regression for two groups classification, problem: Journal of Experimental Education. 1999, 67.

Balogun OS, Balogun MA, Abdulkadir SS, Jibasen DA. Comparison of the performance of discriminant analysis and the logistic regression methods in classification of drug offenders in Kara State. International Journal of Advanced Research. 2014;2(10):280-286.

Hyunjoon K, Zheng G. Predicting restaurant bankruptcy: A logit model in comparison with discriminant model; Tourism and Hospitality Research Journal. 2010;10:171-187.

Balogun OS, Akingbade TJ, Oguntunde PE. An assessment of the performance of discriminant analysis and the logistic regression methods in classification of mode of delivery of an expectant mother. Mathematical Theory and Modeling. 2015;5:147-154.

Zahra SH, Naser M, Leila SH, Parisa N. Prediction of depression in cancer patients with different classification criteria, Linear Discriminant Analysis versus Logistic Regression. Global Journal of Health Science. 2016;8(7):41-46.

Hubert M, Van Driessen K. Fast and robust discriminant analysis. Computational Statistics & Data Analysis. 2004;45(2):301-320.

Poulsen J, French A. Discriminant function analysis. San Francisco State University: San Francisco, CA; 2008.

Tabachnick BG, Fidell LS. Using multivariate statistics. Northridge. Cal.: Harper Collins; 1999.

Young B. Quadratic versus linear rules in predictive discriminant analysis. Mid-South Educational Research Association, 22nd, New Orleans, LA; 1993.

Johnson RA, Wichern DW. Applied multivariate statistical analysis, 6th Edition. Prentice-Hall, London; 2007.

Box GE. A general distribution theory for a class of likelihood criteria. Biometrika, 1949;36(3/4): 317-346.

Huberty CJ. Issues in the use and interpretation of discriminant analysis. Psychological Bulletin, 1984;95(1):156.

Agresti A. An introduction to categorical data analysis, John Wiley & Sons. Inc., Publication; 1996.

Aldrich J. RA fisher and the making of maximum likelihood 1912-1922. Statistical Science. 1997;12 (3):162-176.

Long JS. Regression models for categorical and limited dependent variables. Advanced Quantitative Techniques in the Social Sciences. 1997;7.

Cook NR. Statistical evaluation of prognostic versus diagnostic models: Beyond ROC curve. Clim Chem. 2008;54(1):17-23.

Zhou XH, Obuchowski NA, Obushcowski DM. Statistical methods in diagnostic medicine. Wiley & Sons: New York; 2002.