THE TRAGEDY OF TITANIC: A LOGISTIC REGRESSION ANALYSIS

Dina Ahmed Mohamed Ghandour 1 and May Alawi Mohamed Abdalla 2 . 1. Lecturer at University of Medical Sciences & Technology, Faculty of Business Administration, Khartoum, Sudan, DBA Candidate. 2. Pharmacist at Samasu Medical & Educational Services, Khartoum Sudan, and currently is a DBA Candidate. ...................................................................................................................... Manuscript Info Abstract ......................... ........................................................................ Manuscript History

The sinking of Titanic is one of the most infamous shipwrecks in history. On April 15, 1912, during her maiden voyage, the Titanic sank after colliding with an iceberg, killing 1,502 of the 2,228 passengers and crew. This sensational tragedy shocked the international community and motivated the adoption of better maritime safety regulations. However there are many reasons that the shipwreck led to such loss of life and there was some elements of luck involved in surviving the sinking as some groups of people were more likely to survive than others. The main aim of this research is to identify the Impact of gender, passenger class, Accompany, age on a person's likelihood of surviving the shipwreck. Secondary data was used as the main data collection tool and it was analyzed by fitting a logistic regression model using a statistical package, SPSS.
Findings of this study showed that some passenger groups were more likely to survive than others, with respect to certain demographic characteristic and whether the passenger was traveling in the first, second or third class.

ISSN: 2320-5407
Int. J. Adv. Res. 5(6), 1454-1465 1455 regulations. Titanic only carried enough lifeboats for 1,178 people-slightly more than half of the number on board, and one third of her total capacity.(3) After leaving Southampton on 10 April 1912, Titanic called at Cherbourg in France and Queenstown (now Cobh) in Ireland before heading west to New York. On 14 April, four days into the crossing and about 375 miles (600 km) south of Newfoundland, the ship hit an iceberg at 11:40 p.m. ship's time. The collision caused the ship's hull plates to buckle inwards along its starboard (right) side and opened five of its, sixteen watertight compartments to the sea; it could only survive four flooding. Meanwhile, passengers and some crew members were evacuated in lifeboats, many of which were launched only partially loaded. A disproportionate number of men were left aboard because of a "women and children first" protocol for loading lifeboats. At 2:20 a.m., it broke apart and foundered-with well over one thousand people still on board. (4) The disaster was greeted with worldwide shock and outrage at the huge loss of life and the regulatory and operational failures that had led to it. Public inquiries in Britain and the United States led to major improvements in maritime safety. (5) One of their most important legacies was the establishment in 1914 of the International Convention for the Safety of Life at Sea (SOLAS), which still governs maritime safety today. Additionally, several new wireless regulations were passed around the world in an effort to learn from the many missteps in wireless communications-which could have saved many more passengers. The below table explores Titanic profile:

Objective of the study:-
The General Objective of this research is to: • Explain the Impact of gender, passenger class, Accompany, age on a person's likelihood of surviving the shipwreck.

Methodology:-
This study is based on analytical and quantitative methods. Assumption#3:-There must be one or more independent variables, which can be either continuous (i.e., an interval or ratio variable) or categorical (i.e., an ordinal or nominal variable).

VIF (Variance Inflation Factor): Collinerity exist if VIF > 5
Assumption#5:-The categories (groups) must be mutually exclusive and exhaustive; a case can only be in, one group and every case must be a member of one of the group.  To test the significance of the coefficient (intercept) we set the following:-Ho: the intercept = 0 Ha: the intercept = 0 Sig=.000 < α = .05 So reject H0 and accept the Ha, which means that the intercept doesn't pass through the origin 1.
The null model is: Logit (P) = = -0.481  Table:-The Hosmer & Lemeshow Test is a commonly used test for assessing the goodness of fit of a logistic regression model but has a low power in assessing the significance of the model: Main problems of Hosmer & Lemeshow:- The none significant chi-square is indicative of good fit of the model in case of small sample size.  Even with good fit the test may be significant if sample size is large  Even with poor fit the test may not be significant if sample size is small

Block 1: Method = Enter
Illustration to the above Table:-The overall predictive capacity increased from 61.8% to 78% Important terms in the Table:-Sensitivity percentage of occurrences correctly predicted 345/500=69% Specificity percentage of nonoccurrence's correctly predicted 680/809=84%