Relationships Research Methodology, Data Analysis Essay Sample

The purpose of the research was to determine if a relationship exists between the number of general aviation flight hours and number of midair collisions and NMACs. Data would be collected from various centers to establish whether there exists any relationship between the number of flight hours and the occurrence of mid-air collisions and NMACs ( near mid-air collisions). With this data, we sought to establish the correlation with a simple linear regression analysis that was performed in order to test the null hypothesis that the number of flight hours is not a significant contributor to the total number of midair collisions and near midair collisions. The linear regression was most appropriate to test data with only two variables.

Is your time best spent reading someone else’s essay? Get a 100% original essay FROM A CERTIFIED WRITER!

Order now

Variables

There were only two variables used in the research to conduct the correlation analysis with a simple linear regression. The first variable is the total number of general aviation flight hours and the second variable is the combined total number of midair collisions and NMACs. Both variables were classified by the year but the number of flight hours helped in making the predications. The dependent variable, number of mid-air collisions and NMACS, would help establish whether the number of flights affected the occurrence of NMACs. A scatter plot would help establish whether there is any trend observable between the number of flight hours and the occurrence of midair collisions and NMACs. When plotting the numbers on the scatterplot diagram, general aviation flight hours are placed on the X-axis and midair collisions and NMACs are placed on the Y-axis. If there is an observable pattern, a curve or line, then there is a relationship between the number of midair collisions and NMACs and number of flight hours. If there is no observable pattern, then there is no relationship between the two.

Data Collection

Data collection was accomplished through descriptive research by identifying and obtaining quantitative information. The total number of general aviation flight hours were collected from the General Aviation Manufacturers Associations (GAMA) 2014 statistical data book and industry outlook publication. Located in the publication under Chapter 2, section 2.4, was a list of estimated total hours in the United States ranging from calendar year 1980 to 2013. For the research, only the numbers from 2005 to 2013 were used with the exception of 2011 that listed the flight hours as being unavailable for that year. Other publications from the NTSB and FAA were also reviewed to attempt to find the total flight hours for 2011, but the flight hours were unavailable on all reports.

The NTSB receives information of all airline accidents that occur and establishes the cause. Over the years, NTSB has provided information for most airplane accidents. Their reports contained a list of mid-air crashes and NMACs and the probable cause of each. Information acquired from this report would put into consideration other factors that might have led to the occurrence of the NMACs. Examining the NTSB report would help establish the alleged cause of NMACs and whether the number of flight hours contributed to the alleged cause.

The other data for this research was obtained from the submissions in the Civil Aviation Safety Authority (CASA), which receives all the data regarding MACs and NMACs. These reports contained important information that could help establish the number Additional data was collected from the FAA, which has been receiving reports on Pilot, initiated reports on NMACs since 1959. The FAA investigates communications, the existing radar and the interviewed the cockpit members regarding the NMAC. Apart from that, we also obtained information about the pilots and the cockpit crew involved on the NMACs and MACs.

The total number of midair collisions and NMACs were collected independently and combined once all the data was collected. To obtain the number of midair collisions a search of the NTSBs aviation accident/incident database was performed by calendar year for 2005 to 2013. Search results were narrowed by submitting a query for reports in the United States and with the key word of midair inputted. Each report was then reviewed to analyze the synopsis of the accident, type of aircraft, operation, flight phase, severity, and probable cause. For the number of NMACs a search of the NASAs ASRS database was performed by calendar year from 2005 to 2013. Search results were narrowed by conducting a search for reports by NMAC event type and by federal aviation regulations. Each report was then reviewed to analyze the synopsis of the incident, type of aircraft, flight phase, and probable causes.

Data Analysis

Once the quantitative data was collected and categorized a data analysis was accomplished to test the null hypothesis between the number of general aviation flight hours and number of midair collisions and near midair collisions. The method used was the Pearson product moment correlation, which is an appropriate technique to evaluate a hypothesis between two variables. The Pearsons product correlation would help establish the correlation coefficient between the number of flight hours and NMACs that occur. A correlation coefficient that is close to zero would indicate high correlation between the number of NMACs and flight hours. If the correlation coefficient was not close to zero then there is little or no correlation between the number of NMACs and the number of flight hours. The Pearsons product would give a detailed analysis of the relationship between the number of flight hours and the number of mid-air crashes and NMACs. To obtain the most accurate figures, tables, and results the data analysis program StatCrunch was used to perform the calculations. The program functions by placing the number of general aviation flight hours in the first X variable and number of midair collisions and NMACs being placed in the second Y variable. Then a simple linear regression hypothesis test was executed to produce the results of the analysis. Each of the figures, tables, and results are explained in further detail in the next section.