Statistics Week 10 Pilot Experience & Aviation Safety Questions

Week 10Examining Relationships (Part 1): Bivariate Correlation
Graded Assignment
This week’s graded assignment is an application of bivariate correlation and involves a fictitious
replication of Bell, Robertson, and Wagner’s (1995) study, which examined the relationship
between pilot experience and aviation safety. Bell et al. defined pilot experience as pilots’ total
flight hours in all aircraft, and they defined aviation safety as scores on the Aviation Safety Index
(ASI), which consisted of five safety-related statements that correspond to behaviors associated
with preflight preparation. The five statements are given below.
1. I do a thorough walk-around inspection of an aircraft before I fly it.
2. I check the weather thoroughly before I fly (even on local flight).
3. I compute fuel requirements with an eye toward a 30- or 45-minute fuel reserve.
4. I use a checklist for interior and exterior inspection of an aircraft.
5. I compute takeoff and landing distances as well as runway lengths at airports of
intended use for each flight.
Respondents were asked to self-assess the degree to which they performed each behavior using a
7-item bipolar adjective scale with “Never” at one end of the scale, which was scored 1, and
“Always” at the other end of the scale, which was scored 7. Thus, aggregate scores could range
from 5 to 35, with higher scores indicating more safety conscious pilots. A fictitious set of data
related to this study is given in the Excel file “Week 10 Graded Assignment Data.” Import this
data set into your statistical software program and do the following (see also the corresponding
Guided Example):
A. Pre-Data Analysis
1. What is the research question and corresponding operational definitions?
2. What is the research methodology/design and why is this methodology appropriate?
3. Conduct an a priori power analysis to determine the minimum sample size needed. Is the
given data set sufficient relative to this minimum sample size? In what way do you think
the size of the given sample will impact the results?
B. Data Analysis
Using the data from the Excel file, conduct a hypothesis test as follows:
1. Formulate the null and alternative hypotheses in symbols and words.
2. Determine the test criteria.
3. Test for the assumptions of correlation. (Note: For outlier analysis, there should be six
outliers using Jackknife distances.)
4. Run the analysis and record the results.
5. Make a decision to reject or fail to reject the null hypothesis and write a concluding
statement.
C. Post-Data Analysis
1. Determine and interpret the effect size, r2.
2. Determine and interpret the power of the study.
3. Determine and interpret the 95% confidence interval.
4. Present at least three plausible explanations for the results.
5. Interpret the findings from a practical perspective.
Y = Maintenance
X = Training
ErrorsPerceptions
38
19
36
20
39
11
28
21
36
17
29
20
29
19
28
22
29
19
36
15
17
25
39
19
14
24
28
17
34
15
29
21
25
18
29
17
30
17
39
20
48
15
31
24
24
20
34
13
28
18
26
17
21
20
26
14
31
19
39
15
37
16
30
21
42
20
27
17
31
20
38
20
33
23
26
17
33
13
27
20
30
20
33
20
40
20
30
18
41
12
38
17
37
43
44
37
42
26
44
31
25
38
31
45
48
43
35
31
29
32
46
26
31
38
49
39
34
40
34
48
22
41
29
43
16
40
17
13
16
21
17
24
10
20
16
16
21
8
13
17
20
20
20
23
18
16
20
22
13
9
21
19
15
18
19
16
21
13
24
18