Statistical Analysis

Table of Contents

Question 1 A3

Research Example 13

Research Example 23

Research Example 33

Research Example 43

Question 1 b3

Question 2 A4

Question 2 B4

Question 2 C5

Question 2 D5

Question 3 A7

Question 3 B8

Question 3 C8

Question 49

Question 5 A9

Question 5 B11

Question 611

Question 7a12

Question 7b12

Question 7c12

Question 7d12

Question 8a12

Question 8b12

Question 8c12

Question 8d12

Question 8e13

Question 913

Question 1013

Question 1114

Question 1214

Question 1314

Question 1414

Question 1515

Question 1615

Question 1715

Question 18 A15

Question 18 B16

Question 18 C16

Question 18 D16

Question 18 E16

Question 18 F17

Multiple Choice Questions17

Question #17

Question 1917

Question 2017

Question 2117

Question 2217

Question 2317

Question 2417

Question 2517

Question 2617

Question 2718

Question 2818

Question 2918

Question 3018

Question 3118

Question 3218

Question 3318

Question 3418

Question 3518

Question 3618

Question 3718

Question 3818

Question 3918

Question 4018

Question 4118

Question 4218

Question 4318

Question 4418

Statistical Analysis

Question 1 A

Research Example 1

GroupNominal

Pretest Score Ordinal

Research Example 2

Grade LevelOrdinal

Pretest ScoreRatio

Research Example 3

Subject NumbersInterval

Family Alcohol ProblemNominal

Self Reported Alcohol-Related ProblemsRatio

Research Example 4

Average Time (Sec.) to EscapeRatio

Question 1 b

If we are given the access to the entire population of Grade 3 in research 2 problem, the mean of that data will still be considered a parameter as we have the data on all the grade 3 students of that school, i.e. entire population of grade 3 of that school. However if go on generalizing that the mean represents the score of grade 3 students of all schools in the district, this mean will be considered a statistic.

The mean of 100, provided to us will constitute a parameter for any sample taken out from the grade 3 population of that school, but will be considered a sample if it will be used for statistical analysis of all schools.

Question 2 A

Using data from Research Problem 1 (pretest scores), Table 1 shows the cumulative frequency distribution, real and apparent limits, cumulative frequency and percentiles.

Table 1: Grouped Frequency Distribution of Research Problem 1, Pretest Scores.

Apparent Limits

Real Limits

Frequency

Cumulative Frequency

Percentiles

1-2

0.5-2.5

4

4

11%

3-4

2.5-4.5

17

21

58%

5-6

4.5-6.5

12

33

92%

7-8

6.5-8.5

3

36

100%



Question 2 B

Grouped Frequency Distribution of Pretest Scores of Research Problem 2 are illustrated in Table 2.

Table 2: Grouped Frequency Distribution of Research Problem 2, Pretest Scores

Apparent Limits

Real Limits

Frequency

Cumulative Frequency

Percentiles

75-79

72.5-81.5

1

1

3%

80-84

77.5-86.5

1

2

7%

85-89

82.5-91.5

2

4

13%

90-94

87.5-96.5

5

9

30%

95-99

92.5-101.5

4

13

43%

100-104

97.5-106.5

5

18

60%

105-109

102.5-111.5

3

21

70%

110-114

107.5-116.5

4

25

83%

115-119

112.5-121.5

2

27

90%

120-124

117.5-126.5

2

29

97%

125-129

122.5-131.5

1

30

100%

Question 2 C

The class interval is selected so that not only a large amount of data can be grouped together but also to distribute the data granularity among the different intervals. The scale of data in Question 2a was not very large and it was incrementing with a value of 1, so the interval of 1 was appropriate as it grouped the data in such a way that it became easy to know how many people responded to which answer.

The interval of 5 in Question 2b helped the data to be represented adequately and developed a nice spread. The data didn't accumulate in one area and an interval which is too large would have done the same. If the interval would had been smaller than 5, there would had been too many classes in which data would had been divided. Hence the interval of 5 and starting the class width

Question 2 D

Figure 1: Histogram of Q2 A

Figure 2: Frequecny Polygon Q2 B

Figure 3: Histogram of Q2 B

Figure 4: Histogram of Q2 B

Question 3 A

Table 3: Mean, Median and Mode of the three groups

Group 1 (escape)

Group 2 (no-escape)

Group 3 (control)

30

55

26

28

41

30

25

43

23

33

54

22

29

58

29

32

25

30

31

43

25

27

50

21

Mean

29.375

46.125

25.75

Median

29.5

46.5

25.5

Mode

No mode

43

30

There were no repeated ...