TERM PROJECT

TERM PROJECT

Term Project

Write up a two page maximum overall description of the data set including skewness of appropriate variables, one frequency polygon, and one comparison using two levels of an independent variable with a box and whisker plot. Also include the following table related to your new variables within your two pages.

The purpose of this paper is to examine the association of self-efficacy to gender, GPA and hours worked for students enrolled in a community college science online class. Table 1 shows the variables of interest. Descriptive statistics of Self-Efficacy is presented in table 2. The statistics table tells several interesting things about the distribution of Self-Efficacy, starting with the five-number summary. The center of the distribution can be approximated by the median (or second quartile) 68.0, and half of the data values fall within 7.75 units, the interquartile quartile range. In addition, the extreme values are 47.0 and 84.0, the minimum and maximum. The mean is approximately equal to the median, suggesting that the distribution is approximately symmetric. This is confirmed by the small negative skewness (-0.241), which shows that distribution of Population has balanced tails. That is, the distribution is symmetric, with some distant values in a positive direction and some in negative direction from the center of the distribution. The small positive kurtosis tells that the distribution of Self-Efficacy is normally peaked. Figure 1 depicts the overall shape of the distribution of Self-Efficacy, which is very close to normal distribution.

Table 3, 4, and 5 present the descriptive statistics of Self-Efficacy by Gender, GPA, and Working Hours. There does not seem any difference in Self-Efficacy of male (67.5) and female (68.7). Further, the average values of Self-Efficacy increase with the higher level of GPA and Working Hours. Box Plot (Figure 2) shows that there is a large variability present in female Self-Efficiency than male. However, there are extreme values and outliers present in male Self-Efficiency. Similarly, there is a large variability present in the GPA level 3 (3.0-3.5) and many extreme values and outliers present in level 4 (3.5-4.0). The large variability and outliers may violate the assumption of homogeneity.

Table 1: Variable Description

Type of variable

Name of Variable

Description of Variable

Number of levels of variable

Interval

Self-Efficacy

Self-Efficacy for students enrolled in a community college science online class

-

Nominal

Gender

Students' Gender

2

Ordinal

(Grouped GPA)

GPA

Students' GPA

5

Ordinal

(Grouped Working Hours)

Working Hours

Science Class Working Hours

4

Table 2: Self-Efficacy

Descriptives

Self-Efficacy

Statistic

Mean

67.8929

95% Confidence Interval for Mean

Lower Bound

65.9232

Upper Bound

69.8626

5% Trimmed Mean

68.0000

Median

68.0000

Variance

54.097

Std. Deviation

7.35509

Minimum

47.00

Maximum

84.00

Range

37.00

Interquartile Range

7.75

Skewness

-.241

Kurtosis

.374

Std. Error

Mean

.98287

Skewness

.319

Kurtosis

.628

Figure 1: Self Efficacy

Table 3: Self-Efficacy by Gender

Descriptives

Gender

FEMALE

MALE

Self-Efficacy

Statistic

Mean

67.5854

68.7333

95% Confidence Interval for Mean

Lower Bound

65.1141

65.3944

Upper Bound

70.0566

72.0722

5% Trimmed Mean

67.7046

68.7037

Median

68.0000

68.0000

Variance

61.299

36.352

Std. Deviation

7.82935

6.02929

Minimum

47.00

57.00

Maximum

84.00

81.00

Range

37.00

24.00

Interquartile Range

10.50

4.00

Skewness

-.264

.265

Kurtosis

.169

1.133

Std. Error

Mean

1.22274

1.55676

Skewness

.369

.580

Kurtosis

.724

1.121

Table 4: Self-Efficacy by GPA

Descriptives

GPA

0-2.0

2.5-3.0

3.0-3.5

3.5-4.0

Self-Efficacy

Statistic

Mean

60.5000

68.9333

68.1818

67.4706

95% Confidence Interval for Mean

Lower Bound

16.0283

67.3886

63.9920

63.7536

Upper Bound

104.9717

70.4781

72.3716

71.1876

5% Trimmed Mean

.

68.9259

68.4444

67.4673

Median

60.5000

69.0000

68.5000

68.0000

Variance

24.500

7.781

89.299

52.265

Std. Deviation

4.94975

2.78944

9.44980

7.22943

Minimum

57.00

64.00

47.00

54.00

Maximum

64.00

74.00

84.00

81.00

Range

7.00

10.00

37.00

27.00

Interquartile Range

.

3.00

18.00

8.50

Skewness

.

.466

-.188

-.328

Kurtosis

.

.077

-.439

.012

Std. Error

Mean

3.50000

.72023

2.01470

1.75340

Skewness

.

.580

.491

.550

Kurtosis

.

1.121

.953

1.063

Table 5: Self-Efficacy by Working Hours

Descriptives

Working Hours

Not Employed

1-19 hours per week

20-34 hours per week

35 or more hours per week

Self-Efficacy

Statistic

Mean

64.7143

65.0000

67.4545

70.2692

95% Confidence Interval for Mean

Lower Bound

60.1611

59.7746

62.5696

67.4279

Upper Bound

69.2675

70.2254

72.3395

73.1105

5% Trimmed Mean

64.6825

65.2778

67.1162

70.4957

Median

64.0000

67.0000

67.0000

69.5000

Variance

24.238

67.636

52.873

49.485

Std. Deviation

4.92322

8.22413

7.27136

7.03453

Minimum

59.00

47.00

57.00

55.00

Maximum

71.00

78.00

84.00

81.00

Range

12.00

31.00

27.00

26.00

Interquartile Range

9.00

9.75

4.00

9.00

Skewness

.123

-.934

.892

-.412

Kurtosis

-2.233

1.184

2.179

-.273

Std. Error

Mean

1.86080

2.37410

2.19240

1.37958

Skewness

.794

.637

.661

.456

Kurtosis

1.587

1.232

1.279

.887

Figure 2: Self-Efficacy by Gender (Box Plot)

Figure 3: Self-Efficacy by GPA (Box Plot)

Figure 4: Self-Efficacy by Working Hours (Box Plot)

Using your data, run two cross tabs and chi-square analysis for two sets of appropriate ...