More Subjects

Statistical Analysis

Name of Student

Name of institution

Descriptive Statistics

N

Minimum

Maximum

Mean

Std. Deviation

Skewness

Statistic

Statistic

Statistic

Statistic

Statistic

Statistic

Std. Error

Age

105

19.0

68.0

29.267

11.8112

1.797

.236

Valid N (listwise)

105

In the above table, we have analyzed the variable age to see the relative descriptive statistics. There are a total of 105 entries for this variable and the average age of the respondents is 29.267 years, whereas standard deviation is 11.81 years. An important statistic of the data is shown under skewness which is higher and shows that the data is not bell shaped and is skewed towards right. The youngest respondent is 19 years old whereas, the oldest respondent is 68 years old. There is not much difference between the minimum value and the mean of data showing less variability in the data as a whole. It is a discrete variable so we used descriptive statistics to analyze it. Mean measures the extent to which values tend to move towards the center whereas, standard deviation shows how far an individual value lies from the mean CITATION Gil07 \l 1033 (Byrne, 2007).

Descriptive Statistics

N

Minimum

Maximum

Mean

Std. Deviation

Skewness

Statistic

Statistic

Statistic

Statistic

Statistic

Statistic

Std. Error

Spending

105

$20.00

$5,000.00

$649.9238

$806.49076

2.911

.236

Valid N (listwise)

105

In the above table, we have shown the descriptive statistics for the variable spending including mean and standard deviation. Average spending of this group is $ 649 and standard deviation is $ 806.5. The mean is a simple average of all values or a measure of central tendency showing the extent to which all values tend to move towards the mean. Standard deviation is a measure of dispersion for the data which shows the distance between each individual value and the mean. Another observation is that there is a low minimum value in the data and its mean is very high showing that there is much variability in the individual values of data. Another important statistic is shown under the head skewness which is almost 3, showing that the data is skewed towards right. The following diagram shows the number of outliers in this data.

Above is the box plot for spending data and shows a large number of outliers in this data. The analysis is disturbed by the presence of these outliers and researcher should make sure that values in data are bound close to each other. In order to void these outliers, similar respondents must be chosen for research so that their responses lie close to each other.

Descriptive Statistics

N

Minimum

Maximum

Mean

Std. Deviation

Skewness

Statistic

Statistic

Statistic

Statistic

Statistic

Statistic

Std. Error

Stereotype

105

.0

1050.0

43.381

124.8080

6.237

.236

Valid N (listwise)

105

A very similar pattern of values can be observed in the variable stereotype which has a lower mean value and a very high value in the maximum column. The skewness statistic is very high for the variable showing that the values are skewed to the right. The average value of stereotype variable is 43 and maximum value is 1050. Standard deviation is also high which shows that there is a considerable distance between the individual values and mean of all values. We can see another interesting relationship between standard deviation and skewness that a higher value of standard deviation is accompanied by a higher standard deviation and vice versa.

Descriptive Statistics

N

Minimum

Maximum

Mean

Std. Deviation

Skewness

Statistic

Statistic

Statistic

Statistic

Statistic

Statistic

Std. Error

Empowerment

105

0.00%

30.00%

5.3619%

6.22205%

1.378

.236

Valid N (listwise)

105

The above table shows descriptive statistics for the variable empowerment with mean 5.36 % and standard deviation of 6.22 %. The difference between minimum and maximum values is not very large suggesting that there will be lesser number of outliers in this data. A lower number in the skewness statistic shows that the majority of data will be closer to mean value CITATION Nic03 \l 1033 (colegrave & Ruxton, 2003).

Gender

Frequency

Percent

Valid Percent

Cumulative Percent

Valid

Female

86

81.9

81.9

81.9

Male

19

18.1

18.1

100.0

Total

105

100.0

100.0

Above table shows the analysis of gender variable, this is a categorical variable which has only two distinct categories. This is the reason we have used the frequencies to analyze this data. There is a very high proportion of females in this study which matches the overall purpose of this study to analyze attitude of people towards gender stereotypes.

Education

Frequency

Percent

Valid Percent

Cumulative Percent

Valid

Associate Degree

6

5.7

5.7

5.7

Bachelor Degree

44

41.9

41.9

47.6

Doctorate Degree

10

9.5

9.5

57.1

High school diploma

3

2.9

2.9

60.0

J.D.

2

1.9

1.9

61.9

Master Degree

16

15.2

15.2

77.1

Some undergraduate courses

24

22.9

22.9

100.0

Total

105

100.0

100.0

The above table shows division of various levels of education. The highest proportion among education is bachelor degree holders who represent 41.9% of all the respondents. This is also a categorical variable so frequencies have been used to assess it. The junior diploma is least followed educational field in these respondents.

Gender * Education Cross tabulation

Count

Education

Total

Associate Degree

Bachelor Degree

Doctorate Degree

High school diploma

J.D.

Master Degree

Some undergraduate courses

Gender

Female

4

34

10

1

2

15

20

86

Male

2

10

0

2

0

1

4

19

Total

6

44

10

3

2

16

24

105

The above table shows an analysis of data using two variables namely gender and level of education. The analysis shows that the highest number of respondents are females who had a graduate degree whereas there are two educational categories responding to males which have no representatives. The responses show that most females agree to the presence of cultural gender stereotypes. This approach looks to be somewhat unbalanced because there are a large number of females in respondents. In order to get a more authenticated result, there should be a much larger sample with an equal representation of both genders.

Gender * Transform Cross tabulation

Count

Transform

Total

Agree

Disagree

Neutral

Somewhat Agree

Somewhat Disagree

Strongly Agree

Gender

Female

25

0

5

26

1

29

86

Male

5

1

1

9

0

3

19

Total

30

1

6

35

1

32

105

The above table shows that a large majority of respondents completely agree or somewhat agree to the fact that empowerment advertising will decrease cultural gender stereotypes. All other categories of answers contain ignorable number of respondents. These results are misleading to a certain extent because there is a majority of females in the respondents. In order to achieve much authentic results, number of respondents must be increased and there must be equal representation of both genders.

Correlations

Spending

Ad Frequency

Spending

Pearson Correlation

1

.034

Sig. (2-tailed)

.730

N

105

105

ad Frequency

Pearson Correlation

.034

1

Sig. (2-tailed)

.730

N

105

105

A correlation is a relationship between two variables that shows their movement together or in the opposite direction. The correlation coefficient is used to see power of this relationship which can vary from -1 to +1. The value of 0.034 shows a very weak positive correlation between spending and ad frequency. In order to improve this model, new variables have to be added to analysis. We have to remember that correlation does not show causation but only a relationship between two variables. A relatively high significance level also indicates a weak relationship between these variables.

Correlations

Age

Spending

Age

Pearson Correlation

1

.055

Sig. (2-tailed)

.579

N

105

105

Spending

Pearson Correlation

.055

1

Sig. (2-tailed)

.579

N

105

105

Above table shows relationship between age and spending which is again very weak positive relationship. In order to improve relationship, these variables should be redefined, spending can be redefined in some other way and age can be seen as number of years passed when a person first heard of gender stereotypes. A larger number of respondents will also help to improve the correlation. The best way to improve this relationship is that respondents with similar characteristics should be chosen so that they have similar spending patterns.

One-Sample Test

Test Value = 0

t

df

Sig. (2-tailed)

Mean Difference

95% Confidence Interval of the Difference

Lower

Upper

Spending

8.258

104

.000

$649.92381

$493.8480

$805.9996

The above table shows one sample t test related to the spending variable. The mean difference shows the variation between mean spending and population mean. The upper and lower confidence intervals show that we are 95% sure that any given value of the variable will fall somewhere in between these values. A more precise data will have less difference between lower and upper confidence intervals. The significance is 0 which shows that there is a significant difference between mean spending and population mean.

One-Sample Test

Test Value = 0

t

df

Sig. (2-tailed)

Mean Difference

95% Confidence Interval of the Difference

Lower

Upper

Gender

48.186

104

.000

1.81905

1.7442

1.8939

The above table shows one sample t test related to the Gender variable. This is a categorical variable so we had to recode it before running one sample t-test. The lower and upper confidence intervals show that there is a 95% chance of any value to fall between these intervals. The significance is 0 which shows that there is a significant difference between the average number of people in any gender and population mean.

One-Sample Test

Test Value = 0

t

df

Sig. (2-tailed)

Mean Difference

95% Confidence Interval of the Difference

Lower

Upper

Transform

15.002

104

.000

3.03810

2.6365

3.4397

Transform is another variable that has been converted from categorical status so that one sample t-test can be applied to it. There is a significant difference found between the mean of transform variable and population mean. There is not much difference between the lower and upper confidence interval so the data can be considered precise. Another reason for precision in data is that while converting, we assigned numbers from 1 to 6 to the options available. This also shows the difference in proportion mean because there are 6 distinct categories of the variable.

One-Sample Test

Test Value = 0

t

df

Sig. (2-tailed)

Mean Difference

95% Confidence Interval of the Difference

Lower

Upper

Reinforce

21.488

104

.000

1.51429

1.3745

1.6540

The above table shows the t- test applied to the variable reinforce with a very little difference between lower and upper confidence intervals. The 0 in significance column shows that there is a significant difference between mean of reinforce variable and population mean.

Firstly, the above study should include a much higher number of respondents in this study and these respondents should equally represent both genders. Almost all of the variables need to be redefined so that the results are more meaningful CITATION htt181 \l 1033 (https://statistics.laerd.com, 2018). The respondents should have similar demographic and economic characteristics so that there are minimal number of outliers in the data. Some other tests can also be applied to compare the attributes of respondent in addition to numerical variables.

References

BIBLIOGRAPHY Byrne, G. (2007). A Statistical Primer: Understanding Descriptive and Inferential Statistics. Evidence Based library & information practice.

colegrave, N., & Ruxton, G. D. (2003). Confidence intervals are a more useful complement to nonsignificant tests than are power calculations. Behavioral Ecology, 446-447.

https://statistics.laerd.com. (2018). https://statistics.laerd.com/statistical-guides/measures-central-tendency-mean-mode-median.php. Retrieved from https://statistics.laerd.com: https://statistics.laerd.com/statistical-guides/measures-central-tendency-mean-mode-median.php

More Subjects

(5614)

(2294)

(1760)

(1684)

(929)

(743)

(572)

(446)

(429)

(347)

(310)

(300)

(288)

(249)

(238)

(140)

(109)

(92)

(64)

(53)

(30)

(25)

(8)

(3)

(3)

(2)

(1)

(1)

(1)

(1)

(1)

(1)

(1)

Join our mailing list

Invalid Email Address!

Thank you for joining our mailing list

@ All Rights Reserved 2023 info@freeessaywriter.net