Data Analysis Project: Analyzing Sports Skills with Regression Models

This data analysis project examines sports-specific skills, analyzing a dataset of 60 sports with 12 variables. The project conducts summary statistics, scatter plots, box plots, histograms, and regression analysis to explore relationships between variables. It emphasizes data cleaning to ensure data integrity. The study includes descriptive statistics, data visualization, and multiple regression analysis to identify significant relationships between variables. The analysis involves identifying skewness, outliers, and correlations. The project uses regression models to analyze the impact of different sports skills. The findings include positive and negative skewness and relationships between variables, supported by citations to relevant literature. The project concludes with a summary of the findings and suggestions for future research.

Running head: DATA ANALYSIS
Data Analysis
Name of the Student:
Name of the University:
Author note:

1
DATA ANALYSIS
Table of Contents
Introduction and project description..........................................................................................2
Literature Review.......................................................................................................................3
Data sources, data cleaning and description..............................................................................4
Descriptive statistics and Data Visualization.............................................................................6
Analytical Model and Data Analysis.......................................................................................12
Results and discussion..............................................................................................................15
Summary and conclusion.........................................................................................................16
References and Bibliography...................................................................................................17
Appendix..................................................................................................................................19

2
DATA ANALYSIS
Introduction and project description
The study is based on sports-specific skills. There are 60 different sports, and 60
observations have been conducted in this study. There is a list of 12 variables has been
indicated in this study. This study conduct summary statistics, scatter plot, box plot, and
histogram and regression analysis. Moreover, an essential aspect of this study is data cleaning
and checking outliers. In this study, all the variables are quantitative numerical variables
(Prokoshyna et al., 2015).

3
DATA ANALYSIS
Literature Review
The study on sports specific skills covers 60 different sports and 60 observations. The
previous research analyzes the assessing sports skills with different data set. Sports are
related to the area or field of data science. Moreover, sports is closely associated with the
training sciences and biomechanics of sports. The environment plays a vital role in sports
skills and sports applications. The data was collected by a questionnaire survey (Trottier &
Robitaille, 2014). The study was used to analyze the test for a different team. The present
research or previous study material are different. The study was conducted the inferential
statistics and descriptive statistics. The analysis part is the same for both the study analyzes
inferential and descriptive statistics (Holt et al., 2017). The finding from the previous study
showed that sports skills are based on the environment and guide of training. It has been
concluded that performance analysis depends upon team session group discussion and
defensive formations (Macnamara, Moreau & Hambrick, 2016). With the help of different
analytical skill, data visualization, and data duplication has been conducted. The present
study also shows the data duplication and display in MS-Excel software.

4
DATA ANALYSIS
Data sources, data cleaning, and description
In this study, all the variables are quantitative. There are ten variables have been
conducted in this study. There is no missing observation has been seen among all the
variables. There is a sample of 60 views has been taken in this study. The data has been
collected by a questionnaire survey in a location.
Data cleaning is a procedure that detects and remove corrupt or inaccurate data or
records from a data set. The cleaning is a procedure that modifies the data. This process may
be performed with the help of data wrangling tools or the system of batch (Chalamalla et al.,
2014).
When the data set is clean, then the next step is the cheek about the consistency of the
data. Inconsistent data always have error and missing. Thus this happens due to user error,
corruption in the transmission of storage. In that situation, the other important thing is the
data dictionary. Data cleaning maybe differs from data validation. The data validation defines
the invariability of data (Chu & Ilyas, 2016).
A proper process of data cleaning involves deleting the typographical error. There
some data cleaning procedure or solution has been done with the help of cross-checking with
valid data. In general, the cleaning procedure the enhancement in which data can be
converted by adding some related information. It is also related to the harmonization of data.
There are steps which involve in the data cleaning process. These are monitor errors,
standardize the process, and validate the accuracy, scrub for the duplicity of data and analyze
(Prokoshyna et al., 2015).
In the monitor, errors record and show the trend of data. In this case, most of the data
has been seen. It also helps to detect corrupt data. In this study, there is no missing data. But
some values are zero.

5
DATA ANALYSIS
In standardization, the essential point is to check the data at the time of entry. It helps
to produce useful data and reduce the risk of duplication (Chu, Krishnan & Wang, 2016)
Inaccuracy cleans the existing data. In research, the data tool allows for cleaning the
data. In this study, all the variables are valid.
The identification of duplicate data helps to save the time of analysis. There are
different data cleaning tools that avoid duplication.
In excel, with the help of a unique tool function, the missing data can be identified.
There is also another way to clean the data is that go to conditional formatting in highlight
cell rules, use duplicate values to identify duplication. After that, go-to information and
remove the duplicate, detect and remove the duplication. In this problem, there is no
duplicate value found.

6
DATA ANALYSIS
Descriptive statistics and Data Visualization
Table 1 Summary Statistics (output)
0 to2 2 to 4 4 to 6 6 to 8 8 to 10
0
5
10
15
20
25
Histogram for END
Class
Frequency
Figure 1 Histogram for END

7
DATA ANALYSIS
0 to2 2 to 4 4 to 6 6 to 8 8 to 10
0
5
10
15
20
25
30
Histogram for STR
Class
Frequency
Figure 2 Histogram for STR
0 to2 2 to 4 4 to 6 6 to 8 8 to 10
0
5
10
15
20
25
Histogram for PWR
Class
Frequency
Figure 3 Histogram for PWR

8
DATA ANALYSIS
0 to2 2 to 4 4 to 6 6 to 8 8 to 10
0
5
10
15
20
25
Histogram for SPD
Class
Frequency
Figure 4 Histogram for SPD
0 1 2 3 4 5 6 7 8 9
0
2
4
6
8
10
12
Scatter Plot on AGI versus FLX
AGI
FLX
Figure 5 Scatter Plot on AGI versus FLX

9
DATA ANALYSIS
0 2 4 6 8 10 12
0
1
2
3
4
5
6
7
8
9
Scatter Plot on NER versus DUR
NER
DUR
Figure 6 Scatter Plot on NER versus DUR
1 2 3 4 5 6 7 8 9 10
0
1
2
3
4
5
6
7
8
Scatter Plot on HAN versus ANA
HAN
ANA
Figure 7 Scatter Plot on HAN versus ANA

10
DATA ANALYSIS
END STR PWR SPD
0
1
2
3
4
5
6
7
8
Box Plot
Figure 8 Box Plot on END, STR, PWR, and SPD
In the summary statistics of END it has been seen that the mean, median and mode of
END is 5.08, 4.63, and 4.63. It has been seen that the mean value of END is higher than the
median. Hence the END sports data is positively skewed. The variance, standard deviation
and range is 4.38, 2.09 and 8.63. The mean, median and mode of STR is 5.169, 5.19 and
5.13. Since mean is larger than the median. Hence the STR is positively skewed. In case of
PWR, SPD and AGI the mean value is smaller than the median. Hence their skewness is
negative. Similarly for FLX, NER, DUR, HAN and ANA the mean value is higher than the
median. Hence their skewness is positive. The variance, standard deviation and range among
all the variables has been calculated and which has been shown in the excel file or
appendices.
There are some histogram has been constructed. In this histogram the X-axis represent
the class and the Y-axis represent the frequency. Most of the histogram shows about
normality of data. There some histogram is skewed and some of normal.

11
DATA ANALYSIS
In the section of scatter plot shows the relationship between two variables at a time.
All the scatter plot shows that there is a positive relationship between these variables. It is
positive because the data points are close to the trend line. In the scatter plot section the
relationship AGI and FLX, NER and DUR, and HAN and ANA have been illustrated.
The box plot shows that the outliers are existed or not in this data set. It has been seen
that there are no outliers—there some box plot smmetric and some positively or negatively
skewed.

12
DATA ANALYSIS
Analytical Model and Data Analysis
There are two multiple regression analysis has been conducted in this study. The
output of these analysis is as below
Output 1 Regression Analysis

13
DATA ANALYSIS
Output 2 Regression Analysis
From output 1 the regression model becomes
END = 1.032+1.045* STR+ (-0.80)* PWR+0.46* SPD+0.22*AGI
In this model the END has been taken as a dependent variable and the STR, PWR,
SPD and AGI has been taken as independent variable. The hypothesis test of this model
becomes
Null hypothesis: There is no relationship among the END and STR, PWR, SPD and AGI.
Alternative hypothesis: There is a relationship among the END and STR, PWR, SPD and
AGI.
It is clear from this output 1 that the P-value is less than alpha (at either 5% or 1%).
Hence the null hypothesis is rejected and the alternative is accepted. Thus it may be
summarized that there is a relationship among the END and STR, PWR, SPD and AGI.

14
DATA ANALYSIS
From output 2 the regression model becomes
FLX= 4.18+0.05*NER+0.26*DUR+0.06*HAN+ (-0.27)*ANA
In this model the FLX is dependent variable and the NER, DUR, HAN and ANA are
independent variables. The hypothesis test of this model becomes
Null hypothesis: There is no relationship among the FLX and NER, DUR, HAN and ANA.
Alternative hypothesis: There is a relationship among the FLX and NER, DUR, HAN and
ANA.
It is clear from this output 1 that the P-value is less than alpha (at either 5% or 1%).
Hence the null hypothesis is rejected and the alternative is accepted. Thus it may be
summarized that there is a relationship among the FLX and NER, DUR, HAN and ANA.

15
DATA ANALYSIS
Results and discussion
The study on sports specific skills covers 60 different sports and 60 observations. The
previous research analyzes the assessing sports skills with different data set. The mean value
of END is higher than the median. Hence the END sports data is positively skewed. . The
variance, standard deviation, and range are 4.38, 2.09, and 8.63. The mean, median and mode
of STR is 5.169, 5.19 and 5.13. Since the mean is larger than the median. Hence the STR is
positively skewed. In case of PWR, SPD and AGI the mean value is smaller than the median.
Thus their skewness is negative.
Similarly for FLX, NER, DUR, HAN and ANA the mean value is higher than the
median. Hence their skewness is positive. The variance, standard deviation and range among
all the variables has been calculated and which has been shown in the excel file or
appendices.
Most of the histogram shows about normality of data. There some histogram is
skewed and some of normal. The box plot shows that the outliers are exist or not in this data
set. It has been seen that there is no outliers. There some box symmetric and some of
positively or negatively skewed. From the regression output 1 it has been seen that that there
is a relationship among the END and STR, PWR, SPD and AGI. Similarly from output 2 it is
clear that there is a relationship among the FLX and NER, DUR, HAN and ANA.

16
DATA ANALYSIS
Summary and conclusion
The study is based on sports-specific skills. There are 60 different sports, and 60
observations have been conducted in this study. There is a list of 12 variables has been
indicated in this study. Moreover, the study also performs an essential part, which is data
cleaning. Data cleaning is a procedure that detects and removes the corrupt or inaccurate data
or records from a data set. The cleaning is a procedure that modifies the data. This process
may be performed with the help of data wrangling tools or the method of the batch. In this
study, some variables are positively or negatively skewed, and some are symmetric. The box
shows there are no outliers. Similarly, the histogram also explains about the normality of the
data (Ho & Yu, 2015).

17
DATA ANALYSIS
References and Bibliography
Bedeian, A. G. (2014). “More than meets the eye”: A guide to interpreting the descriptive
statistics and correlation matrices reported in management research. Academy of
Management Learning & Education, 13(1), 121-135.
Cameron, A. C., & Trivedi, P. K. (2013). Regression analysis of count data (Vol. 53).
Cambridge university press.
Chalamalla, A., Ilyas, I. F., Ouzzani, M., & Papotti, P. (2014, June). Descriptive and
prescriptive data cleaning. In Proceedings of the 2014 ACM SIGMOD international
conference on Management of data (pp. 445-456).
Chu, X., & Ilyas, I. F. (2016). Qualitative data cleaning. Proceedings of the VLDB
Endowment, 9(13), 1605-1608.
Chu, X., Ilyas, I. F., Krishnan, S., & Wang, J. (2016, June). Data cleaning: Overview and
emerging challenges. In Proceedings of the 2016 International Conference on
Management of Data (pp. 2201-2206).
Fox, J. (2015). Applied regression analysis and generalized linear models. Sage Publications.
Ho, A. D., & Yu, C. C. (2015). Descriptive statistics for modern test score distributions:
Skewness, kurtosis, discreteness, and ceiling effects. Educational and Psychological
Measurement, 75(3), 365-388.
Holt, N. L., Neely, K. C., Slater, L. G., Camiré, M., Côté, J., Fraser-Thomas, J., ... &
Tamminen, K. A. (2017). A grounded theory of positive youth development through
sport based on results from a qualitative meta-study. International review of sport and
exercise psychology, 10(1), 1-49.

18
DATA ANALYSIS
Macnamara, B. N., Moreau, D., & Hambrick, D. Z. (2016). The relationship between
deliberate practice and performance in sports: A meta-analysis. Perspectives on
Psychological Science, 11(3), 333-350.
Prokoshyna, N., Szlichta, J., Chiang, F., Miller, R. J., & Srivastava, D. (2015). Combining
quantitative and logical data cleaning. Proceedings of the VLDB Endowment, 9(4),
300-311.
Trottier, C., & Robitaille, S. (2014). Fostering life skills development in high school and
community sport: A comparative analysis of the coach’s role. The Sport Psychologist,
28(1), 10-21.
Volkovs, M., Chiang, F., Szlichta, J., & Miller, R. J. (2014, March). Continuous data
cleaning. In 2014 IEEE 30th International Conference on Data Engineering (pp. 244-
255). IEEE

19
DATA ANALYSIS
Appendix
Table 1 Summary Statistics (output)
0 to2 2 to 4 4 to 6 6 to 8 8 to 10
0
5
10
15
20
25
Histogram for END
Class
Frequency
Figure 1 Histogram for END

20
DATA ANALYSIS
0 to2 2 to 4 4 to 6 6 to 8 8 to 10
0
5
10
15
20
25
30
Histogram for STR
Class
Frequency
Figure 2 Histogram for STR
0 to2 2 to 4 4 to 6 6 to 8 8 to 10
0
5
10
15
20
25
Histogram for PWR
Class
Frequency
Figure 3 Histogram for PWR

21
DATA ANALYSIS
0 to2 2 to 4 4 to 6 6 to 8 8 to 10
0
5
10
15
20
25
Histogram for SPD
Class
Frequency
Figure 4 Histogram for SPD
0 1 2 3 4 5 6 7 8 9
0
2
4
6
8
10
12
Scatter Plot on AGI versus FLX
AGI
FLX
Figure 5 Scatter Plot on AGI versus FLX

22
DATA ANALYSIS
0 2 4 6 8 10 12
0
1
2
3
4
5
6
7
8
9
Scatter Plot on NER versus DUR
NER
DUR
Figure 6 Scatter Plot on NER versus DUR
1 2 3 4 5 6 7 8 9 10
0
1
2
3
4
5
6
7
8
Scatter Plot on HAN versus ANA
HAN
ANA
Figure 7 Scatter Plot on HAN versus ANA

23
DATA ANALYSIS
END STR PWR SPD
0
1
2
3
4
5
6
7
8
Box Plot
Figure 8 Box Plot on END, STR, PWR and SPD
Output 1 Regression Analysis

24
DATA ANALYSIS
Output 2 Regression Analysis