Data Collection and Analysis of Quantitative Data

Subject: Sciences
Pages: 8
Words: 2116
Reading time:
9 min
Study level: College

The aim of the study was to highlight the existence of the Relative Age Effect at a football club in the United Arab Emirates and also to carry out an analysis providing information on how this effect has evolved in recent years. The data used in this case has been provided from some clubs in the United Arab Emirates.

The analyzed data shows that players who were born on January 13, March 11, May 11, October 14 and December 1, however, most of this is not shown the distribution of them in terms of age. The final results showed that relative age effects had an impact on the performance and it was in existence in the United Arab Emirates clubs.


Footballers are always grouped according to their ages when choosing a team. Differences in ages of students bring difficulties in blending these students to fit into a team. The consequences of different age groups are what are called relative age groups. Research has shown in the past that a relative age effect exists in various environments. Most differences in performance are usually attributed to the relative age effect. A footballer born the same year will have equal performance however if they are born in different periods they will have different cognitive, emotional and physical. In sports, for a student to shine out of others he must-have qualities that are outstanding from others(Fallowfield, Hale and Wilkinson, 2005).

As a result, children who participate in sporting activity may develop sports burnout, and experience a lifelong avoidance of physical activity (Cooper and Schindler, 2003).

Research objectives

During the study period, the general research objective will be to determine whether the relative age effects exist in the footballer club of the United Arab Emirates and the age groups are distributed from the one hundred sampled. The solution will help the management of football to planning its affairs that is long term. Specifically, the research will be to investigate the effects of age on performance by footballers. Investigating the effects of age on football will be another specific objective. Another specific objective will be to determine if a correlation exists between performance and relative age effects.


There are different methods used in any sociological research carried out, mostly as determined by the objectives of the study and the target population in question. The form of research carried out in the research was a document study, which sought data collected by various departments from the whole population and analyzed it drawing conclusions about the population from the results obtained from the analysis.

The form of data used was primary data obtained from observation and recording of all the cases reported over time. Since the study covered a long duration of time, it took the form of a longitudinal study, a study that considers data collected at several time points, annually in this case, and then used for the general study and for comparisons between the time points. Hence, a comparison of the data for the years is possible in this study.

The methods used for the analysis are quantitative research methods, methods that include consideration of data in quantitative form. The variables involved measured the quantity of the data and included the ages of footballers. In this way, the study considered a comparative analysis of the data obtained. It considered a comparison of the data for the different years and made conclusions from the analysis on the trend of the data. Hence, a trend analysis was also adopted in the study (Batini, Cappiello, Francalanci and Maurino, 2009).

The methodological orientation of the data used in the analysis was scientific. The study adopted a scientific approach in its application and all the methods used were scientific. The data collection methods included observation of the data and recording it as proposed scientifically. The variables and form of the study were also scientific. In addition, scientific approaches were used in obtaining the objectives of the study in which comparative analysis and trend analysis techniques were used to determine the trend and orientation of the data obtained, whether it was on an increase or a decline. However, the study did not consider a probability approach to data collection and did not employ sampling techniques. Data was collected from the whole population(Vaeyens, Philippaerts and Malina, 2005).


The systematic sampling technique was used to choose the participants. The collection or data including the procedures of recording has been described in full detail that gave full information on how and why the procedures are being followed or done. The procedures appear appropriate in which the data that was collected is in a manner of minimizing bias as well as behavioral distortions. The staff of data collection has been trained appropriately wherein the so-called demographic data were absolutely collected through self-report and with the use of an information form such as paper-pencil info.

Data collection

Quantitative research method possesses an innate characteristic and that is to communicate with large sample populations and thus the instruments of quantitative research are designed for the same purpose as well. In other words, data collection from the quantitative research method is fairly simple; especially in the case of surveys. And when such data is collected it can be graphed and tabulated with much ease. By using the compiled data in form of grabs, tabulations and charts results and conclusions can easily be formed(Wolverton, 2009).

Statistical analysis

This evaluation will be retrospective in nature. Hence, the population of the study will comprise footballers. Chi-square will be used to test the hypothesis, whereby α = 0.05 is the decision rule, meaning a 5% chance of being wrong when rejecting the null hypotheses. If the indicated test shows the probability of occurrence of the observed result due to chance or sampling error at less than 5%, this will mean that the alternative hypothesis will be accepted (Garcia and Salvadores, 2005). September was selected as the first month of the selection of the year and august as the last.

The study will consider the age bracket as the average age for a student in high school. Data collection will be done through oral interviews and the use of questionnaires. In the face-to-face interview, an interview guide with guidelines and questions similar to those in the questionnaire will be used. In data treatment, raw data will first be classified into two main categories, male respondents. The categories will be coded 1 and 2 representing male and female respondents respectively.

Apart from gender, other variables to be studied will be age and date of birth. Data analysis will be done using SPSS Software where Scale will be used as the variable measurement level. Through cross-tabulation, the relationship between the effects of age and footballer performance will be established. By using Frequency, as an SPSS tool, variations in a specific variable due to different treatment levels will be determined. T-test statistics will be used to make conclusions about measures of distribution and variations in different dependent variables. Multivariate analysis will be used to determine the effect of different treatment levels on two or more groups. Inferences and conclusions will be made at a 95 percent confidence level (Sprietsma, 2007).


The management of data such as coding including the methods analysis was described sufficiently by using such basic social processes like for instance, Taking Care of Oneself in terms of Risk Environment that is high and at the same time linked to three (3) categories while forming a theory known as descriptive in line with those footballers sampled. Moreover, the analysis of data is strategically compatible with regards to the tradition when it comes to research including the type and nature of data that was gathered. Additionally, the data analysis was able to yield a product that is indeed appropriate such as using comparative method while used to even develop the categories, open coding and of course, analytical memos. Finally, the analytic procedure has not even suggested the possibility of biases because of the use of open coding, examining process, conceptualizing, comparing and of course categorizing the significant data (Simmons and Paull, 2001).

The table also reveals how the distribution of players varies considerably in each of the three groups studied school month

Observed N Expected N Residual
if January 13 8.3 4.7
February 6 8.3 -2.3
march 11 8.3 2.7
April 4 8.3 -4.3
May 11 8.3 2.7
June 5 8.3 -3.3
July 9 8.3 .7
August 3 8.3 -5.3
September 6 8.3 -2.3
October 14 8.3 5.7
November 7 8.3 -1.3
December 11 8.3 2.7
Total 100

Test Statistics

school month
Chi-Square 17.600
df 11
Asymp. Sig. .091

0 cells (.0%) have expected frequencies less than 5. The minimum expected cell frequency is 8.3.


Conducting significance tests on the independent variable enables us to determine whether the variable is significant in the regression or not. This test involves using a term known as the degree of freedom (ν) which is calculated by subtracting the number of variables, including the constant from the number of observations. Hence in this specific case, the degree of freedom v = 100-2 = 98. The test also involves using a (α) value which is the confidence interval chosen specifically. Through the use of (ν) and (α) a t-ratio tabular value, ttab is obtained from the t-distribution table. This value is then used to determine whether the independent variable is significant or insignificant. Through SPSS we are provided with a t-ratio, referred to as tcale . If the absolute value tcale is compared with the ttab value we can determine which hypotheses to accept or reject. If tcale>ttab then we can accept H0. The calculated t value of 17.302 and with the confidence interval of 95% the tabulated t value is 1.734. Here tcale>ttab i.e., 17.302 > 1.734. It can be said that the variables are significant in the regression and we accept the null hypothesis (H0).


Conducting F-test enables us to determine whether the overall model is significant. If the absolute value is compared with the ƒtab value we can determine which hypothesis to accept or reject. If ƒcale>ƒtab then this means that the model is significant and H0 will be accepted. Using α=5% and v = 100-2 = 98 and k = 2-1 = 1, Ftab = 4.41. The calculated value of F is Fcalc = 3219.723. This shows that the calculated value of F is greater than the tabulated value of F, so it can be concluded that the overall model is significant (Sekaran, 1999).

Coefficient of determination

The result shows a correlation of “-0.319”. The strength of the relationship between the variable is closer to +1, which means that the variables are strongly related. The positive (+) sign indicates the direction that an increase in independent variable would certainly cause an increase in the dependent variable (Mujika, Vaeyens, Matthys, Santisteban, Goiriena, and Philippaerts, 2009; Schwab, 2005).

The value determined for R2 is 0.107 (10.70%), which suggests that the model is not a good fit in terms of Motivation. R2 indicates a very weak relationship between Relative age effects (independent variable) and performance (dependent variable)

All the results show a weak and non-significant relationship between the Relative age effects and sports. So H0 will be rejected and H1 will be accepted.

In the nutshell, all the results indicate that Variable age as a whole is a good factor for student football performance.


Quantitative research has an innate attribute that limits its scope and range of research. The reason for this is that quantitative research methods rely heavily on mathematical calculations and empirical reasoning. Therefore several immeasurable and unquantifiable variables are ignored if this method is employed in research. Several researchers are of the view that these non-mathematical variables are sometimes more important than other statistical variables. And since quantitative research methods do not provide any other alternative to include these variables in the research, the quantitative research may sometimes be misleading or it can be based upon incorrect assumptions. Although the quantitative research methods informed the researcher regarding the current situation such researches fail to provide any real insight to him/ her. Some variables might be quantifiable or rather measurable and there is a certain probability that the quantitative research might diagnose the right symptoms. On the other hand, there is also a certain probability that quantitative research methods might not be able to find let alone interpret the relevant variable (Reilly, 2000)


There is a relative age effect in the clubs of United Arab Emirates football clubs. The correction coefficient and chi-square showed that the relative age effect was strong and had a strong impact. The footballers were from age groups players for the same clubs(Philippaerts, Vaeyens, Janssens, Van Renterghem, Matthys, Craen, Bourgois, Vrijens, Beunen and Malina, 2006).

Reference List

Batini, C., Cappiello, C., Francalanci, C. & Maurino, A., 2009. Methodologies for Data Quality Assessment and Improvement. ACM Computing Surveys. Web.

Cooper, D. & Schindler, P., 2003. Business Research Methods. New Delhi: Tata McGraw-Hill Publishing Company Limited.

Fallowfield, J., Hale, B. & Wilkinson, D. 2005. Using Statistics in Sport and Exercise Science Research. Chichester: Lotus Publishing.

Garcia, V.& Salvadores, J., 2005. The relative age effect in football. Training Fútbol.

Mujika, I., Vaeyens, R., Matthys, S., Santisteban, J., Goiriena, J. & Philippaerts, R., 2009. The relative age effect in a professional football club setting. Journal of Sports Sciences.

Philippaerts, R., Vaeyens, R., Janssens, M., Van Renterghem, B., Matthys, D., Craen, R., Bourgois, J., Vrijens, J., Beunen, G. & Malina, R., 2006. The relationship between peak height velocity and physical performance in youth football players. Journal of Sports Sciences.

Reilly, B., 2000. Anthropometric and physiological predispositions for elite soccer. Journal of Sports Sciences

Schwab, D., 2005. Research Methods for Organizational Studies. New Delhi: Routledge Publisher.

Sekaran. U., 1999. Research Methods for Business, a skill-building approach. New York: John Wiley& Sons, Inc.

Simmons, C. & Paull, G., 2001. Season of birth bias in association football. Journal of Sports Science.

Sprietsma, M., 2007. The effect of relative age in the first grade of primary school on long-term scholastic results international. Comparative evidence using PISA 2003. ZEW Discussion Papers 07-037, ZEW – Zentrum für Europäische Wirtschaftsforschung/ Center for European Economic Research

Vaeyens, R., Philippaerts, R. & Malina, R., 2005. The relative age effect in soccer: A match-related perspective. Journal of Sports Sciences.

Wolverton, M., 2009. Research Design, Hypothesis Testing, and Sampling. The Appraisal Journal.