Many studies have reported the frequency and types of injuries in soccer players. However, a few have assessed the relationship of playing position, climate, psychological effects and infra structure facilities with injury. The purpose of...
moreMany studies have reported the frequency and types of injuries in soccer players. However, a few have assessed the relationship of playing position, climate, psychological effects and infra structure facilities with injury. The purpose of the study is to develop a
statistical model for injuries among the soccer players in Jaffna.
The observations on the following soccer injury-related variables, age, body mass index (BMI), playing position, years of experience, training method, equipment and ground facilities, climate and psychological effect were collected from a sample of 125 soccer players from Jaffna. We have grouped the above 9 variables into 3 factors using the
factor analysis techniques. The first factor (TIF) consists of training method and infrastructure facilities; the second factor (AE) consists of age and years of experience and the third factor (BMP) consists of BMI and playing position. It is interesting to note that the three variables in the 1st factor are common for a soccer team and the variables in other
two factors are associated with individual players.
Categorical data analysis techniques revealed that years of experience, BMI and playing position were significantly associated with soccer injury. Moreover, odds ratios were calculated for the international standardized BMI groups and found that injury risk was very less in normal weight BMI group. As per the playing position, the odds of getting injury increased from back to forward direction in the soccer field.
Logistic regression analysis was used to fit a model for soccer injury for a team by considering the factor TIF and another logistic regression model was fitted for soccer injury for an individual player considering other two factors AE and BMP. Further, we have developed a sample maximum likelihood discriminant function (SMLDF) to classify a soccer player as injured or not. Using the SMLDF, based on an individual
soccer player’s observations on the above nine variables, we will be able to advice him about the risk of getting injury in future.
Keyword: Discriminant Analysis, Factor Analysis, Logistic Regression, Odds Ratio, Principal Component Analysis