Introduction.
In comparison to previous modules, this module has been more practical in quantitative data measurement and instrumentation. The module identified the different research instruments, their applications and limitations. In addition, the module discussed quantitative measurement tools and the various methods of data analysis used in quantitative data. The learning derived from this module, together with the previous modules, puts one in a position to collect quantitative data, measure the data, analyze it and quantify the results. This assists in determining the relationships that exists between variables, and in deriving statistics that can describe a population.
Overall, I scored 27 points out of 30 which was a better performance as compared to the previous modules. An analysis of the failed questions indicates that I still need to polish up on correlation statistics and correlation studies. I had some difficulties in establishing the different tests used in correlation statistic and correlation studies. Question 23 could have been better if it was complete; there was no table or graph hence I ended up doing some guess work. Below is an analysis of the concepts that were tested in the questions that I failed, how I understand these concepts, their characteristics and the questions that I have for the instructor in their regard.
A correlation statistic is a measure that indicates a relationship between variables in a study. Possible correlations range from +1 to -1. It can be described as a single number or unit that describes a degree of relationship between variables. Most statistical studies involve an establishment of the degree of association or a relationship that exist between the variables. The t score and r score are the commonly used statistical measures in establishing the degree of association or relation between a set of variables. Some correlation studies involve associations and not only relationships as most studies may indicate. For instance measuring the degree to which performance brings about self esteem may be both relational as well as associational. What remains unclear under co-relational statistics is how to establish if the variables are associated or directly related. The question that I have for the instructor, in this regard, is on how to differentiate between associated variable and related variables in determining the statistical score to apply in a study.
Quantitative statistical analysis also seems to be a problem when it comes to differentiating between the variance and covariance. To my understanding, variance is a range that exists over variables. Covariance, on the other hand, implies how much variables change together. Variance refers to the measure of distribution between variables while covariance measures how much the distributions change together. The presentation of variance and covariance comes in form of ANOVA and ANCOVA respectively. Differentiating between the two techniques is still not clear for me. I understand that ANCOVA analysis covariance while ANOVA analyses variance. However, the instructor needs to assist me understand when a covariance or variance applies. This is in regard to the relationship existing between the variables and the means of developing the covariates used in ANCOVA.
In conclusion, this module has assisted in development of statistical analysis techniques and their application. The concepts integrated in the module, have brought about a clearer image on the importance of quantitative data in how the data is analyzed in coming up with conclusive reports on a population. The module leaves me with more interest in knowing how to present the data and come up with conclusive ideas and generalizations that explain interrelationships and associations in different communities or populations. With this knowledge, I intend to increase on my skills on data collection, research analyses and interpretation of cognitive trends in the society.
