In

Data analysis is a process of organizing raw data as well as structuring it with an aim of extracting important information which is used to draw conclusions (Golden et al., 2011). Data analysis involves three major steps. The first step is data preparation. It entails cleaning and organizing data required for analysis. The second step is data description which largely entails description of the data. The last step is referred to as the inferential statistics which largely deals with hypothesis testing. Data cleaning is the stage in which various changes can be made to the data without affecting the results (Golden et al., 2011). It is also the stage in which standardization and removal of unnecessary data is done making it possible for a researcher to apply the tools selected for data analysis in an efficient and effective way. This process helps the researcher solve issues such as formatting and variance.

Data description involves use of graphs, charts, tables, and numbers to represent the raw data in an organized and summarized manner. These descriptive statistics are mainly used to show the central tendency, skew- ness, and range of dispersion. Measures of central tendency include the mean, median, and mode. A researcher seeks to know the average, the middle, and the most frequent points from a set of data (Golden et al., 2011). Dispersion is measured using variance, standard deviation, coefficient of variation, range, percentiles, and quartiles. These tools help a researcher to know how a given set of data is distributed around the mean.

Inferential statistics helps a researcher to draw conclusions about a set of data. It is at this point that a researcher tests the hypothesis. A researcher has two hypotheses: null hypothesis and alternate hypothesis. The conclusion depends on the alternate hypothesis, which is meant to reject the null hypothesis (Golden et al., 2011).

Correlation refers to a statistical relationship that is used to show the degree of association between two or more variables (Aggarwal & Khurana, n.d.). There are two types of correlation: positive and negative correlation. Positive correlation occurs when the variables take the same direction, for instance, if one variable increases, the other one also increases. Negative correlation occurs when the variables take opposite direction, for instance, if one variable increases, the other one decreases (Aggarwal & Khurana, n.d.).

There is also another category of correlation: linear and curvi-linear correlation. Linear correlation occurs when change in two variables is constant. On the other hand, curvi-linear correlation occurs when the proportionate change in two variables keeps changing (Aggarwal & Khurana, n.d.).

Normally, there are variables that exhibit the same kind of relationship. For this reason, correlation helps to display the degree of association of one variable to the other variables. In the business world, correlation helps business people to come up with price and costs estimates, hence making appropriate business decisions. Correlation also helps economists determine the relationship between different variables that affect the performance of an economy. In addition, correlation assists in determining the value of a variable using the value of another variable.

One of the possible causes of causality between anxiety and depression is mutual dependence. That is, depression could appear because of anxiety while anxiety could be caused by depression. Causality between anxiety and depression could also be because of pure chance. For example, if a researcher is biased in selecting his sample, causality can occur. Lastly, the causality between anxiety and depression can arise due to the presence of a third common factor between the variables, for example, loss of a loved one (Aggarwal & Khurana, n.d., p.2).