• No results found

Purpose:

Main data collection of the study.

Simple random sampling Questionnaire survey 320

Total sample size 320

3.9 Data Analysis

The use of a quantitative research approach allowed the researcher to use statistical approaches for data analysis and interpretation for the data sets outlined under respective sections below.

3.9.1 Quantitative Data

Data preparation was carried out before the analysis of data. This process entailed checking the quality (correctness and completeness) of collected data (Bryman, 2007) and converting the data into a format which enables analysis and interpretation to take place. For the purpose of this study, the questionnaires were cross checked for accuracy by supervisor and two peer students. Pre-coding of questionnaires was done during

questionnaire design. Thereafter, quantitative data was captured and analyzed using Statistical Package for Social Sciences (SPSS) version 23.

Data was analyzed using both the descriptive and inferential statistics. Descriptive statistics used include frequency distribution such as bar charts and pie charts and; statistical measures of location and tendencies such as the mean This was utilized to describe and summarize data in a useful and meaningful way.

Inferential statistics used include Correlation Analysis, Analysis of Variance (ANOVA) T-tests and Multiple Regression.

3.9.1.1 Correlation Analysis

According to Bryman (2007), correlation is a technique for investigating the relationship between interval/ratio variables and or ordinal variables that seeks to assess the strength and direction of the relationship between the variables concerned. Pearson’s r and Spearman’s rho are both methods used to access the level of correlation between variables (Bryman, 2007). This study used Pearson’s r method

Kreinovich, Nguyen and Wu (2013) explain that Pearson’s correlation is used for describing the dependence between random variables, i.e. X and Y. Furthermore, it measures the relationship between these two variables. Pearson's correlation coefficient (r) for continuous (interval level) data ranges from -1 to +1 (Bryman, 2007). A value of +1 represents a positive perfect correlation, while a value of -1 represents a perfect negative correlation. A value of 0 means that the variables are perfectly independent. The closer the absolute value is to 1, the stronger the relationship (Bryman, 2007).

3.9.1.2 Analysis of Variance (ANOVA)

Analysis of Variance (ANOVA) analyses variance which is the spread of data values within and between groups of data by comparing means (Bryman, 2007). Orme and Yamagata (2014) elaborate that ANOVA is used for testing whether groups are significantly different or not and F-statistics represents these differences.

Anders (2017) explains that ANOVA uses the F-statistics to statistically test the equality of means and also test the following:

 The overall significance of a regression model.  Comparing the fits of other different models.  Testing the specific regressing terms.

 Testing the equality of means.

If the likelihood of any difference between groups occurring by chance is low, this is represented by a large F ratio with a probability of less than 0.05. This is referred to as statistically significant (Bryman, 2007).

According to Leedy and Ormrod (2014) the following are different types of ANOVAs: (a) one-way between groups, (b) one-way repeated measures, (c) two-way between groups, and (d) two-way repeated measures. These different types of ANOVA reflect the different experimental designs and situations for which they have been developed.

The study used one-way between groups analysis of variance. This involved only one categorical variable which will tell if there are any differences among the means of two groups or more.

3.9.1.3 T-tests

Kim (2015) explains that a t-test is a type of statistical test which is used for comparing the means of two groups. According to Leedy and Ormrod (2014), the independent- samples t- test evaluates the difference between the means of two independent or unrelated groups. Therefore, a t- test was used to test whether the means of the two groups are significantly different.

Bryman (2007) explain further that it is a statistical test used to determine the probability (likelihood) that the values of a numerical data variable for two independent samples or groups are different. Table 3.4 summarises how the data analysis methods were applied for addressing the research objectives.

3.9.1.4 Multiple Regression Analysis

Diamantopoulos and Schlegelmilch (2000) mentions that the multiple regression analysis is used for analysing the relationship between one dependent variable and a number of independent variables. However, both the dependent and the independent variables should be metric which means that they must be measured at ratio or interval level. Bryman (2007) adds that the independent variables could also be in the form of dummies.

According to Creswell (2013), multiple regression analysis could be used for identifying the strength of the effect that the independent variables have on a dependent variable. Bryman (2007) also add that this analysis enhances the understanding of how much the dependent variable changes when the independent variables change as well. Furthermore, the multiple regression analysis predicts the trends or future values which means it can be used to get the point estimates (Bryman, 2007). In this study, the dependent variable was business strategy execution and the independent variables were work experience, leadership engagement, leadership styles, business culture, demographics and training level.

The multiple regression analysis was therefore conducted to understand the nature of the relationship between the work experience, leadership engagement, leadership styles, business culture, training level and demographics which are the variables or concepts under this study in as far as the execution of business strategy is concerned.

Table 3.4 summarises how the data analysis methods were applied for addressing the research objectives.

Table 3.4: Data analysis methods summary. Source: Researcher’s own compilation

RESEARCH OBJECTIVE DATA SOURCES METHOD OF ANALYSIS