3.4 STATISTICAL TOOLS 3.4.1 REGRESSION ANALYSIS Regression analysis is a statistical process which helps to establish relationship between a dependent variable and one or more independent variables also known as predictors.The method may be parametric or non-parametric. The common ones are linear regression and ordinary least square regression. REGRESSION MODELS Regression model consists of three variables - the dependent variable denoted by Y, the independent variable denoted by X and an unknown parameter denoted by \beta . The regression model aims to explain Y as a function of X and \beta i.e E(Y|X)=f(X,\beta) . UNDERLYING ASSUMPTIONS The Regression analysis is based on certain assumption which are :- • The sample should be
For this research, Quantitative study was used as it involved deduction. Hypotheses was formulated; the dependent and independent variables were identified which assisted in measurements of objectives. Data was collected by using close-ended questionnaires. 5.1 Research paradigm According to the requirements of research question, it was decided that it would be appropriate to choose the positivism approach as the philosophical assumption and research paradigm for the study. Besides this, the quantitative approach was used during this research.
Chapter three discusses the research design and methodology used for the current study. The chapter begins with a discussion of the rational for choosing a qualitative design. Qualitative methodologies that were considered for the current study are discussed next followed by the rational for selecting a focused ethnography. Ethical considerations will then be discussed and the researcher describes how principles of autonomy, beneficence and non-maleficence, justice and respect were adhered to. The chapter continues with a discussion about sampling, recruitment and data collection.
The statistical results showed that the mean P value (0.66) is less than the alpha value (0.80) which means that the null hypothesis is false and his inventory is valid to identify students’ understanding. It is important to recall that the inventory was administered to 262 students from different universities in Turkey; so, the sample size is not enough and not representable. Only students who have an introduction to astronomy were included in the study, so the researcher used purposive sampling in his study. The researcher could have used graphs to represent the results of
The F-statistics is used to reject or accept the null hypothesis, no causation between the variables when F-statistics is greater than 2 and less than 2 respectively. Granger causality theorem suggests that there will be granger causality in at least one direction if there exists co-integration relationship among the variables provided the variables are integrated order of one (Muhammad et al. 2008). According to Engle-Granger (1987) argued that granger causality test is conducted at first difference through vector auto regression (VAR) method than it will be misleading in the presence of co-integration. An additional variable to ARDL method such as the error correction term will helps the study to capture the long run relationship.
II. Methodology : 1. Research methodology: Accounting techniques for estimations and predictions are various and numerous. Each method stands for a different specific situation. We will be using the regression method because it gives the most accurate estimate of the relationship between the dependent variable and the independent variables.
Under inferential statistics, reliability analysis and a logistic regression has been done. Descriptive statistics are used to represent analyzed data in a meaningful and a clear way. 4.2 Reliability Test. Reliability analysis for this research allowed studying the properties of measurements and scales and the items that compose scales. Reliability analysis calculates number of commonly
Respondents are selected because they are accessible and articulate. The advantage of using sampling in this type of research is that it saves time and simplifies the process. It is easier to study a representative sample of a population than to study the entire population. Whilst studying an entire population can be time-consuming, especially if the population is large or distributed over a large geographical area. The non-probability sampling method seemed the most appropriate as students were invited to participate in the research by completing a survey questionnaire anonymously.
Chapter 4: Research Methodology 4.1. Introduction This chapter discusses research methodology that was used to conduct study. There are elements which are employed for conducting research .According to the Crotty (1998) there are three elements which offer practical guide for conducting social research whether it is quantitative or qualitative and those are methods, methodology and theoretical perspective. 4.2. Qualitative Approach This research adopts qualitative approach.
They collected a large-scale of sample of parents and children from Germany in the research. After that, they analyzed the data by applying the advanced quantitative methodology, which is the bi-variate dual-change score model. Factors such as age, gender, school type, intelligence, and family socioeconomic status (SES) and others were taking into consideration while analyzing the data. It is a good practice for repeating the experiment on the families in United States as it increased the robustness of the results. Additionally, the authors conducted robustness check by doing traditional cross-lagged model to prove that their results did not depend on particular model.