The Steps of Correlational Survey Research Technique

37 2 Prediction Design A second type of correlational design is called a prediction design. The purpose of this design is to identify variables that can effectively predict some outcome or criterion. The variable being predicted is called the criterion variable, and the variable or variables being used to predict the criterion are called predictors. When a study involves only two variables, the predictive relation is estimated with a statistical procedure called simple linear regression. When more than one predictor variable is used to predict a criterion, the analysis is called multiple regression. This is an extremely powerful statistical procedure that can estimate the collective as well as the individual contributions of all predictor variables. This analysis makes it is possible to develop not only an effective prediction, but also an efficient one. While the general characteristics of prediction designs are similar to those for relational designs, they differ several important ways. These are as follows. a Two or more variables are collected from each individual in the sample. b Data for the predictor variables is typically collected prior to that of the criterion variable. c The data is analyzed as a single group. d A correlation coefficient – typically a multiple R – is reported and discussed in terms of its strength, direction, and statistical significance. e The contribution of each predictor variable is examined in terms of its unique contribution to the prediction of the criterion variable. A regression coefficient – b i – is reported for each predictor variable and is discussed in terms of its significance to the prediction of the criterion variable. In 38 some cases, a specific analysis is used to evaluate the efficiency and effectiveness of the predictor variables. This is called stepwise regression and results in the prediction of the criterion variable in which the effectiveness of each predictor variable is examined for redundancy with other predictors. Those predictors that do not uniquely contribute to the prediction are eliminated. f A regression equation is produced which can be used to predict the criterion variable from data collected only on the predictor variables. g Interpretations from the statistical results are drawn about the predictive process.

6. Regression Analysis

Regression analysis is a statistical tool for the investigation of relation between variables. It is to determine the linear relation between two or more variables. Regression is primarily used for prediction and causal inference. Campbell, 2008. Regression analysis is a statistical tool for the investigation of relations between variables. Usually, the investigator seeks to ascertain the causal effect of one variable upon another Alan, O. 2006. Regression analysis is used when two or more variables are thought to be systematically connected by a linear relation. In simple regression, we have only two – let us designate them x and y – and we suppose that they are related by an expression of the form y = b0 + b1 x + e. The hypothesis might be that there is a positive correlation or a negative correlation. A perfect correlation would be an r = +1.0 -1.0, while no correlation would be r = 0. Perfect correlation would almost never occur; expect to see correlation much less than + or - 1.0. Although correlation cant prove a 39 causal relation, it can be used for prediction, to support a theory, to measure test- retest reliability, etc.

7. Confirmatory Survey Research

“Confirmatory Survey research is a research to determine the tendency or pattern of two or more variables to vary consistently” John W., 2012. Confirmatory research tests a priori hypotheses - outcome predictions that are made before the measurement phase begins. Such a priori hypotheses are usually derived from a theory or the results of previous studies. Exploratory research on the other hand seeks to generate a posteriori hypotheses by examining a data-set and looking for potential relations between variables. It is also possible to have an idea about a relation between variables but to lack knowledge of the direction and strength of the relation. 8. Variables The researcher will not be able the research unless you know how to talk about variables. A variable is any entity that can take on different values. Anything that can vary can be considered a variable John W., 2012. A researcher must determine which variable needs to be manipulated to generate the results. a. The Definition of Controllable Variables Controllale variable is an extraneous variable that an investigator does not wish to examine in a study. Thus the investigator controls this variable. Control Variables - the variables that we control don’t change in an experiment. For example, in the dog experiment example, it would need to control how hungry the dogs are at the start of the experiment, the type of food we are feeding them, and