Introduction
The way data analysis is accomplished depending on:
- the nature of the research problem
- the purpose of the research or
- the design of the investigation.
The purpose of the research:
- describing variables or
- examining relationship between variables
Decision made in the data analysis
Decision made in the data analysis of survey research is characterized by a wide spectrum of statistical analysis used.
It may simply consist of determining the frequencies and percentages for the most number of variables in the study.
In an explanatory survey, however, this is desired in exploring the relationship between variables, whether two variables or more.
Depending on the scale of measurement of data used in the data collection, whether continuous, rank or dichotomous relationship studies normally use correlation and regression statistics.
Research problems may also suggest that the purpose of an investigation is to find differences between or among sample means. This is generally called the “analysis of variance” or ANOVA. If only two groups are involved, the analysis is called t-test.
ANOVA allows researcher to deal with:
two or more independent variables simultaneously, asking not only about the individual effects of each variable separately, but
also about the interacting effects of two or more variables.
Regression
Regression is a statistical technique used to establish the relationship between a independent variable (Y) with a set of independent variables (X’s).
the variables of Y and X’s are related in a linear manner.
Regression model is, therefore, used for the value prediction of Y or any X, known to have relationship in a linear manner.
Sometimes, researcher needs to find the significance of differences among the proportions of subjects, objects, events, etc., that fall into different categories.
A statistical technique used in such cases is called the chi-square test.
