In order to answer this question, we must first remember the difference between an experimental and a quasi-experimental design. An experimental design is one in which there is an independent variable and a dependent variable and the experimenter manipulates the independent variable. There is also a control group for which...
In order to answer this question, we must first remember the difference between an experimental and a quasi-experimental design. An experimental design is one in which there is an independent variable and a dependent variable and the experimenter manipulates the independent variable. There is also a control group for which the independent variable is not manipulated. By contrast, in a quasi-experimental design, one of these factors is not present. Either the independent variable cannot be manipulated or there are no real control groups. With that in mind, let us try to answer this question.
The independent variable in this case is the education that women receive. It will be operationalized as years of formal schooling. The dependent variable is marriage. It will be operationalized as whether the woman is married by a certain age at which marriage is usual in a given society.
To manipulate the independent variable, the researcher will have to randomly assign different women to get different levels of education. The researcher would have to control the women and in some way require them to get a certain level of education. This would be highly unethical. The researcher would then wait until the women all reach the specified age and determine what percentage of each women receiving each level of education was married.
As I mentioned, this is highly unethical and therefore cannot be done. This means that a quasi-experimental design will need to be used to explore this relationship. If I can only have two groups, my two groups for this design would be women who had gotten a university degree and women who had not. (If I could have more groups, I would have women who did not finish high school, women who finished high school but not college, and women who finished college.) The independent variable is the amount of schooling they have gotten, but I cannot manipulate it—I am just going to have to take women who have already reached my marriage age and look at how much schooling they have. The dependent variable is whether they are married when they are at the marriage age. I would look at each of my groups and see if their marriage rates were different.
The expected results would vary widely by country, I suspect. Here in the United States, more educated women are more likely to marry and stay married. I expect this would be different in different societies.