1. Political scientists have difficulty controlling the variables in the cases they study. In other words, in our search for correlations or causal relationships, we are unable to make true comparisons because each of our cases is different. (The economies, cultures, geography, resources, and political structures of each country are very diverse, and it is difficult to control for these differences.) Even in a single study, variables change over time. These differences may distort our conclusions.
2. Even if we can control our variables in making our comparisons, there is the problem that many of these variables are interconnected and interact. Many variables are tied together to produce particular outcomes, in what is known as multicausality.
3. There are limits to our information and information gathering. Although the cases we study have many uncontrolled and interconnected variables, we often have too few cases to work with. A small pool of cases makes it difficult to select cases in such a way as to control our variables.
4. It is very difficult to access the few cases we do have, since they are not easy to acquire. They involve interviews, studying government archives abroad, and even international travel, which takes time and money. Furthermore, interviewees may be unwilling to speak on sensitive topics or even distort information. Governments may also restrict sensitive information, and the information that is available may be incomplete.
5. Even when comparativists widen their range of cases, their focus tends to be limited to a single geographic region. This regional focus is often distributed unevenly around the world, resulting in a high amount of information on one region and little to no studies on another.
6. The problem of bias makes it even harder to control for variables and select the right cases. As a result, investigators randomize case selection as much as possible to avoid choosing cases that support one hypothesis or another. However, due to the limited number of cases and difficulty in controlling variables, such randomization is not possible in political science. Cases should be selected based on what we think is the cause, rather than what we think is the effect.
7. It is sometimes difficult to establish which is the cause and which is the effect in a causal relationship. In some cases, it is possible that it can work either way. This problem of distinguishing cause and effect is known as endogeneity. Even if we have found two correlating factors we can't easily ascertain which is the cause and which is the effect.