You are on page 1of 1

From Variables to Hypotheses H = statement that propose a relationship betwn 2 var .

It is specified as X affects Y tentative statement abt how the var may be related to each other involve the effect of 1 var on another the way 1 var cause the other var to change its value violent cartoons cause children to be more aggressive var u think causes something to happen is called ind var(IV) var that changes because of IV is dep var ( DV) its value depends (hypothetically!) on what you do with the IV Political participation increases with education. Union members are more likely to vote Democratic than non-union members.People with college degrees earn higher incomes. Countries with democratic political systems tend to solve their political conflicts through peaceful means. Countries with British colonial experience tend to accept democratic institutions more than countries who did not have that this experience 2. Hypotheses seek to establish both direction and magnitude. Directional Hypothesis It states the expected direction of the relationship, or how the researcher thinks the variables are related. For example: As more countries become industrialized, political stability will increase. Nondirectional Hypothesis It states that there is a relationship but does not specify the direction of the relationship. For example: As more countries become industrialized, political stability will get affected. Null Hypothesis The null hypothesis says that there is no relationship between the independent and dependent variables. For example: A country's level of industrialization has no affect on political violence. Technically, all statistical tests are tests of the null hypothesis first, which is rejected in favor of degrees of confidence in the alternatives.

Magnitude in relationships refers to the extent of change in the dependent variable caused by a change in the independent variable. Never in the social sciences can all of the change in the dependent variable be explained by a change in one independent variable. 3. Properties of Good Hypotheses: Hypotheses should be constructed in such a way that they lend themselves to the Scientific Method: 1. They should be empirical statements; never normative or value statements about what should or should not be. 2. A hypothesis should describe a general phenomena not a particular occurrence. Thus, it is meaningful to test if Americans whose income improved during Clintons first term will vote for him again in the second term. Yet, it is better to test the impact of income change on individuals voting behavior in general using data from as many elections as possible. 3. A good hypothesis should be plausible. There should be some logical reason for thinking it possible. Usually there should be a theoretically well-founded link between the independent and the dependent variables. Ex. Do not tell me that you want test the following hypothesis: The more people in China catch flu, the more likely Americans prefer tax cuts. Or, As temperature rises, crime increases. 4. A good hypothesis is specific. The concepts used are clearly defined. An example of a bad hypothesis is to say that there is a relationship between personality and political attitudes. Which personality type? What attitudes? A good hypothesis is more specific, e.g., People who feel alienated are not likely to have a strong trust in government. 5. A good hypothesis should be direct. In other words, if you have a compound relationship, youd better break it up to two hypotheses. Ex. Independent variable (X) => intervening variable (Y) => dependent variable (Z) Break it into two hypotheses: X => Y and then Y => Z ** In comparing voters, those whose economic situations have gotten better are more likely to have favorable opinions about the incumbents handling of the economy than are voters whose economic situations have gotten worse. ** In comparing voters, those who have favorable opinions about the incumbents handling of the economy are more likely to vote for the incumbent than are those who have unfavorable opinions about the incumbent. 6. Last, a good hypothesis is testable. There must be evidence that is obtainable which will indicate whether the hypothesis is correct or not. 4. How to derive hypothesis: DEDUCTION - reasoning from general to specific (theory, then research) Theory indicates that the more countries get engaged in world economy, the more they tend to adopt democratic reforms. You will test this hypothesis using data from Latin American countries. INDUCTION - reasoning from specific to general (research, then theory) Jane and Rebecca vote for Democratic candidates ==> most women favor Democratic candidates 5. Steps in Formulating a Hypothesis Decide what you want to explain: choose a dependent variable Your dependent variable must show variation. So do not choose a dependent variable that is constant. In other words, do not try to study the causes of civil wars by selecting only the countries with civil wars. Run Descriptives to see mean and dispersion statistics. Even better, run Frequencies, and call for a histogram along with the mean and std. dev (suppress the Frequency table itself) Choose independent variables that also show variation One can't explain variation in a dependent variable with an independent variable that doesn't vary. Simply you cannot explain a variable with a constant or vice versa. Moreover, the variation in the independent must match that in the dependent variable. Otherwise, they can't possibly covary, which is needed for the covariation needed in correlation and causal relationships. Examples of lack of theoretical potential: Voting for Clinton in 1996 in the suburb of Winnetka can't be explained by race, for race does not vary much in Winnetka. Variation across time in deaths in domestic violence within nations can't be explained by ethnic diversity, for ethnicity doesn't change much across time within a nation. However, variation in deaths across nations can be related to variation in ethnic diversity across nations. Think of multiple causes of the dependent variable: Do two or more independent variables combine to affect it? Consider using multiple regression to deal with multiple causes. Does a relationship hold for some units of analysis but not others? For northern states but not for southern ones? For European nations but not for Third World nations? For whites, but not for blacks? For reformed cities, but not unreformed cities? For multi-party states, but not single-party states? In other words, is there a potential interaction among the independent variables. For example, does education affect African Americans differently from its effect on non African Americans (we will call that interaction terms.) Try to develop your analysis so that it considers all the cases, even if the relationship doesn't apply equally to them. As a rule always consider alternative measures of both the dependent and independent variables.

You might also like