NOTE: Here are seven examples of past Research Methods tests. They are merely illustrations of the types of tests that I give. The specific questions may already be outdated and obsolete.

RESEARCH METHODS, TEST 1 (Latest sample)

RESEARCH METHODS, TEST 1 (2003 class)

Answer ALL of the following questions, and answer fully in the detail requested.

1. (10 points) What are the six characteristics of the behavioral (scientific) era in the discipline of political science? Explain why each characteristic is important to researchers by giving an example of a study for each one, and explain how that characteristic is relevant to that study.

            2. (10 points) What are the four characteristics of a "good theory" according to the lecturer? Now briefly outline one relevant theory of your choice (such as explaining election outcomes, how people vote, turnout, religiosity), and discuss how it operates. Is your theory a "good theory" using the four characteristics mentioned already, and discuss separately each characteristic as applied to this theory?

            3. (10 points) What is the unit of analysis for each of the following studies? One word answers for each of the ten studies are desired. The answer choices are: individual, county, state, nation.

            A. A study of income differences across the 50 states, based on the following data on each state: household income; unemployment rate; high school dropout rate; college graduation rate.

            B. A study of domestic abuse in Mississippi, based on a sample of 600 individuals asking each of them: have you ever struck your spouse; are you unemployed; how often do you drink alcoholic beverages; what is your income.

            C. A study of the 2004 intended presidential vote of Mississippians based on a statewide sample of 1000 individuals, asking each person their intended vote between Republican Bush and Democrat Clark, their party identification, their ideology, their income, and their race.

            D. A study of the AIDS epidemic worldwide, drawn from the following information on each nation: percentage of adult population having AIDS; number of doctors per capita; health care expenditure per capita; percentage of schools teaching sex education; percentage of the population that is of the Islamic faith.

            E. A study of the quality of higher education in America, based on the following data on each state: number of faculty publications in academic journals; number of students winning national scholarships like the Rhodes and Truman; state spending on higher education per capita.

            F. A study of how each nation in the world deals with repeat sex offenders and the effectiveness of their practices, based on the following information about each nation: a penalty "harshness" measure for each country, ranging from a low score for probation or community service to a medium for a jail term to a high score for the death penalty; the sex crime per capita crime rate for each country; estimated distribution of sexually-explicit material per capita in each nation.

            G. A study of the business climate in Mississippi and what factors encourage a business to move into or stay in a particular county, based on the following information about each of the state's 82 counties: change in the number of jobs in the county over the past four years; change in the property and income tax level for a $1 million dollar business over the past four years; change in the percentage of workers over the age of 25 who hold a college degree; change in the costs of doing business per 100 workers over the past four years, such as workman’s compensation, health, and social security contributions made by employers.

            H. A study of rising crime in Mississippi, based on a public opinion poll of 1000 Mississippi adults, asking each person the following questions: how many times have you been victimized in the past five years; what county do you live in; what is your income level; do you own a firearm.

I. A study of voter turnout in Mississippi, based on the following information on each of the state's counties: percentage of adult population of each county that voted in the 2002 Congressional election; percentage of adult population that is registered to vote; extent of party organization activities designed to mobilize voters, drawn from the NSF Grassroots Party Activists project of 2001; mean educational level of each county; mean income level in each county.

            J. A national study of domestic violence in America, based on a survey of all 50 states obtaining the following information from each state: reported number of criminal convictions for domestic abuse per one thousand married couples; reported consumption level of alcoholic beverages per capita; unemployment rate in each state; percentage of each state’s population over the age of 25 that holds a college degree.

            4. (10 points) What is the level of measurement of each of the following indicators? One word answers for each of the 10 items are desired-- nominal, ordinal, interval.

A. In what state were you born?

B. What former governor of Mississippi do you believe was the greatest leader that the state had? Cliff Finch, William Winter, Bill Allain, Ray Mabus, or Kirk Fordice.

C. Do you strongly agree, agree, disagree, or strongly disagree with the following statement: The American war against Iraq was an immoral war.

            D. What is your age?

            E. Compared to our current expenditures, do you think that more, less, or about the same should be spent on public higher education in Mississippi?

            F. What is your salary in your current job?

            G. What public program do you consider most important when it comes to funding priorities: health, education, welfare, police, highways, or economic development?

            H. How satisfied are you with the education you are receiving at Mississippi State University? Pretty well satisfied, more or less satisfied, or not satisfied at all?

I. If the Democratic presidential primary was held today, whom would you vote for? Wesley Clark, Howard Dean, Dick Gephardt, John Kerry, Joe Lieberman, or Al Sharpton?

            J. How many years of formal education have you completed?

5. (10 points) A department head of a state agency is concerned about the extent to which agency workers are satisfied with their jobs. She creates a worker satisfaction scale that seeks to measure the extent to which her employees are satisfied with their jobs. It ranges from 1 for low satisfaction to 3 for high satisfaction, with 2 being a medium level of satisfaction. She then has an independent company (which guarantees the employees anonymity) conduct a test‑retest of the scale=s reliability by determining workers= scores on the scale in September 2003 and then December 2003. One hundred workers were measured at both time points.

NOTE: Cell entries in the table below are the numbers of workers who gave the listed combination of responses in September and December, 2003.

Examining the table below, is this worker satisfaction scale a "reliable" indicator? Why or why not? Defend your answer mathematically, and by relying on the verbal definition of reliability.

WORKER SATISFACTION SCORES IN SEPTEMBER 2003

            6. (10 points) A researcher is concerned about potential validity problems with a seven point reputed gubernatorial leadership scale. The scale's categories are: very strong leadership, moderate strong leadership, moderate high leadership, moderate leadership, moderate low leadership, moderate weak leadership, and very weak leadership. She relates this reputed leadership scale to more well established indicators asking about a governor's ability to inspire others, to motivate others, personal drive, vision for the state, and personal ambition. Each of the cell entries indicates the percentage of average Mississippians polled who fell in the listed category of the reputed gubernatorial leadership scale, who indicated that they believed that the governor possessed that specific characteristic listed at the left.

REPUTED LEADERSHIP SCALE SCORE

Note: Each of the seven columns indicates the seven categories of the questionable reputed gubernatorial leadership scale. Each of the five rows indicates how Mississippians polled rated the governor on each of five well established leadership criteria. Each of the five well established criteria are simple yes or no responses. For instance, does the governor inspire others, yes or no. Therefore, the 98% at the extreme top left indicates that among those classified as “very Strong” on the reputed gubernatorial leadership scale, 98% of them rated the governor as able to inspire others. Hint: In searching for validity problems, read across each row.

Using this construct or criterion validity test, are there any validity problems with this 7 point scale of reputed gubernatorial leadership. If so, what does the problem involve, and how could you determine that a problem existed? Address each of the five well-established indicators separately, and circle pairs of problem categories in each row.

7. (10 points) What are the five hypotheses in the following model? Write out each of these five hypotheses, and use scientifically precise language for each hypothesis. The four variables are coded as follows: Sex is male or female; Income Level is high, medium, or low; Political Knowledge is high, medium, or how; Trust in State Officials is high, medium, or low.

INCOME LEVEL (High)                                                                                                                     

SEX (Men)                                                                                    TRUST STATE OFFICIALS (High)                                                                  

POLITICAL                                                                        KNOWLEDGE                                                                                (High)                                                                                                                                                                               

8. (10 points) What are the strengths and weaknesses of in‑person, mail, and telephone surveys, and use complete sentences? Make sure you cite at least twelve factors, and try to have at least four items for each of the three types of surveys.

9.  (4 points) When do you have the MOST sample error? Circle the correct category.

A) 600 people sampled, sample is split 90-10 in responses on key question asked.

B) 600 people sampled, sample is split 50-50 in responses on your key question asked.

C) 1500 people sampled, sample is split 90-10 in responses on key question asked.

D) 1500 people sampled, sample is split 50-50 in responses on key question asked.

10. (6 Points) List the six demographic groups cited by the lecturer that tend to be under represented by telephone surveys such as the Mississippi Poll. No explanation beyond this listing is required.

11. (10 points) Circle the correct responses on each of the following five questions about the articles assigned for class. No discussion is required, but make sure that you carefully circle only one response for each of the five questions.

A. Which of the following conclusions was reached in “The Troublesome Cleft: Public Administration and Political Science,” by Whicker, Strickland, and Olshfski?

1.                  Public administration offers the political science researcher a more thorough training in scientific rigor than currently exists in political science.

2.                  Knowledge of concepts used in political science, such as power, justice, equity, conflict, and policy, is useful for public managers.

3.                  Public administration is NOT an interdisciplinary hybrid, as it relies solely on public administration concepts and methods

4.                  Political science has reached a consensus about a single, key concept which they use as their dependent variable 

5.                  All of the above are true

B.  The article examining the incidence of casino gaming taxes, authored by William C. Rivenbark and Bradley R. Rounsaville, conducted a statewide opinion poll in order to study casino gambling in which state?

1.                  Illinois

2.                  New Jersey

3.                  California

4.                  Nevada

5.                  Mississippi

C. The article that studied a community services attitudes scale, authored by Ann Harris Shiarella, Anne M. McCarthy, and Mary L. Tucker, and published in the journal Educational and Psychological Measurement, used what methodology?

1.      Development and construct validity

2.      Content analysis

3.      A panel design

4.      Aggregate data

5.      A nonrecursive path analysis

D.  The article on “A National Study of Gender-Based Occupational Segregation in Municipal Bureaucracies: Persistence of Glass Walls,” authored by Will Miller, Brinck Kerr, and Margaret Reid, tested what theory?

1.      Graham Allison’s models of rational, organizational, and bureaucratic behavior

2.      Susan Welch’s feminist theory of socialization, structural, and situational forces

3.      Theodore Lowi’s theory of distributive, regulatory, and redistributive functions and agencies

4.      Aaron Wildavsky’s incremental model of budgeting and personnel administration

5.      Aage Clausen’s typology of economic management, social welfare, and agricultural policy areas

E. In the article, “What Do Administrators Think Citizens Think? Administrator Predictions as an Adjunct to Citizen Surveys,” by Julia Melkers and John Clayton Thomas, what city was studied?

1.      New Orleans

2.      Memphis

3.      Miami

4.      Atlanta

5.      Detroit

RESEARCH METHODS, TEST 1 (First sample)

RESEARCH METHODS, TEST 1 (2001 class)

1. (10 points) What are the six characteristics of the behavioral era? Explain why each is important to researchers by giving an example of a study for each one.

2. (10 points) What are the four characteristics of a "good theory," according to the lecturer? Now briefly outline one theory and discuss how it operates (such as explaining election outcomes, how people vote, turnout, religiosity). Is your theory a "good theory" using the four characteristics mentioned already, and discuss separately each characteristic as applied to this theory?

3. (5 points) What is the definition of a panel design? What are the four problems with panel studies, and very briefly explain each?

4. (5 points) What is the definition of the ecological fallacy? Give an example of the ecological fallacy.

5. (5 points) What is the unit of analysis for each of the following studies? One word answers for each of the ten studies is fine-- individual, county, state, nation.

A) A study of world terrorism that uses the following information about each nation: number of terrorist deaths per capita; per capita income of the nation.

B) A study of Bush's job approval rating after the terrorist bombings, based on a national survey of 1500 individuals, asking each person what their party identification is, what their ideology is, and whether they approve or disapprove of Bush's job performance.

C) A study of wetland and forest preservation in Mississippi, based on information drawn from each of 82 counties, ascertaining: number of forest/wetland acres in the county; number of such acres open to timber operations; number of such acres open to farming.

D) A study of electoral use of military base closures, based on information from each of 50 American states: number of military personnel in the state; number of votes cast for Bush in the 2000 presidential election; party composition of the state's congressional delegation.

E) A study of American support for a war against terrorism, based on a survey of 1000 Americans across the nation, asking each of them how much of a threat they perceive from terrorism, whether they support military action against countries harboring terrorists, and how many casualties they would be willing to suffer in a war.

6. (10 points) What is the level of measurement of each of the following indicators? One word answers for each of the 10 items is fine-- nominal, ordinal, interval.

A) How do you use the land that you own? For tree harvesting, farming, or hunting.

B) How much money (in dollars) did you lose in the stock market crash after the terrorist bombings?

C) If you were the state economic development chief in Mississippi, what would be the first country that you would court to help bring jobs to the state: Japan; Germany; Britain; China; or Italy?

D) How satisfied are you with President Bush's reaction to the terrorist bombings? Are you very satisfied, somewhat satisfied, or somewhat dissatisfied, or very dissatisfied?

E) How many years have you lived in Mississippi?

F) Do you describe yourself politically as very liberal, somewhat liberal, moderate, somewhat conservative, or very conservative?

G) How many hours a week do you watch television news programs?

H) Is your religion Protestant, Catholic, Jewish, Muslim, or Buddhist?

I) Do you strongly agree, agree, disagree, or strongly disagree with the following statement: In the upcoming war with Afghanistan, if I were President, I would use tactical nuclear weapons if it were necessary to prevent the loss of many American lives.

J) How proud are you to be an American citizen or resident? Very proud, somewhat proud, or not very proud?

7) (10 points) A state public personnel manager has formed a government employee workplace satisfaction scale that seeks to measure the extent to which state workers are satisfied with their jobs. It ranges from 0 for low satisfaction to a 10 for high satisfaction. The scale categories are then combined into three groups, defined as low, medium, or high workplace satisfaction. She then conducts a test-retest of the scale's reliability by determining workers' scores on the scale in September of this year and then in November. One thousand workers were measured at both time points.

NOTE: Cell entries in the table below are the numbers of people who gave the listed combination of responses in September and in November.

Examining the table below, is this workplace satisfaction scale a "reliable" indicator? Why or why not? Defend your answer mathematically, and by relying on the verbal definition of reliability.

WORKPLACE SATISFACTION SCORES IN SEPTEMBER

8. (10 points) Another researcher has employed a workplace dissatisfaction scale based solely on attitudinal data, asking state workers' opinions regarding how they feel about their boss, coworkers, salary, and other working conditions. She is concerned over whether her scale has any validity problems. Her workplace dissatisfaction scale is a 7-point scale ranging from very low dissatisfaction to very high dissatisfaction. She conduct a construct or criterion validity test by examining the behavior of people in each category of her workplace dissatisfaction scale. She is interested in turnover (percentage of workers who quit their job each year), absenteeism (number of work days per month missed), theft (dollar value of missing equipment and supplies per worker), equipment misuse (hours per day spent in unauthorized e-mail and Internet use), and tardiness (average number of work days per month where workers arrive at work late or leave early).

Do any validity problems exist with the researcher's attitudinal scale of workplace dissatisfaction? If so, indicate specifically where each problem is for each of the behavioral indicators.

WORKPLACE DISSATISFACTION SCALE

	very low	low	medium low	medium	med-ium high	high	very high
Turnover (% quit)	5	30	25	40	60	55	70
Absenteeism (days per month)	1	2	3	4	8	7	10
Theft (in dollars)	0	10	5	18	25	35	50
Misuse (in daily hours)	0	.4	.6	1.1	1.3	1.7	2
Tardiness (days per month)	1	4	2	5	8	6	9

Note: each column indicates the five behaviors of workers who have the score on the attitudinal workplace dissatisfaction scale listed at the top. In searching for validity problems, read across each row.

9. (10 points) What are the strengths and weaknesses of in-person, mail, and telephone surveys, and use complete sentences?

10. (4 points) When do you have the LEAST sample error? Circle the correct category.

A) 600 people sampled, sample is split 50-50 in responses on your key question asked

B) 1500 people sampled, sample is split 50-50 in responses on key question asked

C) 600 people sampled, sample is split 90-10 in responses on key question asked

D) 1500 people sampled, sample is split 90-10 in responses on key question asked

11. (6 points) List the six demographic groups cited by the lecturer that tend to be under represented by telephone surveys such as the Mississippi Poll, and why is each under represented?

12. (10 points) In chapter 5 of the textbook on probability sampling, what is the definition of a probability sample? What are the four types of probability samples, and fully explain each? One type is divided into proportionate and disproportionate. Which type of probability sample is it, and explain how these two sub-types differ from each other?

13. (5 points) What are the five hypotheses in the following model? Write out each of these five hypotheses, and use the correct language for each hypothesis.

----------------------------------------------------------------------> INCOME ------------------------------------------------------------------------V

----------------------------------------------------------------------> (High)-----------------------------------------------------------------------------V

AGE --------------------------------------------------------------------------------------------------------------------------------------------------->PARTY

(older)-----------------------------------------------------------------------------------------------------------------------------------------------> IDENTIFICATION

------------------------------------------------------------------------------------------------------------------------------------------------------------(Republican)

----------------------------------------------------------------------->IDEOLOGY----------------------------------------------------------------------^

----------------------------------------------------------------------->(Conservative)--------------------------------------------------------------------^

RESEARCH METHODS, TEST 1 (Second sample)

1. (10 points) What are the characteristics of the scientific era (behavioral era, 1945 to present), and explain each? Give an example of each of these characteristics, and explain each characteristic's significance.

2. (10 points) What are the four characteristics of a "good theory" according to the lecturer? Now briefly outline one theory and discuss how it operates (such as groupthink, religiosity, voting behavior, etc.). Is your theory a "good theory" using the four characteristics mentioned already, and discuss separately each characteristic as applied to this theory?

3. (10 points) What is the unit of analysis for each of the following studies? One word answers for each of the ten studies is fine-- individual, county, state, nation.

A. A study of the willingness of Mississippians to vote for a qualified woman as Lieutenant Governor, based on a public opinion poll of 600 adult Mississippians asking each of them that question, what their party identification and personal ideology is, and what their age and education is.

B. A study of the effectiveness of motor voter registration, based on the following information about each of the fifty states: change in voter turnout after motor voter was enacted; which political party controls the governorship; which political party controls the state legislature; percentage of state population that is African-American.

C. A study of the cost effectiveness of the county unit system of road construction, based on the following information about each of the state's 82 counties: number of miles constructed last year; total expense of road construction last year; whether the county operates under the county unit system, or whether it operates under the "beat" system.

D. A study of political instability in the world, based on the following information about each nation: the number of years that the current chief executive has been in office; unemployment rate; change in per capita personal income; other factors.

E. A study of the quality of health care in the American states, based on the following information about each state: average life span; government expenditures on health care per capita; poverty rate in each state; extent of physical fitness classes in the public schools.

F. A study of the causes of President Clinton's high job approval rate, based on a national survey of 1500 Americans asking each of them to rate the President's job in office, what their party identification is, how they would rate the health of the American economy, how their own personal financial situation has changed over the past year, and how they would rate the character of Bill Clinton.

G. A study of world famine, based on the following information drawn from each nation: percentage of population that has died of starvation in the past year; presence of absence of civil war in each nation; per capita income of each nation; weather conditions over the past year.

H. A study of highway safety in Mississippi, based on the following information about each county: number of highways deaths last year adjusted for county population; number of law enforcement vehicles actively patrolling the highways; average age of the average car in each county; per capita alcohol consumption in each county.

I. A study of the quality of American universities, based on the following information from each state: percentage of college students who graduate within six years; average starting salary of college graduates; percentage of state population over 25 years of age that has a college degree; state government expenditure on public higher education institutions, adjusted for number of students; presence of absence of a merit system for evaluating the performance of faculty.

J. A study of race relations in Mississippi based on the following public opinion poll conducted among 600 adult residents, asking each of them: how would you rate the quality of race relations in Mississippi; what is your race, party identification, and ideology; have you ever been a victim of police brutality.

4. (10 points) What is the level of measurement of each of the following indicators? One word answers for each of the 10 items is fine-- nominal, ordinal, interval.

A. How many women do you think that Bill Clinton has had sexual relations with since he was elected President?

B. Which of the following people do you most admire? Bill Clinton, Hillary Clinton, Kenneth Starr, Newt Gingrich, Trent Lott.

C. How would you rate the honesty and integrity of President Bill Clinton? Excellent, good, fair, or poor?

D. Where do you think that most of our state taxes should be spent? On health care, police forces, elementary and secondary education, higher education, welfare, prison construction.

E. Do you strongly agree, agree, disagree, or strongly disagree with the following statement: America is a racist nation.

F. What score did you get on the GRE exam?

G. Last month, what was your take home pay, after taxes and benefits were deducted from your paycheck?

H. Where do you get most of your information about national news from? Newspapers, television, radio, news magazines, the internet, conversations with other people.

I. How frequently do you vote in state elections? Always, most of the time, only some of the time, or rarely.

J. How high do you think that taxes are in Mississippi? Very high, somewhat high, about right, somewhat low, very low.

5. (10 points) Political scientists have formed a political trust scale that seeks to measure the extent to which people feel trustful towards public officials. It ranges from 0 for low trust to 4 for high trust. One researcher conducts a test-retest of its reliability by determining people's scores on the scale in March and in September. One thousand people were measured at both time points.

POLITICAL TRUST SCORE IN MARCH

NOTE: Cell entries are the numbers of people who gave the listed combination of responses in March and in September.

Is this political efficacy scale a "reliable" indicator? Why or why not? Defend your answer mathematically, and by relying on the verbal definition of reliability.

6. (10 points) 5. (10 points) A member of the mayor's staff is interested in public attitudes toward local spending programs. She conducts a public opinion poll asking citizens whether the local government should be spending more, less, or about the same on the following programs:

a) Police forces

b) Ambulance service

c) Public elementary school

d) Public junior high school

e) Public high school

f) City parks

g) City sportsplex recreation center

She theorizes that public attitudes toward government spending constitute a single dimension of liberalism versus conservatism--that a citizen either tends to support local government spending in general or oppose it in general. She therefore forms a summary local spending scale by combining each person's score on each of these seven indicators, believing that all seven questions measure the same concept or dimension.

A political science researcher believes that there may be a validity problem with a single scale of local spending. She argues that there may be different components of local spending, and that some citizens may support government spending on some types of issues but not on others. She generates a correlation matrix to study how peoples' responses on the seven indicators are interrelated.

CORRELATION MATRIX

Is there any validity problem with forming a single scale that combines all seven indicators of local spending into a local spending scale, as the first researcher did? If so, what is the problem? Explain and discuss your answer, and refer to specifics in the correlation matrix. In your answer discuss how many dimensions of attitudes toward local spending there are, how you can determine that, and what they appear to pertain to.

7. (10 points) A researcher is concerned about potential validity problems with a seven point reputed presidential leadership scale. The scale's categories are: very strong leader, moderately strong leader, moderately high leader, moderate leader, moderately low leader, moderately weak leader, very weak leader. She relates this reputed leadership scale to more well established indicators asking about a president's reputed ability to inspire others, ability to motivate others, personal drive, vision for the nation, and personal ambition. Each of the cell entries indicates the percentage of the people in the listed category of the reputed presidential leadership scale that indicate that they believe that the President possesses that particular characteristic.

REPUTED LEADERSHIP SCALE SCORE

Are there any validity problem with this 7 point scale of reputed presidential leadership scale. If so, what does the problem involve, and how could you determine that a problem existed? Address each of the five well-established indicators separately.

8. (10 points) What are the strengths and weaknesses of in-person, mail, and telephone surveys, and use complete sentences?

9. (10 points) We discussed the historic problems with polling, and the correlates of sample error in class. What were the three historical problems with polling, and give an example of each? What are the three correlates of sample error, and explain when sample error is greatest for each of the three?

10. (10 points) Chapter 5 of the textbook discusses Sampling. What is the difference between Probability Samples and Nonprobability Sampling Designs, and explain? What are the four types of probability samples, according to the text, and explain each? What are the three types of nonprobability sampling designs, according to the text, and explain each?

RESEARCH METHODS, TEST 1 (Third sample)

1. (10 points) What are the characteristics of the scientific era (behavioral era, 1945 to present), and explain each? Give an example of each of these characteristics, and explain each characteristic's significance.

2. (10 points) What are the four characteristics of a "good theory" according to the lecturer? Now briefly outline one theory and discuss how it operates (such as groupthink, religiosity, voting behavior, etc.). Is your theory a "good theory" using the four characteristics mentioned already, and discuss separately each characteristic as applied to this theory?

3. (10 points) What is the unit of analysis for each of the following studies? One word answers for each of the ten studies is fine-- individual, county, state, nation.

A. A study of the causes of ethnic conflict within nations, based on the following information about each country in the world: number of incidents of ethnic violence last year on a per capita basis; how strong each nation's central government is; how frequently the people of each nation attend religious ceremonies; whether there is a perceived external threat to the nation.

B. A study of the black vote in the 1995 Democratic gubernatorial nomination battle in Mississippi, based on information about each county's racial composition and its support for Molpus and Fordice.

C. A study of gender inequality worldwide based on the following information about each nation: the average estimated number of hours that women work more than men in workplace jobs, household work, child and elderly care, and yard work; the percentage of public officials who are men; the percentage of college students who are men; how much higher the average income of men is compared to women.

D. A study of educational progress in America, based on the following information concerning each state: change in the high school dropout rate over a five year period; change in per pupil expenditures by state government over a five year period; change in the divorce rate over a five year period; change in per capita income over a five year period.

E. A study of poverty in America based on the following information about each state: percentage of population living in poverty; unemployment rate of each state; average number of years of formal education completed; divorce rate of each state; teenage pregnancy rate of each state.

F. A study of worker efficiency based on a survey of 100 agency heads in Mississippi, asking each agency head: what percentage of the time are your subordinates actually working; how frequently do you inspect their work; how frequently do you speak to them; how frequently do you evaluate their performance in writing.

G. A study of why Mississippians voted as they did in the 1996 presidential general election, based on a statewide sample of 600 likely voters asking each voter: who they voted for; what was the voter's party identification; which candidate they felt could provide better public policy leadership; which candidate was more conservative on issues.

H. A study of teenage pregnancy in Mississippi based on the following information about each county: teenage pregnancy rate; percentage of students completing a sex education program; per capita income level of the county; percentage of students who are college bound.

I. A study of the incidents of highway fatalities in America, based on the following information about each state: number of highway deaths per highway miles driven; gallons of alcohol consumed per person last year in each state; number of traffic tickets written per capita last year; number of days of bad weather last year.

J. A study of alcoholism in America, based on a national survey of 1500 adults asking each person how frequently they drink alcoholic beverages, whether they are currently unemployed, whether they are divorced or experiencing marital difficulties, and what their income level is.

4. (10 points) What is the level of measurement of each of the following indicators? One word answers for each of the 10 items is fine-- nominal, ordinal, interval.

A. What county were you born in?

B. What is your age?

C. Currently, Mississippi maintains eight public universities? How many public universities do you think that the state ought to maintain?

D. What public program do you consider most important when it comes to funding priorities: health, education, welfare, police, highways, or economic development?

E. How satisfied are you with the education you are receiving at Mississippi State University? Pretty well satisfied, more or less satisfied, or not satisfied at all?

F. What recent American President do you most admire? Jimmy Carter, Ronald Reagan, George Bush, or Bill Clinton?

G. How would you rate the job performance of Senator Trent Lott? Excellent, good, fair, or poor?

H. If the Democratic gubernatorial primary was held today, whom would you vote for? Ray Mabus, Mike Moore, or Ronnie Musgrove?

I. How many years of formal education have you completed?

J. In politics today, do you consider yourself very liberal, somewhat liberal, middle-of-the-road, somewhat conservative, or very conservative?

5. (10 points) Political scientists have formed a political interest scale that seeks to measure the extent to which people feel interested in political matters. It ranges from 0 for low interest to 2 for high interest. One researcher conducts a test-retest of its reliability by determining people's scores on the scale in January and in March. Three hundred people were measured at both time points.

POLITICAL INTEREST IN JANUARY

MARCH POLITICAL INTEREST	LOW	MEDIUM	HIGH		MARGINALS
LOW	90	10	0		100
MEDIUM	10	80	5		95
HIGH	0	10	95		105
MARGINALS	100	100	100		300

Is this political efficacy scale a "reliable" indicator? Why or why not? Defend your answer mathematically, and by relying on the verbal definition of reliability.

6. (10 points) A researcher is concerned about potential validity problems with a seven point ideological identification scale. The scale's categories are: strong liberal, moderate liberal, weak liberal, pure moderate, weak conservative, moderate conservative, and strong conservative. She relates this ideology scale to two theoretically relevant scales--feeling thermometers of attitudes toward liberals Ted Kennedy and Bennie Thompson, and conservatives Trent Lott, Newt Gingrich, and Dick Armey. The scales range from 0 for greatly dislike the political figure to 100 for greatly like them. Do you see any validity problems with this ideological self-identification scale, and if so what pairs of categories may be characterized by problems? Circle the pairs of categories that have validity problems; for each line, circle the numbers in adjacent categories that have validity problems.

Note: cell entries are means or average feeling thermometer ratings for each ideology category.

	Strong Liberal	Moderate Liberal	Weak Liberal	Pure Moderate	Weak Conser-vative	Moderate Conser-vative	Strong Conser-vative
Kennedy	98	85	90	60	35	45	20
Thomp-son	90	87	80	55	20	30	5
Lott	20	30	28	50	80	73	95
Gingrich	5	25	15	45	60	75	90
Armey	7	15	30	45	75	65	85

7. (12 points) What are the strengths and weaknesses of in-person, mail, and telephone surveys, and use complete sentences?

8. (8 points) What demographic groups tend to be undersampled in telephone surveys like the Mississippi Poll, according to the lecturer? Explain why each one is undersampled.

RESEARCH METHODS, TEST 1 (Fourth sample)

1. (10 points) What were the six characteristics of the behavioral period of the discipline of political science, according to the lecturer, and explain? On what grounds did the traditionalists and post-behavioralists attack behavioralism, and discuss?

2. (10 points) What are the four components of a "good theory," according to the lecturer, and elaborate? Now focus on one of the two theories outlined in the readings, pertaining to Presidential Character or Groupthink. Propose three specific hypotheses based on this theory, and clearly specify the independent and dependent variables in each case. Is this theory a "good theory" or a bad theory, and defend your answer?

3. (10 points) What is the unit of analysis of each of the following studies? Is it the individual, county, state, or nation?

A. A study of how each nation in the world deals with repeat sex offenders and the effectiveness of their practices, based on the following information about each nation: a penalty "harshness" measure for each country, ranging from a low score for probation or community service to a medium for castration to a high score for the death penalty; the sex crime per capita crime rate for each country; estimated distribution of sexually-explicit material per capita in each nation.

B. A study of the expected presidential vote, based on a national survey of 1500 likely voters, asking each person their party identification, their ideology, their perception of the economy, and whether they intend to vote for Dole or Clinton.

C. A study of the business climate in Mississippi and what factors encourage a business to move into or stay in a particular county, based on the following information about each of the state's 82 counties: change in the number of jobs in the county over the past ten years; change in the property tax level for a $1 million dollar business over the past ten years; change in the percentage of workers over the age of 25 who hold a college degree.

D. A study of racism in America based on the following information about each of the 50 states: percentage of black churches in each state that are the targets of arson over the past five years; percentage of the white population that are estimated to be members of white supremacy groups in each state; average educational level of the state's population; state unemployment rate.

E. A study of rising Republicanism in Mississippi, based on a public opinion poll of 600 Mississippi adults, asking each person the following questions: what is your party identification; what is your ideology; what is your income level; how strongly do you favor or oppose affirmative action policies.

F. A study of welfare reform policies across America, drawn from the following information about each of the 50 states: average monetary payment to a family of four per month; percentage of the population receiving welfare; number of years after which welfare payments are cut off; whether unwed teenagers are required to live with their parents or be enrolled in school in order to receive the payment.

G. A study of drug use worldwide, based on the following information about each nation: percentage of adult population in each country estimated to be regular drug users; percentage of governmental budget spent on drug education, prevention, and rehabilitation programs; unemployment rate of each nation; divorce rate of each nation; percentage of each country's population living below the poverty level.

H. A study of voter turnout in Mississippi, based on the following information on each of the state's counties: percentage of adult population of each county that voted in the 1995 gubernatorial election; percentage of adult population that is registered to vote; extent of party organization activities designed to mobilize voters, drawn from the NSF Grassroots Party Activists project; mean educational level of each county; mean income level in each county.

I. A national study of addiction to cigarettes, based on the following information about each state: reported number of lung cancer and relevant heart disease deaths in the state; expenditure of the state medicaid program by the state on smoking-related illnesses; estimated percentage of children under age 18 who regularly smoke; advertising budget of cigarette companies spent in each state. J. A national study of domestic violence, based on a survey of 1,000 married men, asking each of them: whether they have ever shoved or slapped their wives; whether their fathers' had ever slapped or pushed their mothers; how many times they had been unemployed; how frequently they drank alcoholic beverages.

4. (10 points) What is the level of measurement of each of the following indicators, as discussed in class? Is it nominal, ordinal, or interval?

A) Do you strongly agree, agree, disagree, or strongly disagree with the following statement? An adult should have the right to marry any adult that they wish, regardless of whether the person is of the same or different sex from their own.

B) How many parking tickets and traffic tickets have you received over the past five years?

C) Whom do you plan to vote for in the upcoming presidential election? Bill Clinton? Bob Dole? Ross Perot; or the Natural Law candidate?

D) How much money do you think that people should be fined for repeated failure to use their seat belts?

E) What Mississippi governor do you most admire? William Winter? Bill Allain? Ray Mabus? Or Kirk Fordice?

F) What is your political ideology? Very liberal? Somewhat liberal? Moderate? Somewhat conservative? Or very conservative?

G) How frequently do you read the newspaper? Always? Most of the time? Some of the time? Or rarely?

H) What county are you currently living in?

I) What is your salary in your current job?

J) Compared to our current expenditures, do you think that more, less, or about the same should be spent on public elementary and secondary education?

5. (10 points) A member of the Governor's staff is interested in public attitudes toward state spending on public programs. She conducts a statewide public opinion poll asking citizens whether state government should be spending more, less, or about the same on the following programs:

a) Police forces

b) Elementary and secondary education

c) Corrections (prisons)

d) Medicaid

e) Higher education

f) State employees health care plan

She theorizes that public attitudes toward government spending constitute a single dimension of liberalism versus conservatism--that a citizen either tends to support government spending in general or oppose it in general. She therefore forms a summary state policy "ideology" scale by combining each person's score on each of these six indicators, believing that all six questions measure the same concept or dimension.

A political science researcher believes that there may be a validity problem with a single scale of state policy ideology. She argues that there may be different components of state spending, and that some citizens may support government spending on some types of issues but not on others. She generates a correlation matrix to study how peoples' responses on the six indicators are interrelated.

CORRELATION MATRIX

	Police	Elem-Sec. Education	Corrections	Medicaid	Higher Education	Health Plan
Police	1.0
Elem-Sec. Education	.07	1.0
Corrections	.95	.11	1.0
Medicaid	.10	.05	.03	1.0
Higher Education	.02	.89	.12	0	1.0
Health Plan	.15	.05	.08	.85	.04	1.0

Is there any validity problem with forming a single scale that combines all six indicators of state spending into a state public policy ideology scale, as the first researcher did? If so, what is the problem? Explain and discuss your answer, and refer to specifics in the correlation matrix. In your answer discuss how many dimensions of attitudes toward state spending there are, how you can determine that, and what they appear to pertain to.

6. (10 points) Some political scientists have questioned the validity of an internal political efficacy scale. They test its validity by conducting criterion validity tests--relating the political efficacy indicator to measures of political behavior, such as whether one voted in the last election (turnout), extent of any activity in political campaigns (campaigns), whether one regularly contacts public officials and makes their views known about issues (contacting), and whether one is involved in community organizations to improve the community (communal activity).

POLITICAL EFFICACY LEVELS

	Very High	Medium High	Slightly High	Slightly Low	Medium Low	Very Low
Turnout	85%	80%	70%	45%	50%	30%
Campaigns	40%	25%	30%	15%	10%	5%
Contacting	50%	30%	40%	20%	25%	10%
Communal	65%	50%	55%	30%	40%	20%

NOTE: Cell entries are the percentage of people with each of the six listed levels of political efficacy who are high in political activity. These are hypothetical data.

Is there any validity problem with this 6 point scale of political efficacy. If so, what does the problem involve, and how could you determine that a problem existed? Address each of the four well-established indicators separately.

7. (10 points) A political researcher has devised two indicators of political trust. Indicator A asks people whether they believe that public officials are honest and trustworthy. Indicator B asks people whether they believe that public officials are hard working and intelligent. The researcher wants to select the most reliable indicator of political trust, so she conducts a test-retest reliability test of each indicator in March and June. Each indicator was divided into three categories--low, medium, and high political trust.

For Indicator A, 400 respondents were low in trust at both time points; 80 were low in March and medium in June; 20 were low in March and high in June; 50 were medium in March and low in June; 350 were medium in both months; 100 were medium in March and high in June; 20 were high in March and low in June; 70 were high in March and medium in June; 410 were high in trust in both months.

For indicator B, 175 were low in trust in both months; 165 were low in March and medium in June; 160 were low in March and high in June; 180 were medium in March and low in June: 155 were medium in both months; 165 were medium in March and high in June; 150 were high in March and low in June; 200 were high in March and medium in June; 150 were high in trust in both months.

Construct two contigency tables- one for each indicator- showing the relationship between people's political trust responses at each time point. Which indicator is most reliable, and which is least reliable, and explain and defend your answer?

8. (10 points) What are the strengths and weaknesses of personal, mail, and telephone surveys, and discuss fully? Name at least two strengths and two weaknesses of each of these three methods of survey research.

9. (10 points) Chapter 1 of the text discusses Approaches to Knowledge, and the Basic Assumptions of Science. What are the three approaches to knowledge, and the six basic assumptions of science, as discussed in the text, and briefly explain each?

10. (10 points) Chapter 8 of the text discusses sampling and sample design. What is the difference between probability and nonprobability samples, and elaborate? What are four types of probability sample designs, and describe how the sample is selected in each of the four?

11. (10 points) Chapter 11 of the text discusses questionnaire construction. Two aspects of questionnaire construction are the types of questions and avoiding biases in constructing questionnaires. What are the differences between open-ended, closed-ended, and contingency questions, and briefly explain? Give examples of each type of question. Regarding avoiding bias and pitfalls in questionnaire construction, what are the five problems researchers encounter, and briefly explain each?

RESEARCH METHODS, TEST 1 (Fifth sample)

1. (10 points) What are the six characteristics of the behavioral era (1945 to present) in the history of the discipline of political science, and explain each? Give an example of each of these characteristics, and explain its importance.

2. (10 points) Briefly outline one theory and discuss how it operates (such as religiosity, voting behavior, etc.). Now cite three specific hypotheses derived from that theory, and be specific regarding each hypothesis. Is your theory a "good theory" using the four characteristics mentioned already, and discuss separately each characteristic as applied to this theory?

3. (10 points) What is the unit of analysis for each of the following studies? One word answers for each of the ten studies is fine-- individual, county, state, nation.

A. A study of income differences across the 50 states, based on the following data on each state: household income; unemployment rate; educational level.

B. A study of nations' olympic success, based on the following information on each nation: number of gold medalists per capita; GNP; percentage of high income persons; percentage of high schools having sports programs.

C. A study of domestic abuse in Mississippi, based on a sample of 600 individuals asking each of them: have you ever struck your spouse; are you unemployed; how often do you drink alcoholic beverages; what is your income.

D. A study of school quality in Mississippi, based on information from each county: dropout rate in each county; average teacher salary; poverty rate in the county.

E. A study of the intended presidential vote of Mississippians based on a statewide sample of 1000 individuals, asking each person their intended vote, their party identification, their ideology, their income, and their race.

F. A study of racial tensions in Mississippi, based on the following information drawn from each county: reported racial incidents per capita; level of inequality of income distribution between the races; number of churches per capita; African-American percentage of county.

G. A study of the AIDS epidemic worldwide, drawn from the following information from each nation: percentage of adult population having AIDS; number of doctors per capita; health care expenditure per capita; percentage of schools teaching sex education.

H. A study of public attitudes toward Governor Musgrove, based on a public opinion poll of 800 Mississippi residents, asking them to rate the governor's job performance, what their race is, what their party identification is, and their family income.

I. A study of the quality of higher education in America, based on the following data on each state: number of faculty publications in popular science magazines; number of students winning national scholarships like the Goldwater; state spending on higher education.

J. A study of growing Republicanism in Mississippi, based on each county's vote in the 2000 presidential election, % African-American population of each county, median household income in each county.

4. (10 points) What is the level of measurement of each of the following indicators? One word answers for each of the 10 items is fine-- nominal, ordinal, interval.

A. In what state were you born?

B. What is your age?

C. What candidate do you think is the most decisive leader? George Bush, Al Gore, Ralph Nader, or Pat Buchanan?

D. How would you rate the quality of public services in your community? Excellent, good, fair, or poor?

E. How many years of education have you completed?

F. What is your religious denomination? Protestant, Catholic, Jewish, Buddhist, Muslim, or Hindu?

G. Do you strongly agree, agree, disagree, or strongly disagree with the following statement: The death penalty is state murder and should be outlawed in this country.

H. How much did you pay in higher education expenses over the last year?

I. Are your taxes too high, too low, or about right?

J. Where do you get most of your information about the presidential campaign from? Newspapers, magazines, television, radio, the internet, friends.

5. (10 points) Political scientists are interested in devising a reliable indicator of political ideology. They create two indicators of this concept, and use test-retest reliability to determine which is more reliable. A panel study is conducted in 1999 and 2000, and the following results are obtained from the two indicators:

INDICATOR A: A FIVE CATEGORY IDEOLOGY INDICATOR

1999

2000

	very liberal	somewhat liberal	moderate	somewhat conservative	very conservative
very liberal	40	50	30	40	40
somewhat liberal	50	30	40	20	25
moderate	30	40	50	60	55
somewhat conservative	60	45	20	40	45
very conservative	20	35	60	40	35
column N's	200	200	200	200	200

NOTE: Cell entries are the numbers of people who gave the listed combination of responses in March and in September.

INDICATOR B: A THREE CATEGORY IDEOLOGY INDICATOR

1999

2000

	Liberal	Moderate	Conservative
Liberal	150	20	35
Moderate	30	260	65
Conservative	20	20	400
column N's	200	300	500

NOTE: Cell entries are the numbers of people who gave the listed combination of responses in March and in September.

Which of these two indicators is a "reliable" indicator? Explain and defend your answer mathematically, and by relying on the verbal definition of reliability.

6. (10 points) Construct (Criterion) Validity. A researcher is concerned about potential validity problems with a seven point reputed influence or power scale for city council members. The scale's categories are: very influential person; moderately influential; somewhat influential; little influence; no influence. She relates this reputed influence scale to more well established indicators of influence such as: percentage of resolutions introduced by the person that are passed; amount of money allocated to the council member's ward; number of staff members allotted to that council member; column inches of newspaper space received by the council member; popular vote received in the last election. She administers the reputed influence indicator to one hundred city council members in twenty different cities, and then examines how each of the five groups of council members (based on the five categories of reputed influence) fares on the five well established indicators of influence, and obtains the following results:

Are there any validity problems with this 5 point scale of reputed influence. If so, what does the problem(s) involve, and how could you determine that a problem existed? Address each of the five well-established indicators separately.

7. (10 points) What are the strengths and weaknesses of in-person, mail, and telephone surveys, and use complete sentences? You should mention at least 10 points offered by the lecturer.

8. (10 points) What six demographic groups have traditionally been underrepresented in telephone surveys, according to the lecturer, and explain why? What are at least two sources of higher sampling error, and explain?

9. (10 points) Chapter 5 of the textbook discusses Sampling. What is the difference between Probability Samples and Nonprobability Sampling Designs, and explain? What are the four types of probability samples, according to the text, and explain each? What are the four types of nonprobability sampling designs, according to the text, and explain each?

10. (10 points) Question on the reading material.