ASSIGNMENT 1-              

1. Every time we calculate a statistic while doing inferential statistics, we lose one degree of freedom

A. True

B. False

2. What is the term used to describe a distribution of scores created by drawing an unlimited number of samples of 20 scores from a population, computing the mean for these scores and plotting means?

A. Sampling distribution

B. Standard distribution

C. Sampling distribution of the mean

D. Sampling distribution of the difference between two means

3. A director of a large child-care center decides to train all her teachers in the use of CPR. The Red Cross is invited to provide the training to the teachers. To assess the teachers' increase in knowledge of CPR, the Red Cross suggests that all teachers complete a competency test before and after the training program. After completing the pretest, the teachers participated in a two- day CPR training program. After the training, they again completed the CPR competency test. Which t-test would be appropriate

A. One sample t-test

B. Independent t-test

C. Paired t-test

D. A t-test would be inappropriate

4. Which of the following is needed to use the t- test for independent samples?

A. One group

B. A series of observations and treatments of a single subject

C. Two groups

D. Two variables

5. A negative t statistic only occurs when you have made a mistake in calculations.

A. True

B. False

6. Which of the following is a correct interpretation of a significant t-test result when comparing two mean scores using an alpha level of .05?

A. There is less than a 5% chance the observed difference is due to chance

B. There is less than a 5% chance the observed difference is a result of the treatment

C. There are no differences between the means

D. There are differences between the means but they are caused by sampling errors

7. How does the shape of the t distribution change as the sample size increases?

A. It becomes broader

B. It becomes skewed

C. It becomes flatter

D. It becomes more normal looking

8. A one-tailed hypothesis makes it harder to reject the null hypothesis

A. True

B. False

9. A researcher should select the level of significance for their study ____ the sample data are collected.

A. Before

B. After

10. A researcher wants to determine if there is a difference between two educational techniques on math scores. Class A is taught using one technique and Class B is taught using a different technique. Shapiro Wilks test had a p = .001; histograms of Class A shows a negative skew and Class B shows a positive skew. Which test would be appropriate?

A. Independent t test

B. Paired t test

C. Wilcoxon

D. Mann Whitney U

E. None of the above

11. In addition to knowing about statistical significance of your data, it is important to know about effect size, the strength of the relationship between your variables.

A. True

B. False

12. Researchers want to test the hypothesis that men with coronary heart disease have similar cholesterol values (interval/ratio) to the general population. The average serum cholesterol value for the general population is known to be 185 mg/dl. Indicate what type of t-test is appropriate:

A. One sample t-test

B. Independent t-test

C. Paired t-test

D. A t-test would be inappropriate

13. The calculated t can be compared against criterion that comes from a statistical table. This is called:

A. Critical value or deviate

B. Test Statistic

C. Alpha

D. Beta

E. Threshold value

14. The larger the value of our obtained t:

A. The more probable that our results are due to chance alone.

B. The less probable that our results are due to chance alone

C. The larger our critical t-value.

D. The larger the probability of making a Type 1 error.

15. In an investigation of the pharmacodynamics of digoxin, serum digoxin levels measured at interval ratio level) were determined in 50 males and 50 females (all healthy and between 20- 45 years old) 4 hours after rapid intravenous injection of the drug. The researchers want to know if there is any evidence of gender differences. Indicate what type of t -test is appropriate:

A. One sample t -test

B. Independent t -test

C. Paired t-test

D. A t-test would be inappropriate

16. Under which circumstance is the null hypothesis, that "there is no difference in means between two groups", more likely to be rejected?

A. When there is a small observed difference between means.

B. When there is a large observed difference between means.

C. When there is no observed difference between means.

17. A small p value indicates that the sample data deviate ______ from what would be expected if the null hypothesis was true

A. A little

B. A lot

18. The results of a study comparing two class means were reported as t = 5.41, p = .03, and effect size = .01. These results are

A. statistically significant but clincally nonsignificant

B. statistically nonsignificant but clinically significant.

C. both statistically and clinically significant

D. both statistically and clinically nonsignificant

19. A standard deviation that is larger than the mean is often associated with a non-significant result.

A. True

B. False

20. The mean of the sampling distribution of the difference between means will always be zero.

A. True

B. False

21. When comparing the means of two samples (groups) using the t-test, the sample sizes must be equal.

A. True

B. False

22. What is it you compare when applying a t-test to two independent samples?

A. Sample variances

B. Sample means

C. Population variances

D. Population means

E. Coefficients of determination

23. Knowing that a result is statistically significant tells you that

A. the result is of practical importance.

B. the result is unlikely to be due to chance.

C. the result is definitely not due to chance

D. the result corresponds to a large effect size

24. The Mann Whitney U test is only valid if you have symmetry around the median for each group

A. True

B. False

25. When the calculated t exceeds the critical value from the statistical table, will the null hypothesis be rejected?

A. Yes

B. No

26. Which of the following would help us to decide on the appropriate test?

A. Are the data measured at a level appropriate to the test?

B. Are the assumptions of the test met, or, is the test robust to violations of the assumptions?

C. Is the test the most powerful appropriate to the problem and data at hand?

D. All of the above

E. None of the above

27. In a box-plot 50% of the values fall above the dark line and 50% below it.

A. True

B. False

28. Assuming any required assumptions are upheld, which of the following tests is the most powerful

A. Independent t-test

B. Wilcoxon

C. Mann Whitney

29. A researcher wants to know if a new drug will improve visual acuity. Subjects were randomly assigned to receive the drug or to receive a placebo. Preliminary analysis is found on your working document. Given this information, what advice would you give the researcher (put answer in electronic submission; does not have to be APA)?

Tests of Normality

a. Lilliefors Significance Correction

Group Statistics

Independent Samples Test

30. A researcher wants to know if patients in ICU, post open-heart surgery, cope better with a Morphine PCA or a Duramorph [both are methods for pain control]. He randomly assigns subjects to one of the two treatments. During the 1st 12 hours post op each patient is asked hourly what his or her pain is on a 1-10 scale (1 = 'I feel great' and 10 = 'The pain is horrible'). The averages of those hourly scores for each individual in both groups are presented below.

1. Given the information above are the groups independent or dependent?

2. Given the situation above, what is your null hypothesis?

3. Calculate the t statistic for the above data (put final answer in blackboard and upload math)

4. What is the critical deviate for the PCA/Duramorph situation (2-tail, alpha .05)? NOTE: put final answer in blackboard and upload math

5. What is the effect size for the PCA/Duramorph data (put final answer in blackboard and upload math)?

6. Do you ACCEPT or REJECT the null hypothesis for the PCA/Duramorph data?

31. A researcher wants to learn about the effect of cold on 9 asthmatics. PEFR (Peak expiratory flow rate interval/ratio level) is measured before & after a walk on a cold winter's day. The printout is below.

1. What is your dependent variable?

2. What is your independent variable?

3. Should you accept or reject your null hypothesis?

4. A researcher wants to learn about the effect of cold on 9 asthmatics. PEFR (Peak expiratory flow rate) is measured before and after a walk on a cold winter's day. Using the computer printout WRITE UP YOUR APA RESULTS AND DON'T FORGET TO INTERPRET THE FINDINGS.

ASSIGNMENT 2-

1. A correlation coefficient is needed to

a. Measure the distance between two variables

b. Estimate the value of the independent variable based on the dependent variable

c. Estimate the coefficient of determination

2. A Pearson product moment correlation coefficient measures the causality of the relationship

a. True

b. False

3. A regression equation was computed to be Y' = 15 + 6X. The value of 15 indicates

a. The regression line crosses the Y axis at 15

b. The coefficient of correlation is 15

c. The coefficient of determination is 15

d. An increase of one unit of X will result in an increase of 15 in Y

4. For a Pearson r of 0.66, the coefficient of determination equals 0.44.

a. True

b. False

c. Not enough information to determine

5. An analysis of the relationship between income (normally distributed) and IQ (normally distributed) scores among 150 randomly selected men found a Pearson Correlation coefficient of 0.45. What effect would increasing the sample to 300 have on the correlation coefficient?

a. Minimal to no change

b. Increase coefficient

c. Decrease coefficient

6. The Pearson product correlation coefficient, r must lie between 0 & +1

a. True

b. False

7. In a simple linear regression model, the slope coefficient measures:

a. The elasticity of Y with respect to X

b. The change in Y which the model predicts for a unit change in X

c. The ratio Y/X

d. The value of Y for any given value of X

Suppose a research report gave the correlation coefficient between the IQ test scores of students when they were in the second grade and their arithmetic achievement scores when they were in the third grade. The reported value was 0.60. The report also stated that the correlation between the number of days the third-graders were absent from school and their third-grade arithmetic achievement scores was -0.85.

8. Given the scenario above: The number of absences during the 3rd grade is a better predictor of 3rd-graders' arithmetic achievement than are their 2nd-grade IQ test scores.

a. True

b. False

9. Given the scenario above: Second grade IQ test performance and number of absences during the third grade are equally good predictors of third graders' arithmetic achievement.

a. True

b. False

10. For making predictions from one variable to another, a Pearson r of -0.68 is better than a Pearson r of 0.52.

a. True

b. False

11. If bivariate regression is used to predict, predictions are made of the _____ variable:

a. Dependent variable

b. Independent variable

12. Is a linear regression appropriate for the following: To predict a car's gas mileage from its weight in pounds.

a. Appropriate

b. Not appropriate

13. The correlation of a variable with itself is:

a. 0.00

b. 0.50

c. 0.75

d. 1.00

e. Depends on the strength of the relationship

14. How would you describe the relationship depicted by the following scatterplot?

a. A high positive correlation

b. A moderate negative correlation

c. A high negative correlation

d. A low correlation close to zero

15. If the results of a study demonstrated a highly significant association showing that the vast majority of people who win lotteries smoke cigarettes, you would be wise to consider:

a. Taking up smoking if you ever hope to win the lottery

b. That cigarettes are prohibitively expensive for most, but people who have won the lottery can afford them, hence the association

c. That gambling and smoking tend to occur together in individuals as a reflection of an addictive personality trait

d. That Correlation proves causation

16. Is a linear regression appropriate: To predict NCLEX scores (licensure exam) based on type of nursing program (AAS, BSN, and Diploma)?

a. Appropriate

b. Not appropriate

17. Which correlational procedure handles data sets having ties better than does Spearman's?

a. Kendall's tau

b. Tetrachoric

c. Phi

d. Cramer's V

18. The Pearson product moment correlation coefficient, r can only have a valid significance test carried out when at least one of the variables is from a normal distribution

a. True

b. False

19. Student NCLEX (licensure exam) pass rates states that "the correlation between annual expenditures on simulation and average student NCLEX performance was +2.7 for the 500 Universities in the sample." From this result, which of the following can you safely conclude is true?

a. There was either an error in computing the correlation coefficient or a typographic error in reporting the result.

b. Higher NCLEX scores attract higher financial support for nursing simulation labs.

c. There is a positive association between expenditures on simulation labs and nursing student NCLEX scores.

d. Spending more on nursing simulation labs causes higher student NCLEX scores.

20. The Pearson product moment correlation coefficient, r is 0 when there is no linear relationship

a. True

b. False

21. The statistic best used to find the relationship between teachers' rankings of students' leadership ability and their rankings of students' communication skills is:

a. Pearson r

b. Spearman's rho

c. Biserial correlation

d. Cramer's V

e. Tetrachoric

22. What does the squared correlation coefficient, r2, measure?

a. The slope of the least squares regression line

b. The intercept of the least squares regression line

c. The extent to which cause and effect is present in the data

d. The percent of the variation of one variable that is explained by the other

23. When the slope of the regression line is negative, the line goes from:

a. Upper left to lower right

b. Lower left to upper right

c. The line is flat

d. It depends on the intercept

24. Which of the following correlation coefficients indicates the weakest relationship between two variables?

a. r = +.56

b. r = +.60

c. r = +.12

d. r = -.15

e. r = -.74

25. A researcher wants to determine if depression, as measured by a depression inventory where subjects are categorized as depressed/not depressed based on their score, is related to IQ score (categorized into normal intelligence or above normal intelligence). The appropriate test would be:

a. Pearson's

b. Kendall's tau

c. Phi

d. Point biserial

e. Biserial

f. Tetrachoric

26. A study of marital status (married/not married) and attrition rate in college (dropped out/completed degree) was done.  The appropriate test would be:

a. Pearson's

b. Kendall's tau

c. Phi

d. Point biserial

e. Biserial

f. Tetrachoric

27. Using the regression formula with a slope = 2,000 and intercept = 15,000, what would the predicted income be for someone who has 16 years of education?

a. 40,000

b. 42,000

c. 45,000

d. 47,000

28. You cannot do a one tail test with a Pearson correlation:

a. True

b. False

29. Which of the following will have an impact on the magnitude or direction of a correlation coefficient?

a. Presence of outliers

b. Adding a constant to the raw scores

c. Changing the units of measurement

d. Reversing the two variables in terms of which is the causal and which is the outcome variable

30. A student wonders if people of similar heights tend to date each other. She measures herself, her dormitory roommate, and the women in the adjoining rooms; then she measures the next man each woman dates. Here are the data (height in inches); which of the following statements is true about the data:

a. The variables measured are all categorical

b. There is a strong negative association between the heights of men and women, since the women are always smaller than the men they dated

c. There is a positive association between the heights of men and women given

d. Any height above 70 inches must be considered an outlier

31. Using the correlation matrix on your worksheet, what two variables have the highest correlation?

** Correlation is significant at the 0.01 level (2-tailed).

Definitions:

a. Gest age: gestational age of women; length of pregnancy

b. Gravida: number of times a woman has been pregnant

c. APGAR 5: score given to infant at 5 minutes after birth that addresses his/hers transition to life outside uterus [0-10 with 10 being the best]

d. Birth weight: self explanatory (BUT IN GRAMS)

32. What term would you apply to the relationship depicted in the scatter plot below?

33. A researcher wants to know if High School GPA is a good predictor of first year college GPA (assume assumptions of homoscedasticity, linearity, and joint normality are met). Use the data below to answer the next 4 questions (Don't forget to put final answer in BB and upload math to Submit Homework):

a. What is r?

b. How much of the variance in college GPA can be explained by High School GPA?

c. What is the regression equation that will allow you to predict first year college GPA from High School GPA?

d. Using the regression equation, what is the predicted college GPA for a high school graduate whose GPA in high school was 3.5.

HIGH SCHOOL GPA          FIRST YEAR GPA               

3.5                                          3.3         

2.5                                          2.2         

4.0                                          3.5         

3.8                                          2.7         

2.8                                          3.5         

1.9                                          2.0         

3.2                                          3.1         

3.7                                          3.4         

2.7                                          1.9         

3.3                                          3.7         

34. The computer printout below explores the linear relationship between height and self- esteem in men. Self- esteem was measured with an interval/ratio scale instrument with higher scores indicating greater self-esteem. Researchers want to know if self-esteem is associated with height and whether knowledge of a person's height can predict self- esteem. Data was collected from 20 adult males. NOTE: you do not need to upload any math for this, although you will need to do a little to get some answers.

a. What is your non-directional null hypothesis?

b. What is your IV?

c. What is your DV?

d. List each regression assumption and indicate how your data/results meet or don't meet the assumptions (place answer directly into electronic submission).

e. How much of the variance in self-esteem levels can be explained by height (place answer directly into electronic submission)?

f. What is the predicted self-esteem level for someone who is 66 inches tall (place answer directly into electronic submission)?

g. What is the predicted self-esteem level for someone who is 51 inches tall (place answer directly into electronic submission)?

h. Name one other measurable (interval/ratio) variable that could also explain self- esteem levels (place answer directly into electronic submission).

i. Write up your results (3-4 sentences).

Descriptive Statistics

Correlations

Variables Entered/Removed^b

Model   Variables Entered            Variables Removed        

a. All requested variables entered.

 Variables Entered/Removed^b

b. Dependent Variable: esteem

Model Summary

a. Predictors: (Constant), height

Coefficientsa