Deck 24: Using Statistics to Predict

Question 1

A researcher conducts research on optimism. The researcher is calculating a multiple regression equation to predict levels of optimism and wishes to consider religious affiliation as one of the predictor variables. The researcher creates several dummy variables, for this purpose. Why must this be done?

A)It is safer to create more variables than less, since they may each contribute.
B)Multiple regression requires that the researcher enter numerical values, not names such as Lutheran, Orthodox Jewish, Buddhist, Islamic, and so forth.
C)Reducing nominal or categorical data to one or a series of dichotomous values allows mathematical computation of the regression equation.
D)Religious affiliation is a protected entity under HIPAA and must be coded before it is used in calculations.
E)The researcher's aim is to develop a formula with which to calculate optimism, given certain other variables, so these must all be represented as numbers.

Answer 1

Multiple regression requires that the researcher enter numerical values, not names such as Lutheran, Orthodox Jewish, Buddhist, Islamic, and so forth.
Reducing nominal or categorical data to one or a series of dichotomous values allows mathematical computation of the regression equation.
The researcher's aim is to develop a formula with which to calculate optimism, given certain other variables, so these must all be represented as numbers.

Question 2

What is a multiple regression equation?

A)One that represents the mathematical effect that several independent variables have on the dependent variable
B)One in which the x-values are multiplied by one another
C)One that explains more of the variance in y than does a single linear regression equation
D)An experimental model for determining best practices
E)One that uses more than one predictor variable to predict the value of the outcome variable
F)One that explains all of the variance in the dependent variable, in terms of several independent variables

Answer 2

One that represents the mathematical effect that several independent variables have on the dependent variable
One that explains more of the variance in y than does a single linear regression equation
One that uses more than one predictor variable to predict the value of the outcome variable

Question 3

A researcher collects a nationally based set of data about cholesterol levels and age at first circulatory incident (myocardial infarction or cerebrovascular accident). The researcher performs a linear regression analysis, in order to do which of the following?

A)To be able to estimate the age at which circulatory incidents are likely to occur, given the cholesterol level.
B)To determine how well the data fit the theoretical framework
C)To calculate the strength of the relationship between cholesterol levels and circulatory incidents
D)To determine whether there is a linear relationship between cholesterol levels and circulatory incidents
E)To derive the formula for the line of best fit
F)To obtain information from which to construct a better scatter plot

Answer 3

To be able to estimate the age at which circulatory incidents are likely to occur, given the cholesterol level.
To calculate the strength of the relationship between cholesterol levels and circulatory incidents
To determine whether there is a linear relationship between cholesterol levels and circulatory incidents
To derive the formula for the line of best fit

Question 4

Which of the following dependent variables is suitable for logistic regression analysis?

A)How many compressions were delivered in the first minute following the call of a code blue
B)Serum sodium value
C)Born on earth-not born on earth
D)Height at adulthood
E)Birth gender
F)Whether a patient with cancer goes into remission

Question 5

Why does a researcher decide to calculate odds ratio instead of calculating linear regression, when comparing whether a person voted in the last election, and the person's gender?

A)Voting records are sealed.
B)Both predictor and dependent variable are dichotomous.
C)Odds ratio is a simpler calculation.
D)Strength of relationship is not an issue.

Question 6

Which of the following terms in correlational research mean the same thing?

A)Predictor variable
B)Dichotomous variable
C)Dependent variable
D)Multicollinearity
E)Independent variable

Question 7

A researcher decides to study how many college freshmen with continuous enrollment graduate within 4, 4.5, 5, 5.5, and 6 years and to analyze this according to what their majors at graduation are, as well as other demographic variables. Why would a Cox proportional hazards regression analysis be suitable for this research?

A)Demographic variables could affect time until graduation.
B)The data of people who do not graduate at all may be informative.
C)Attendance at college can present hazard.
D)A predictor of the dependent variable is time-related.
E)Only people who actually graduate by the end of 12 semesters will have their data analyzed.

Question 8

Why does a researcher decide to use logistic regression instead of linear regression to calculate survival odds after suffering an out-of-hospital heart attack, in persons of various ages, genders, and cardiac diagnoses?

A)Survival versus nonsurvival is a dichotomous variable.
B)Having a heart attack is a variable that has many possible outcomes.
C)Linear regression is less logical than is logistic regression.
D)Age is a ratio-level variable.
E)Gender is a nominal-level variable.
F)Cardiac diagnosis is a nominal-level variable.

Question 9

A researcher draws a scatter plot of study data. The researcher develops a multiple regression equation and determines R² as 0.5625. What does the calculated value R² represent?

A)It means the standard error, squared.
B)It means that the predictor variables accounted for 56.3% of the variance in the outcome variable.
C)It stands for the standard deviation of the data set y, squared.
D)It estimates shrinking regression.
E)It is the coefficient of determination.
F)It is the explained variance.

Question 10

A researcher is studying daily carbohydrate intake and the next day's first morning blood glucose monitor value. After drawing a scatter plot, the researcher develops a multiple regression equation. What is does the value R represent?

A)The line of best fit
B)The amount of change in blood glucose monitor values that daily carbohydrate intake predicts
C)Daily carbohydrate intake times blood glucose monitor value
D)The correlation between daily carbohydrate intake and the next day's first morning blood glucose monitor value

Question 11

Which of the following statements about prediction is true?

A)Simple linear regression can predict possible changes in A, given b.
B)Multicollinearity is used to provide definitive attribution in predicting dependent variables with similar outcomes.
C)Multiple regression can provide information about the strongest predictors, C, D, E, and F, associated with an outcome variable g.
D)Odds ratio is used to predict the likelihood of a dichotomous event, in the light of a different dichotomous variable
E)Logistic regression is used to predict a dichotomous variable, using a variety of other variables.
F)Cox hazard regression can predict the likelihood of an event occurring at certain points in time.

Question 12

A researcher is studying stress and various factors that seem to be related to it, in women with terminally ill spouses. Among other things, the researcher finds out that depression contributes to total stress; depression contributes to lack of exercise; exercise contributes to depression; exercise relieves stress; guilt contributes to depression; exercise has no effect on guilt, but it affects total stress; stress worsens depression; and stress decreases motivation to perform exercise. This is an example of what problem commonly encountered in regression analyses?

A)Multicollinearity
B)Hazard ratio
C)Odds ratio
D)Predictive validity