Exam 3 Study Guide
If there is a positive association between two variables, A) as one variable increases in value, the other also increases B) as one variable decreases in value, the other increaes C) the researcher can be certain of his conclusions D) neither variable can decrease
A) as one variable increases in value, the other also increases
One key assumption of correlation analysis is that the variables have an essentially _____________ relationship. A.linear B.non-linear C.curvilinear D.circular
A. linear
In a bivariate table, the categories of the dependent variable are placed in the A.rows. B.columns. C.marginals. D.far right-hand column.
A. rows
Which pattern of cell frequencies in a 2x2 table would indicate that the variables are independent? A.All cell frequencies are exactly the same. B.There are a different number of cases in each of the four cells. C.Only the cells in the top row of the table have cases in them. D.There are no cases in any cell.
A.All cell frequencies are exactly the same.
For a 3 x 3 table, the appropriate chi square based measure of association would be A.Cramer's V. B.phi. C.lambda. D.gamma.
A.Cramer's V
Unlike other tests of significance, chi square is based on A.a bivariate table. B.means as well as proportions. C.continuous variables only. D.ordinal-level variables only.
A.a bivariate table.
The square of Spearman's rho is the proportional reduction in error when predicting A.rank on one variable from rank on the other variable compared to predicting rank while ignoring the other variable. B.the rank of a case from its score. C.rank on gamma vs. rank on phi. D.score on X while ignoring Y.
A.rank on one variable from rank on the other variable compared to predicting rank while ignoring the other variable.
In most correlation matrices, the diagonal line has a value of A.0. B.1. C.5. D.it cannot be predicted.
B) 1
If a = 17, b1 = 5, b2 = 20, X1= 100, and X2 = 200, what would the predicted Y score be? A.17 B.4,517 C.101 D.6,217
B.4,517
The subtotals calculated for bivariate tables are also known as A.expected frequencies. B.marginals. C.observed frequencies. D.cells.
B.marginals.
The coefficient of multiple determination (R) shows A) the effect of the control variable after removing the independent from the equation B) essentially the same thing as a partial gamma C) the combined effects of all independents on the dependent D) the zero-order relationships after controlling for the independents
C) the combined effects of all independents on the dependent
If the conditional distributions of Y change, the variables are A.independent. B.not associated. C.significantly related. D.associated
D.associated
In the Chi square test for independence, the null hypothesis and the research hypothesis A.always contradict each other. B.always agree with each other. C.are never actually stated. D.are usually both rejected.
A.always contradict each other.
If the slope (b) is zero, the value of r A.would also be zero. B.would be 1.00. C.would be - 1.00. D.cannot be determined from the information given.
A.would also be zero.
If the regression line showing the effect of education on income has a slop of 1000, A) the variables are not related B) every year of education increases income by 1000 C) every change in education increases income D) the Y-intercept would be 1.00
B) every year of education increases income by 1000
A researcher reports a Pearson r of .57 between gender (female = 0, males = 1) and involvement in juvenile delinquency. Which of the following is an appropriate interpretation? A.Females are more delinquent. B.There is no relationship between the variables. C.Delinquency increases as gender "increases." D.Only males were delinquent.
C.Delinquency increases as gender "increases."
Proportional reduction in error (PRE) measures of association are based on the logic of A.percentages. B.inference. C.prediction. D.zero errors.
C.prediction.
Partial and multiple correlation are based on A) bivariate tables B) random sampling C) the Analysis of Variance D) Pearson's r
D) Pearson's r
The Chi square test is based on the assumption that A.the variables are dependent. B.the expected frequencies are not produced by random chance. C.samples are non-random. D.the null hypothesis is true.
D.the null hypothesis is true.
When referring to interval-ratio variables, a commonly used synonym for association is A.probability. B.predictability. C.correlation. D.causation.
C) correlation
The coefficient of determination may be interpreted with a logic akin to A.chi square. B.the standard deviation. C.PRE. D.bivariate tables.
C.PRE.
Cramer's V is A) used for tables that are larger than 2 x 2 B) based on chi square C) easy to calculate D) all of the above.
D) all of the above
When variables vary in opposite directions, the association between variables is said to be A) positive B) neutral C) contradictory D) negative
D) negative
If the regression line on a scatterplot slopes upward from left to right, the relationship is A) bivariate B) strong C) parallel D) positive
D) positive
Partial and multiple correlation require data which are A.nominal and continuous B.ordinal and discrete C.inferential and bivariate D.interval-ratio
D. interval-ratio
Which measure of association is based on predicting the order of pairs of cases? A.Gamma B.Cramer's V C.Phi D.Lambda
A.Gamma
A researcher tested the relationship between gender and support for assisted suicide ("death with dignity") and found a Cramer's V of 0.45. This relationship is A.strong. B.weak. C.positive. D.significant but not important.
A.strong.
In regression analysis, the symbol "a" stands for A.the scores on the Y variable. B.the slope. C.the Y intercept. D.the X intercept.
C.the Y intercept.
Gamma provides a summary measure of the A.existence of a bivariate relationship. B.strength of a relationship. C.direction of a relationship. D.All of the above
D) All of the above
Gamma and lambda are based on the logic of A) chi square B) associational percentages C) proportional repartitioning D) proportional reduction in error
D) proportional reduction in error
The degrees of freedom in a chi square analysis are dependent upon the A) expected frequencies B) expected and observed frequencies C) marginal values D) the number of rows and columns in the table
D) the number of rows and columns in the table
Standardized partial slopes are also called A.alpha levels. B.gammas. C.Z scores. D.beta-weights.
D.beta-weights.
In the multiple regression equation, the symbol b stands for the A) partial slope B) slope of X and Y C) beta slop of X and Z D) Y-intercept
Not D, B
A researcher examines the relationship between poverty and crime rates for 100 metropolitan areas and finds a zero-order correlation of 0.37. She controls for the percent of families that are headed by single parents and finds a first order partial correlation of 0.33. Which of the following correctly describes this outcome? This is a ___ relationship. A) direct B) statistically significant C) spurious D) interactive
A) direct
A Chi square test has been conducted to assess the relationship between marital status and church attendance. The obtained Chi square is 23.45 and the critical Chi square is 9.488. What may be concluded? A.Reject the null hypothesis, church attendance and marital status are dependent B.Reject the null hypothesis, church attendance and marital status are independent C.Fail to reject the null hypothesis, church attendance and marital status are dependent D.Fail to reject the null hypothesis, church attendance and marital status are independent
A.Reject the null hypothesis, church attendance and marital status are dependent
When working with interval-ratio data, the optimal strategy for predicting Y while taking X into account would be to A.use the regression line. B.guess randomly. C.ignore the slope (b). D.always predict the Y intercept (a).
A.use the regression line.
A test of the relationship between social class and socialization values was reported in the text. Which of the following was a result of this test? A) Socialization values are much stronger in the middle class B) Although only one relationship was significant, the pattern of percentages in the tables generally conforms to theoretical expectations C) Socialization values increase as class increases D) People in the lowest classes were overwhelmingly supportive of obedience as a socialization value.
B) Although only one relationship was significant, the pattern of percentages in the tables generally conforms to theoretical expectations
If we fail to reject the null hypothesis in a test of significance for a Pearson's r, we conclude that A.there is a negative association between the variables. B.no inference can be made about the relationship of the two variables in the population. C.the relationship exists but its direction and strength are unknown. D.the variables are related in the population.
B) no inference can be made about the relationship of the two variables in the population
The sampling distribution for chi squares is A) shaped like any other normal curve B) not normally distributed C) bimodal D) all of the above
B) not normally distributed
One advantage of the technique of multiple regression is that it allows the _______________ effects of the ________________ variables to be investigated. A.combined, independent B.separate, independent C.combined, control D.separate, dependent
B) separate, independent
In the formula for Cramer's V, the expression (minimum of r1, c1) A) appears in the numerator B) tells us to use phi if there are fewer than 3 rows or columns C) is in the denominator D) is used only for samples larger than 100
B) tells us to use phi if there are fewer than 3 rows or columns
A standardized regression equation is stated as: Zy = (.46)Z1 + (.47)Z1. Which conclusion is most consistent with this formula? A.Z is caused by both X and Y. B.The independents have equally strong relationships with the dependent. C.This is a spurious relationship. D.There is a direct relationship between X and Y after controlling for the effects of Z.
B.The independents have equally strong relationships with the dependent.
Chi square is used to test relationships for their A) empirical importance B) logical importance C) statistical significance D) theoretical importance
C) statistical significance
To the extent that the variables do not meet the assumptions of regression analysis, coefficients and slopes become A.greater in value. B.lower in value. C.less trustworthy. D.less representative of the population.
C.less trustworthy
After controlling for Z, the partial correlation coefficient is 0.78. The bivariate Pearson's r between X and Y was only A) None, these results are mathematically impossible B) There is a spurious relationship between X and Y C) X and Z are both caused by Y D) X and Z are separate, uncorrelated causes of Y
D) X and Z are separate, uncorrelated causes of Y
A researcher asked a sample of dual career families about the percentage of the family budget contributed by the wife's job (Y) and the total number of children (X). Pearson's r for this relationship is -0.34. Which of the following is an appropriate interpretation of these results? A.For every dollar contributed by the wife, the number of children increases by .34. B.For every additional child, the wife must work longer hours. C.Every additional child lowers the economic wellbeing of the family. D.As number of children increase, the percentage of the budget contributed by the wife decreases.
D.As number of children increase, the percentage of the budget contributed by the wife decreases.
Unlike lambda, phi A.is computed from percentages. B.ranges from - 1.00 to + 1.00. C.is the square root of Cramer's V. D.is based on chi square.
D.is based on chi square.
A problem with both Cramer's V and phi is that values between 0.00 and 1.00 A) are very rare B) are mathematically impossible C) can actually indicate negative relationships D) can be interpreted only as an index of the relative strength of the association
D) can be interpreted only as an index of the relative strength of the association
Some potential difficulties arise in the chi square test when A.sample size is small. B.sample size is very large. C.many cells have expected frequencies of five or less. D.All of the above
D. All of the above
In the multiple regression equation, the partial slopes are analogous to A.chi square. B.gamma. C.Pearson's r. D.the partial correlation coefficient.
D.the partial correlation coefficient.
A researcher can demonstrate a strong association between gender and income. Which variable is independent? A.Gender B.Both C.Income D.Neither
A.Gender
The closer the value of a measure of association is to one, A) the stronger the relationship B) the more evenly the scores are distributed C) the weaker the relationship D) the more certain we are that samples are representative
A) the stronger the relationship
The appropriate measure of association for situations in which both variables are interval-ratio in level of measurement is A.Pearson's r. B.gamma. C.chi square. D.the slope (b).
A.Pearson's r.
After controlling for Z, the partial correlation coefficient is .78. The bivariate Pearson's r between X and Y was only .51. What should the researcher do next? A.Use multiple regression techniques to investigate this relationship further. B.Halt the investigation since these results are mathematically impossible. C.Conclude that the relationship between Z and Y is direct. D.Conclude that the relationship between Z and Y is spurious.
A.Use multiple regression techniques to investigate this relationship further.
In the case of gamma, a positive relationship means that A.if case A ranks below case B on one variable, case A will rank below case B on the other variable. B.if case A ranks above case B on one variable, it will rank below case B on the other variable. C.if case A ranks below case B on one variable, it will rank above case B on the other variable. D.the ranking of cases will be unrelated.
A.if case A ranks below case B on one variable, case A will rank below case B on the other variable.
A problem with large samples in the chi square test is that the test statistic A.increases at the same rate as sample size and trivial relationships may seem important. B.decreases as sample size increases and may cause Type I errors. C.fluctuates so much that the results are completely unreliable. D.is always elevated above the neutral area.
A.increases at the same rate as sample size and trivial relationships may seem important.
There is no linear relationship between two interval-ratio variables when the regression line on a scatterplot A.is parallel to the horizontal axis. B.does not touch all of the scores. C.is not an equal distance from all of the scores. D.is bimodal.
A.is parallel to the horizontal axis.
After scores of all cases have been located on a scatterplot, a straight line drawn so that it comes as close as possible to touching every score is called the A.regression line. B.line of approximation. C.cluster line. D.scatterplot summary.
A.regression line.
Visual examination of a scatterplot indicates the existence of an association between variables when A.the distribution of Y changes as X changes. B.the regression line is parallel to the horizontal axis. C.the regression line is perpendicular to the horizontal axis. D.no single regression line can be found.
A.the distribution of Y changes as X changes.
Unlike the chi square test of independence, in the chi square goodness of fit test, the expected frequencies are A.not used. B.computed. C.determined from the null hypothesis. D.the same as the observed frequencies.
C.determined from the null hypothesis.
If there is no association between two variables, knowledge of the independent variable A.causes us to make more prediction errors. B.improves the accuracy of our predictions. C.does not change the number of errors of prediction. D.makes prediction of the dependent variable impossible
C.does not change the number of errors of prediction.
By convention, the independent variable is arrayed along the in a scatterplot. A.vertical axis (the ordinate) B.regression line C.horizontal axis (the abscissa) D.calibration line
C.horizontal axis (the abscissa)
Lambda is asymmetric, which means that A.the value of lambda is the same regardless of which variable is taken as independent. B.the upper limit of lambda is less than 1.00. C.the value of lambda may vary depending on which variable is taken as independent. D.lambda cannot exceed .50.
C.the value of lambda may vary depending on which variable is taken as independent.
In addition to random sampling, interval-ratio level of measurement, and a normal sampling distribution, model assumptions for testing Pearson's r for significance include A) bivariate normal distributions B) a linear relationship C) uniformity in the variance of the Y scores around the regression line for all values of X D) all of the above
D) all of the above
One limitation of the Chi square test (and all tests of hypothesis) is that they cannot tell us if relationships between variables are A.significant. B.random. C.by chance. D.important.
D) important
When the row marginals are extremely unequal A) lambda is the preferred measure of association B) lambda may exceed 1.00 C) any chi square based measure of association will be less than zero D) lambda may be zero even though there is an association between the variables
D) lambda may be zero even though there is an association between the variables
The partial correlation coefficient will reveal an interactive relationship between three variables when A) the partial correlation coefficients drop to zero B) the partial is greater in value than the zero-order correlation coefficient C) the partial correlation coefficient is negative D) none of the above. Partial correlation will not detect interaction
D) none of the above. Partial correlation will not detect interaction
A researcher has found a strong relationship between level of education and income and concludes that "higher levels of education cause higher income." What error has been made? A.None, the argument is sound. B.Income is only nominal in level of measurement and education is ordinal so they cannot be causally related. C.Since these variables are continuous and interval ratio, they cannot have a causal relationship. D.By itself, association does not prove causation.
D.By itself, association does not prove causation.
A researcher wants to measure the strength of the association between income (measured in dollars per year) and education (measured in number of years of formal schooling). Which of the following would be the most appropriate measure of association? A.The slope (b) B.Gamma C.Chi square D.Pearson's r
D.Pearson's r
The regression equation for a particular relationship is Y = 10 + (.78) X1 + (-.54) X2. Which conclusion is consistent with this equation? A.The Y intercept is zero. B.Neither independent variable has an important relationship with Y. C.A value for a (the Y intercept) needs to be calculated before the equation can be interpreted. D.The two independent variables have opposite effects on the dependent.
D.The two independent variables have opposite effects on the dependent.
In the study examining the relationship between unemployment rates and civil disturbances in five cities, researchers A.as unemployment decreased, civil disturbances decreased slightly. B.as unemployment increased, civil disturbances decreased strongly. C.as unemployment decreased, civil disturbances increased slightly. D.as unemployment increased, civil disturbances increased greatly.
D.as unemployment increased, civil disturbances increased greatly.
If two variables are independent, the cell frequencies will be A.exactly the same. B.concentrated in only two of the cells. C.less than the expected frequencies. D.determined by random chance.
D.determined by random chance.
If a researcher is looking to perform an analysis based upon the relationship between the number of arrests as an A.phi. B.lambda. C.Cramer's V. D.none of these would be appropriate.
D.none of these would be appropriate.
The chi square goodness-of-fit test can be used when A.degrees of freedom are less than one. B.column percentages are equal. C.sample size is very large. D.the distribution of a single variable must be tested for significance.
D.the distribution of a single variable must be tested for significance.
While unstandardized partial slopes permit predictions of Y in the original units of the variable, standardized partial slopes permit an assessment of A.the combined effects of the independents. B.the partial effects of the independents. C.the independent effects of the partials. D.the relative importance of the independents.
D.the relative importance of the independents.
If there is a perfect association between sexual attraction and accelerated heartbeat, then A.sex is unhealthy. B.there is strong evidence that sexual attraction and accelerated heartbeat are causally related. C.if there is no sexual attraction, the heartbeat never accelerates. D.whenever the heartbeat accelerates, people become sexually attractive.
D.whenever the heartbeat accelerates, people become sexually attractive.
An obtained chi square of 10.78 has been calculated. Critical Chi square is 3.841. What should be concluded? A) Nothing -- information is incomplete B) Reject the null hypothesis, the variables are not independent C) Reject the null hypothesis, the variables are independent D) Fail to reject the null hypothesis
B) Reject the null hypothesis, the variables are not independent
A Pearson's r calculated for a bivariate relationship is 0.50. After controlling for Z, the partial correlation coefficient is A) direct B) spurious or intervening C) interactive D) positive
B) spurious or intervening
When calculating lambda, to find E2 A) multiply E1 by N B) subtract the largest cell frequency in each column from the column total and then add the subtotals C) subtract the column totals from the largest cell frequency in each column and then add subtotals together D) subtract the respective column totals from row totals and divide by N
B) subtract the largest cell frequency in each column from the column total and then add the subtotals
For variables measured at the ordinal level, gamma measures A) the statistical significance of the relationship B) the proportional reduction in error gained by predicting one variable while taking the other into account C) the relative importance of each variable to the association D) all of the above
B) the proportional reduction in error gained by predicting one variable while taking the other into account
When presented in professional literature, bivariate tables are usually presented with the ____________ as columns and _____________ as rows. A.dependent variable, independent variable. B.independent variable, dependent variable. C.gammas, Spearman's rho. D.phi, lambda.
B.independent variable, dependent variable.
"As education increases, income rises." This is an example of a A.non-causal relationship. B.positive relationship. C.negative relationship. D.neutral relationship.
B.positive relationship.
In order to examine which of the independent variables has the strongest effect on the dependent variable, you A.unstandardized partial slopes. B.standardized partial slopes. C.correlations. D.none of these choices are correct.
B.standardized partial slopes
Which assumption about level of measurement is made for the Chi square test? A) All variables are at least ordinal in level of measurement B) All variables are at least interval-ratio in level of measurement C) All variables are nominal in level of measurement D) At least one variable must be ordinal in level of measurement
C) All variables are nominal in level of measurement
The techniques of multiple correlation and regression can be used as long as A) the total number of variables is not greater than three B) the independents are strongly correlated with each other C) each independent is linearly related with the dependent variable D) sample size is less than 100
C) each independent is linearly related with the dependent variable
When working with interval-ratio data, the optimal strategy for predicting Y while ignoring X will be to use the A) mode of the Y scores for every case B) median Y score for every case C) mean Y score for every case D) lowest Y score for every case
C) mean Y score for every case
The "first order" partial correlation coefficient measures A) the bivariate relationship between X and Y B) the relationship between the dependent and control variables C) the bivariate relationship after controlling for the third variable D) the bivariate relationship after controlling for the fourth variable
C) the bivariate relationship after controlling for the third variable
In the case of a perfect association, predictions from one variable to another can be made A) only if variables are measured at the nominal level B) when at least one variable is ordinal C) without error D) only if the relationship is positive
C) without error
A bivariate table shows the association between gender and whether or not a person ever attends formal religious services. Lambda was .34. What may be concluded? A.Women are more likely to attend church. B.Men are more likely to attend church. C.Knowing a person's gender improves our ability to predict whether or not they attend religious services by 34%. D.Knowing whether a person attends religious services improves our ability to predict their gender by 34%.
C.Knowing a person's gender improves our ability to predict whether or not they attend religious services by 34%.
After controlling for Z, a researcher finds evidence of a direct relationship between X and Y. What step should be taken next? A.Z should become the new independent variable. B.Z should become the new dependent variable. C.Z should be disregarded and a new control variable should be selected. D.Z should be disregarded and a new independent variable should be selected.
C.Z should be disregarded and a new control variable should be selected.
