Deck 3: Pre-Analysis Data Screening

Question 1

The best thing to do when a data set includes missing data is to collect new data.

Answer 1

False

Question 2

If a researcher decides that the missing data are important and need to be addressed, the first thing to do is to estimate the missing values and then use these values during the main analysis.

Answer 2

False

Question 3

A third alternative for handling missing data deletes the missing values using a regression approach.

Answer 3

False

Question 4

Cases with unusual or extremely large values at one or both ends of a sample distribution are known as outliers.

Question 5

One of the fundamental causes for outliers is that data-entry errors were made by the research participant.

Question 6

The problem with outliers is that they can distort the results of a statistical test.

Question 7

Univariate outliers are cases with extreme values on one variable.

Question 8

Multivariate outliers are cases with unusual combinations of scores on two or more variables.

Question 9

A statistical procedure known as Mahalanobis distance can be used to identify outliers of any type.

Question 10

Robustness refers to the relative insensitivity of a statistical test to violations of the underlying inferential assumptions.

Question 11

Kurtosis is a quantitative measure of the degree of symmetry of a distribution about the mean.

Question 12

Skewness is a quantitative measure of the degree of peakedness of a distribution.

Question 13

The Kolmogorov-Smirnov statistic tests the null hypothesis that the variables in the population are linear.

Question 14

One of the characteristics of multivariate normality is that any linear combination of the variables must be nonnormally distributed.

Question 15

If a distribution differs only moderately from normal, a log transformation should be obtained.

Question 16

Linearity presupposes that there is a straight-line relationship between two variables.

Question 17

Residuals are defined as the portion of scores not accounted for by the multivariate analysis.

Question 18

Homoscedasticity is the assumption that the variability in scores for one continuous variable is roughly the same at all values of another continuous variable.

Question 19

With univariate analyses, homogeneity of variances is assessed statistically with Levene's test.

Question 20

In multivariate situations, homoscedasticity can be assessed statistically by using Box's M test for equality of variance-covariance matrices.

Question 21

The main purpose for screening data prior to conducting a multivariate analysis is to deal with the accuracy of the findings.

Question 22

Another purpose for screening data is to enter missing data and assess the effect of and ways to deal with complete data.

Question 23

A third purpose of screening data is to assess the effects of large values on either end of the distribution.

Question 24

A fourth purpose of screening data is to assess the adequacy of fit between the data and to make assumptions of a specific procedure.

Question 25

Pre-analysis data screening is an analysis after the analysis.

Question 26

Many researchers tend to assume that any missing data that occur within their dataset:

A) Are random in nature.
B) Are caused by research participants not giving honest answers.
C) Reflect responses to a taboo topic where participants were ashamed to answer the question(s).
D) None of the above is correct.

Question 27

There are three fundamental causes for outliers:

A) Data-entry errors were made by the researcher.
B) The participant is not a member of the population for which the sample is intended.
C) The participant is simply different from the remainder of the sample.
D) All three are correct.

Question 28

There are three general assumptions involved in multivariate statistical testing:

A) Normality.
B) Linearity.
C) Homoscedasticity.
D) All three are correct.

Question 29

If the researcher determines that the data have deviated from normal, she or he can consider transforming the data by:

A) A square root transformation.
B) A log transformation.
C) An inverse transformation.
D) All three are correct.

Question 30

Linearity presupposes that:

A) There is a straight-line relationship between two variables.
B) The variability in scores for one continuous variable is roughly the same at all values. of another continuous variable.
C) Both (a) and (b) are correct.
D) Neither (a) nor (b) is correct.