Ch 11: Understanding Statistics in Research

Which of the following is not a characteristic of ANOVA? a. Can be used only with two groups b. Often requires post hoc tests to identify locations of differences c. Tests for differences between means d. F statistic used to report results

a. Can be used only with two groups This is not a characteristic of analysis of variance (ANOVA). ANOVA can be used with three or more groups.

During data cleaning, the researcher will perform which of the following? Select all that apply. a. Check the data for accuracy b. Correct all errors c. Identify missing data points and supply the data d. Organize according to responses e. Sort according to demographics

a. Check the data for accuracy b. Correct all errors c. Identify missing data points and supply the data Data cleaning involves checking for accuracy, errors, or missing data. Organizing and sorting are components of analysis.

Which of the following is related to inference? a. Conclusion or judgment based on evidence b. Logical movement from a general truth to a specific instance c. Researcher's guess about the outcomes of the study d. Theoretical application of study findings

a. Conclusion or judgment based on evidence An inference is made from the study findings obtained from a specific sample and applied to a more general population using the results from statistical analyses.

Which of the following is not a descriptive statistic? a. Correlational analysis b. Frequency distribution c. Mean d. Standard deviation

a. Correlational analysis Correlational analysis is not a descriptive statistic, but it is an inferential statistic. Inferential statistics are designed to address objectives, questions, and hypotheses in studies to allow inference from the study sample to the target population. Descriptive statistics are summary statistics that allow the researcher to organize data in ways that give meaning and facilitate insight. Frequency distribution describes the occurrence of scores or categories in a study. The mean is the sum of the scores divided by the number of scores being summed. Standard deviation is the square root of the variance.

Types of results from inferential statistical analyses include all except which of the following? a. Findings b. Not significant c. Significant d. Unpredicted

a. Findings The researcher, not the statistical procedures, must reach findings.

The risk of a type II error increases with which of the following? Select all that apply. a. Low levels of power b. Small effect sizes c. Type I error d. Small samples

a. Low levels of power b. Small effect sizes d. Small samples Options A, B, D are type II errors.

A researcher wants to conduct a study examining the relationship between gender and heart disease. Which of the following methods would be most appropriate? a. Analysis of variance (ANOVA) b. Chi-square c. Pearson's r d. Regression analysis

b. Chi-square Chi-square is used to examine relationships between categorical data. Analysis of variance (ANOVA) is a parametric statistical technique used to examine differences among three or more groups. Pearson's r is a correlation coefficient designating the magnitude of relationship between two interval- or ratio-level variables. Regression analysis is used to predict the value of one variable when the value of one or more other variables is known.

In any study in which the data are numerical, data analysis begins with which of the following? a. Correlational statistics b. Descriptive statistics c. Hypothesis-testing statistics d. Predictive statistics

b. Descriptive statistics All quantitative studies begin analysis with descriptive statistics.

A researcher wanted to study the elements or variables associated with fear. Which of the following would be an appropriate statistical measure? a. Chi-square b. Factor analysis c. Pearson's r d. t-test

b. Factor analysis Factor analysis is used to determine the relationships among large numbers of variables associated with a complex phenomenon. Chi-square test of independence examines the frequencies of observed values and compares them with the frequencies that would be expected if the data categories were independent of each other. Pearson's r is a correlation coefficient designating the magnitude of relationship between two interval- or ratio-level variables. The t-test is used to examine group differences when the variables are measured at the interval or ratio levels.

Which of the following is true of a one-tailed test of significance? a. Increases the risk of a type II error b. Indicates that extreme scores on only one tail are considered significant c. Is referred to as no directional d. Is weaker than two-tailed tests

b. Indicates that extreme scores on only one tail are considered significant In a one-tailed test, the statistical procedure tests for differences in only one tail. Thus only extreme scores in that tail are considered significantly different.

Which of the following is the purpose of exploratory data analysis? Select all that apply. a. Check the data for accuracy b. Correct all errors c. Determine the nature of variation in the data d. Identify outliers e. Obtain a better understanding of the data

c. Determine the nature of variation in the data d. Identify outliers e. Obtain a better understanding of the data Analysis involves interpreting variations, outliers, and gaining understanding of the data. Checking for errors and accuracy are data-cleaning activities.

What do measures of dispersion indicate? a. Differences among samples b. Homogeneity, which indicates wider dispersion c. Individual differences of the members of the sample d. The central tendency of the sample

c. Individual differences of the members of the sample Measures of central tendency, or variability, are measures of individual differences of the members of the sample.

To judge statistical suitability while critiquing a study, the nurse researcher needs to know all except which of the following? a. Level of measurement b. Number of groups c. Reliability of the measures d. Whether the groups are dependent or independent

c. Reliability of the measures This information is not necessary to judge statistical suitability.

For what purpose is the t-test used? a. To describe relationships between two variables b. To examine differences among three or more groups c. To test for a significant difference between the means of two samples d. To test the power of a statistical procedure

c. To test for a significant difference between the means of two samples The t-test is used to test for a significant difference between the means of two samples. Correlational analyses are conducted to describe relationships between two variables. When differences are examined among three groups, post hoc analyses are conducted. Power is the probability that a statistical test will detect a significant difference that exists. The risk of a type II error can be determined using power analysis.

Which of the following leads to a type I error? a. When data are not measured at the interval level b. When results are not significant c. When results indicate a significant difference when there is no difference d. When wrong statistical procedures are used

c. When results indicate a significant difference when there is no difference A type I error indicates a significant difference when there is no difference.

Which of the following describes the purpose of the Chi-square test of independence? a. Determines whether two variables are independent or related b. Has a high risk of a type II error c. Is a very weak statistical test d. All the above

d. All the above All the options are correct.

Which of the following describes the tails of the normal curve? a. They are defined by the level of significance selected by the researcher. b. They are representative samples that may not belong to the same population. c. They are the extreme statistical values on the peripheral ends of the normal curve. d. All the above

d. All the above All the responses are correct.

For what reason is it important to describe the sample? a. Allow readers to determine if the sample is similar to persons in their clinical setting b. Determine if groups being compared are equivalent c. Determine if the sample is representative of the target population d. All the above

d. All the above These options are important reasons for describing the sample.

The researcher understands that exploratory analysis is used for all except which of the following? a. Become familiar with the data b. Examine measures of central tendency and dispersion for each variable c. Identify outliers d. Generalize to a larger population

d. Generalize to a larger population Exploratory analysis is not used for this purpose. This requires confirmatory analysis using inferential statistics.

Which of the following best explains power? a. It is the amount of variance allowed in the measured scores. b. It is the capacity of the computer to run complex statistical analyses. c. It is the degree to which the null hypothesis is false. d. It is the probability that a statistical test will detect a significant difference that exists.

d. It is the probability that a statistical test will detect a significant difference that exists. Power is the capacity of a statistical analysis to identify real differences (or relationships) in the data. The variance for scores in a study is calculated with a mathematical equation and indicates the spread or dispersion of the scores. The standard deviation (SD) is the square root of the variance. Just as the mean is the average value, the SD is the average difference (deviation) value. Computation is a mechanical process usually performed by a computer. The Statistical Package for the Social Sciences (SPSS Statistic 20) is a software program for analyzing data and running statistical tests. The effect size is the degree to which the null hypothesis is false.

Using decision theory, if the level of significance was set at 0.05, which of the following probability levels from statistical analyses would indicate the greatest significant difference? a. 0.04 b. 0.01 c. 0.001 d. None of the above

d. None of the above According to decision theory, results are expressed dichotomously. Results are either significantly different or not significantly different. There are no "degrees" of significant difference.

The most common purpose of a Pearson's correlation is to examine which of the following? a. Differences between groups b. Differences between variables c. Relationships among groups d. Relationships among variables

d. Relationships among variables A Pearson's correlation usually examines relationships among variables.

When interpreting research outcomes, the type of results that agree with those predicted by the researcher and support the logical links developed by the researcher among the framework, purpose, study questions, hypotheses, variables, and measurement tools is known as? a. Nonsignificant results b. Significant and unpredicted results c. Unexpected results d. Significant results

d. Significant results Significant results agree with those predicted by the researcher and support the logical links developed by the researcher among the framework, purpose, study questions, hypotheses, variables, and measurement tools. Nonsignificant (or inconclusive) results, often referred to as "negative" results, may be a true reflection of reality. In that case, the reasoning of the researcher or the theory used by the researcher to develop the hypothesis is in error. Significant and unpredicted results are the opposite of those predicted by the researcher and indicate that flaws are present in the logic of the researcher and theory being tested. Unexpected results usually are relationships found between variables that were not hypothesized and not predicted from the study framework.

Which of the following does the normal curve indicate? a. Distribution of the values of a single sample b. Illustration of scores from several samples c. Real distribution of the values of a population d. Theoretical frequency distribution of all possible values in a population

d. Theoretical frequency distribution of all possible values in a population The normal curve is a theoretical frequency distribution of all possible values in a population; however, no real distribution exactly fits the normal curve.

A researcher wants to compare the results of two tests completed on the same group. Which of the following methods would be most appropriate? a. Analysis of variance (ANOVA) b. Chi-square c. t-test d. Z-score

d. Z-score Z-scores are used to standardize scores of different tests to make comparisons. Analysis of variance (ANOVA) is a parametric statistical technique used to examine differences among three or more groups. Chi-square is used to examine relationships between categorical data. The t-test is used to examine group differences when the variables are measured at the interval or ratio levels.