EBP II Weekly Quiz Questions
Matching: 1. Descriptive statistics 2. Inferential statistics 3. Efficacy 4. Effectiveness 5. Independent variable 6. Dependent variable 7. Ordinal 8. Ratio 9. Coefficient of Variance (CV) A. Mean, Median, mode B. Variable being negotiated or controlled C. % to allow unitless comparison of variability in an outcome measure D. t-test, ANOVA, paired t-test E. Equal intervals, has true zero F. Truth to real life, external validity G. Truth in study, internal validity H. Rank order to categorical variables I. Outcome variable
1. A 2. D 3. G 4. F 5. B 6. I 7. H 8. E 9. C
Match the parametric test with the nonparametric counterpart. 1. Unpaired t-test 2. Paired t-test 3. One-way ANOVA 4. One-way Repeated Measures ANOVA A. Wilcoxon signed-ranked Test B. Mann-Whitney U Test C. Kruskal-Wallis analysis of variance D. Friedman two-way analysis of variance
1. B 2. A 3. C 4. D
Matching: 1. A quantitative variable with a finite number of values. 2. Best measure of central tendency for numeric, symmetrically distributed data 3. Best measure of central tendency for numeric, non-symmetrically distributed data 4. A quantitative variable with an infinite number of values. A. Median B. Mean C. Discrete Variable D. Continuous Variable
1. C 2. B 3. A 4. D
Type I or Type II error? 1. Claiming there is a true difference when there is none. 2. Claiming there is a no difference when there is one. 3. A false positive. 4. A false negative 5. Rejecting the null hypothesis when you shouldn't have.
1. Type I 2. Type II 3. Type I 4. Type II 5. Type I
T/F: If our finding is NOT statistically significant and the MCID is excluded from the confidence interval, we have adequate power and there is no need to do a post hoc power analysis.
True
T/F: In order for a t-test to be used, there should be 1 independent variable with 2 levels.
True
T/F: Post-hoc testing should be done when a statistically significant interaction is found after performing an ANOVA.
True
T/F: The F-statistic is used in an ANOVA; the larger the F-ratio, the grater the differences between the group means.
True
T/F: The variable of age is continuous.
True
T/F: Type 1 error is ALL of the following: claiming a true difference when there is actually no difference, a false positive, rejecting the null when you shouldn't have
True
T/F: You can not commit a type II error unless you accept (fail to reject) the null hypothesis.
True
If I am measuring pain in 2 groups (pain is rated 0-10) and I see that the 'treatment' group has a decrease in pain of 1.5 with a 95% confidence interval of (-2, 5). Which of the following conclusions can I draw? Mark ALL that apply. A. The estimate of effect has wide variation/less precision B. The change in pain is NOT statistically significant C. I can be 95% confident the true population mean lies between -2 and 5 D. The change in pain is clinically meaningful
A, B, C
Descriptive statistics include the Standard Deviation (SD) which is how the data spreads out from the mean of a data set. In a normal "bell" curve what percentage of the data points are included "one standard deviation" from the mean? A. 68.26% B. unable to determine without seeing the data C. 95.45% D. 34.13%
A. 68.26%
You are measuring your outcome of interest at 4 weeks and 3 months. Given the variable of time, what is the level of measurement? A. Categorical B. Interval C. Ratio
A. Categorical
You are looking at baseline demographics between two groups in a table published in an article. You note a p-value of .87 (alpha set at .05) for the characteristic of gender. Which test was most appropriately used to compare genders between groups at baseline? A. Chi-squared B. Un-paired t-test C. Kruskal-Wallis D. Paired t-Test
A. Chi-squared
Which ANOVA design is most appropriate when you want to answer the question: Does the amount of improvement over time depend upon treatment group allocation? A. Mixed-model ANOVA B. One-way ANOVA C. Independent t-test D. Two-way ANOVA
A. Mixed-model ANOVA
If there is a study examining the change scores (difference between pre and post test elbow ROM) for four different treatment groups the best statistical analysis for this study would be: A. One-way ANOVA B. Mixed-model ANOVA C. Two-way ANOVA D. Independent t-test
A. One-way ANOVA
You are looking to perform a study that is looking at the use of relaxation exercises on anxiety measures for 100 DPT students randomly drawn. Students take the anxiety questionnaire before any intervention is provided. Then, the DPT students perform relaxation exercises. Later, the same DPT students take the same anxiety questionnaire. You want to compare the mean scores on the anxiety assessment to determine if the relaxation exercise helped anxiety. What test is most appropriate? A. Paired t-test B. Independent t-test C. Un-paired t-test
A. Paired t-test
Clinical prediction rules use which type of statistical analyses? A. Regression B. ANCOVA C. Mixed Model ANOVA D. MANOVA
A. Regression
Alpha is the maximum probability of a: A. Type 1 error occurring. B. Type 2 error occurring.
A. Type 1 error occurring.
Statistical power is determined by which of the following? A. Effect size B. All of these choices C. Sample size D. Variance
B. All of these choices
Which is NOT an assumption needed for a linear regression analysis. A. Homogeneity of variance B. DVs are categorical C. For every X there is a normal distribution of Y. D. DVs are continuous
B. DVs are categorical
Which is NOT an assumption needed for a logistic regression analysis. A. DVs are categorical B. DVs are continuous C. Predictor variables can be continuous, ordinal, or dichotomous
B. DVs are continuous
You are looking to perform a study that is looking at the use of relaxation exercises on anxiety measures for 100 DPT students randomly drawn. The trial involves randomly assigning the class to 1 of 2 groups. There are 50 students in each group. One group will get the relaxation exercises and the other will not. You will be comparing levels of anxiety between groups (pre-post exercises) with the use of an anxiety questionnaire. What test is most appropriate? A. Paired t-test B. Independent t-test C. Dependent t-test
B. Independent t-test
You are wanting to compare four different groups in a study you are designing for individuals with persistent low back pain. One group is getting mirror box training, another group is getting laterality training, the third group is getting a combination of both and the final group is the control group. The outcome of interest is tolerance to pressure at the L4 segment and measured as "hypersensitive", "normal" or "diminished". The group is randomly selected from several clinics. If you only measure at one time point after intervention, Which is most appropriate in this situation? A. Friedman's Two-way ANOVA B. Mann-Whitney U Test C. Un-paired t-test D. Kruskal-Wallis
B. Mann-Whitney U Test
You are wanting to see if gluteus strength improves with strengthening. There are two groups: One group is getting eccentric exercises targeting the gluteus medius muscle group and the other group is getting concentric exercises targeting the same muscle group. Subjects were randomly selected from 3 different clinics located at different geographical locations. The outcome of interest is muscle strength which will be measured as either "strong", "diminished" or "poor" via a manual muscle testing procedure. If you only measure at one time point after intervention, how would you assess the data? A. Friedman's Two-way ANOVA B. Mann-Whitney U Test C. Un-paired t-test D. Kruskal-Wallis
B. Mann-Whitney U Test
I am looking at 2 studies examining physical therapy treatments for individuals with knee pain related to OA. One study looks at manual therapy and cardiovascular exercises concluding NNT is 3. The other study looks at manual therapy and high load strengthening concluding NNT is 2. Based only on this information, which treatment would I choose first? A. Manual therapy and cardiovascular exercise B. Manual therapy and load based strengthening
B. Manual therapy and load based strengthening
You are reading a study where the investigators want to see if there is a difference in strength measured in pounds of force for 4 different test positions for the gluteus medius muscle. The study design includes a group of 25 randomly selected healthy individuals who are put into the 4 different test positions where strength is measured. The mean force (in pounds) is compared between each test position to measure differences. This is an example of a: A. One-way ANOVA B. Repeated Measures ANOVA C. Dependent t-test D. Two-way ANOVA
B. Repeated Measures ANOVA
You are reading a study and notice that the authors have used a Bonferroni correction. Which of the below explain why this correction was used. A. To use an un-adjusted t-test approach for post-hoc testing that increases power. B. To account for the family-wise error rate where alpha is divided by the number of post-hoc comparisons C. To account for the family-wise error rate where beta is divided by the number of post-hoc comparisons
B. To account for the family-wise error rate where alpha is divided by the number of post-hoc comparisons
In a normal distribution, what percentage of the sample is included within 2 standard deviations of the mean? A. 68 B. 50 C. 95 D. 97
C. 95
When comparing the magnitude of two different dependent variables it is best to calculate a ________________ to allow for objective comparison. A. Kurtosis of Result B. Mean C. Coefficient of Variance D. Standard Deviation
C. Coefficient of Variance
I want to know if quarter 4 GPA (half way through) in the South College DPT program is predictive of passing licensure on the first try. Which statistical analysis should I use? A. Linear Regression B. Multiple Linear Regression C. Logistic Regression
C. Logistic Regression
You come across a study and see that the p-value is .02 for a given interaction. The alpha in the study was set at .05. You interpret this finding as: A. Statistically significant given that the alpha is less than the p-value. B. Not statistically significant given that the p-value is more than the alpha. C. Statistically significant given that the p-value is less than alpha. D. Not statistically significant given that the alpha is more than the p-value.
C. Statistically significant given that the p-value is less than alpha.
The more narrow the confidence interval range: A. The smaller the sample size. B. The less precise/more variation. C. The more precise/less variation. D. The more variance there will be.
C. The more precise/less variation.
You are reading a study that indicates that they were using a 2 x 3 ANOVA. From this, we can conclude that: A. There are two IVs being compared first, then 3 IVs being compared second. B. There are 2 factors for the first level and 3 factors for the second level. C. There are two levels for the first IV and there are 3 levels for the second IV
C. There are two levels for the first IV and there are 3 levels for the second IV
You are reading a study that reports an Odds Ratio or Relative Risk of 5 when looking at the rate of persistent low back pain (LBP) in those who are obese. The correct interpretation of this value is: A. Those who are obese are 5 times less likely to suffer from persistent LBP. B. There is a 5% increase in the probability that those who are obese will develop LBP. C. Those who are obese are 5 times more likely to suffer from persistent LBP.
C. Those who are obese are 5 times more likely to suffer from persistent LBP.
A data set may present with a skewed distribution. If the distribution is negatively skewed is means ___________. A. Data indicates there was a poor outcome B. Data indicates there are more negative outliers C. It indicates that the data is corrupted D. Mean and median will be less than the mode
D. Mean and median will be less than the mode
What level of measurement is gender? A. Ratio B. Interval C. Ordinal D. Nominal
D. Nominal
I have 2 treatment groups and I measure outcomes on 4 different time periods. Which is true of the factors and levels? A. There are 2 factors and 4 levels B. There are 2 levels (group and time) with 2 factors in one and 4 factors in the other C. There are 2 factors and 2 levels D. There are 2 factors (group and time) with 2 levels in one and 4 levels in the other
D. There are 2 factors (group and time) with 2 levels in one and 4 levels in the other
Which of the following is an accurate description of a parametric assumption? A. Categorical level data is used. B. Samples are drawn specifically from populations. C. Population is skewed. D. There is homogeneity of variance.
D. There is homogeneity of variance.
Self-reported measure such as ODI and pain are examples of:
Dependent variables
T/F: An ANOVA is different than a t-test due to the fact that an ANOVA is used with 2 groups and a t-test is used when there are 3 or more groups.
False
T/F: An effectiveness trial is one that is highly controlled.
False
T/F: Non-parametric tests are more powerful than parametric testing.
False
T/F: Statistical significance and clinical significance are interchangeable terms.
False
T/F: We recommend a post hoc power analysis IF the finding is NOT statistically significant and we suspect a possibility of Type I error.
False
T/F: When calculating sample size a-priori, one holds the alpha at .80.
False
Spinal manipulation and functional technique are examples of:
Independent variables
