36 Questions
Which item difficulty range is considered very difficult?
0.0-0.19
What level of internal consistency does a Cronbach's alpha of 0.75 indicate?
Acceptable
According to Cohen & Swerdlik, what percentage of the upper and lower areas of the distribution of scores is typically considered when the distribution is normal?
27%
What verbal description corresponds to an item discrimination value of 0.35?
Good
Which interrater reliability coefficient is considered poor according to Fleiss (1981)?
0.3
What is the p-value range that provides strong evidence against the null hypothesis?
0.01 < p < 0.05
What level of difficulty corresponds to an item difficulty range of 0.61-0.79?
Easy
What is the verbal description for an interrater reliability coefficient of 0.8 according to Landis & Koch (1977)?
Substantial
Which test should be used to measure the correlation between one nominal variable and one ordinal variable?
Kendall's Rank Biserial Differences
Which test is appropriate for comparing the means of three groups, tested for two different nominal variables?
Two-Way ANOVA
Which test should be used if the variables are both artificially dichotomous?
Tetrachoric
Which statistical test is used to predict the unknown value of variable Y using the known value of variable X?
Linear Regression of Y on X
Which test is most suitable for analyzing if there is a significant difference in blood pressure before and after a treatment in the same group?
T-Test Dependent
Which test should be used to explore the differences in salaries among different socio-economic statuses?
One-Way ANOVA
Which statistical test is used when controlling for an additional variable influencing the relationship between the independent and dependent variables?
ANCOVA
Which method is appropriate for analyzing the correlation between a true dichotomous variable and an interval/ratio variable?
Point Biserial
Which test should be used to measure the differences of board reviewers' focus levels during morning, afternoon, and night sessions of review?
One-Way Repeated Measures
Which non-parametric test is equivalent to the one-way ANOVA?
Kruskal-Wallis H Test
Which measure of central tendency is most useful for nominal scales?
Mode
How is variance defined in the context of psychological assessment?
The average squared deviation around the mean
What does a large spread of values in measures of spread or variability indicate?
Large differences between individual scores
What is the semi-quartile range?
The interquartile range divided by 2
What does a bimodal distribution indicate?
There are two scores occurring with the highest frequency
Which measure of location expresses the percentage of persons in a sample who fall below a given score?
Percentile rank
What does a high standard deviation indicate about the scores in a distribution?
Scores are spread out far from the mean
What is the purpose of using measures of spread or variability in psychological assessment?
To describe the amount of variation in a distribution
Which test is used to measure the variance homogeneity assuming a less sensitive departure from normality?
Levene's Test
If a sample's size is 45, which test for normality should be used?
Shapiro-Wilk
What aspect is NOT determined during the test conceptualization phase?
Scoring rules
Which test is used for testing the variance significance of more than two groups in ordinal scale measurements?
Kruskal Wallis H Test
Which process involves the creation, revision, and deletion of preliminary items?
Pilot Work
What type of dichotomy involves only fixed possible categories?
True Dichotomy
When the P-Value is greater than 0.05 in Levene's Test, what can be inferred about the variances?
Variances are homogeneous
What is the primary focus during the test development process?
Test Conceptualization
Which test should be used if the dependent variable is measured at an ordinal scale and the groups are compared more than twice?
Friedman Test
What distinguishes item banks from item pools?
Item banks are large and accessible
Study Notes
BLEPP
- 0 means 0% of the variance in the scores assigned by the scorers was attributed to true differences and 100% to error
Item Difficulty
- Item difficulty ranges from 0.0 to 1.0
- 0.0-0.19: very difficult
- 0.20-0.39: difficult
- 0.40-0.60: average/moderately difficult
- 0.61-0.79: easy
- 0.80-1.0: very easy
P-Value
- p-value ranges from 0 to 1
- p > 0.10: weak or no evidence against H0
- 0.05 < p < 0.10: moderate evidence against H0
- 0.01 < p < 0.05: strong evidence against H0
- p ≤ 0.01: very strong evidence against H0
Item Discrimination
- Item discrimination ranges from 0 to 1
- ≥0.40: very good item
- 0.30-0.39: good item
- 0.20-0.29: fair item
- 0.09-0.19: poor item
Inter-Item Reliability Index
- Cronbach's alpha measures internal consistency
- α ≥ 0.9: excellent
- 0.9 > α ≥ 0.8: good
- 0.8 > α ≥ 0.7: acceptable
- 0.7 > α ≥ 0.6: questionable
- 0.6 > α ≥ 0.5: poor
- 0.5 > α: unacceptable
Interrater Reliability Coefficient
- K coefficient measures interrater reliability
- K = 1.0: excellent
- 0.9 > K ≥ 0.8: excellent
- 0.8 > K ≥ 0.7: good
- 0.7 > K ≥ 0.6: fair
- 0.6 > K ≥ 0.5: poor
- 0.5 > K: unacceptable
Research Methods and Statistics
- Statistics are used in research studies and test construction
- Measures of central tendency include mean, median, and mode
- Measures of variability include range, interquartile range, and standard deviation
- Test for normality includes Kolmogorov-Smirnov test and Shapiro-Wilk test
True Dichotomy
- Dichotomy in which there are only fixed possible categories
Artificial Dichotomy
- Dichotomy in which there are other possibilities in a certain category
Levene's Test
- Used to test if k samples have equal variance
- If p-value > 0.05, variance is not significantly different from each other
- If p-value < 0.05, there is a significant difference between variances
Bartlett's Test
- Used to test if k samples have equal variance
- More sensitive than Levene's Test
Test Development
- Includes test conceptualization, pilot work, and item construction
- Test conceptualization determines the construct, goal, user, taker, administration, format, response, benefits, and costs
Methods and Statistics Used in Research Studies and Test Construction
- Includes measures of central tendency, variability, and correlation
- Correlation coefficients include Pearson R, Spearman Rho, Biserial, Point Biserial, Phi Coefficient, and Tetrachoric
Statistical Tests
- Includes t-test, ANOVA, ANCOVA, MANOVA, and non-parametric tests
- Non-parametric tests include Mann Whitney U Test, Wilcoxon Signed Rank Test, Kruskal-Wallis H Test, and Friedman Test
This quiz covers the concept of item difficulty in psychological assessment, including the interpretation of item difficulty ranges and levels of difficulty. It is based on sources like Cohen & Swerdlik, Kaplan & Saccuzzo, and Groth & Wright.
Make Your Own Quizzes and Flashcards
Convert your notes into interactive study material.
Get started for free