Quiz
Cross-Cultural Research Methods
This quiz has question types that open in the usual player.
Questions in this quiz (67)
1Which of the following statements is correct?
- AAn appropriate translation from the source language into the target language ensures that the two tests are equivalent
- BTest adaptation is a broader concept than test translation
- CThe difficulty of educational test items never changes with the translation from one language into another
- DNone of the other alternatives are correct
2The following item was translated from English into Italian. This is an appropriate translation.

- ATrue
- BFalse
3The following item was translated from Italian into English. This is an appropriate translation.

- ATrue
- BFalse
4The following item was translated from English into Italian. It is an appropriate translation.

- ATrue
- BFalse
5The following item was translated from Italian into English. This is an appropriate translation.

- ATrue
- BFalse
6An Italian test measuring numerical skills consists of the following three items:
1. Quanto fa dieci moltiplicato per tre?
2. Quanto fa cinque più due?
3. Quanto fa dodici diviso quattro?
The test has been translated into English as follows:
1. What is ten multiplied per three?
2. What is five plus two?
3. What is twelve divided by four?
This is an appropriate translation.- ATrue
- BFalse
7Consider the English item: Which of the following is the central bank of the Eurozone?
A. ECB
B. WB
The item was translated into Italian as follows: Quale delle seguenti è la banca centrale dell’Eurozona?
1. ECB
2. WB
This is an appropriate translation.- ATrue
- BFalse
8Which of the following statements concerning the adaptation of passages is correct?
- APassages must always be translated literally
- BWhen the target language version of the passage is much shorter than the source language version, text can be added to the former version to make its length comparable to that of the source language version
- CTopics that are appropriate for a certain culture are certainly also appropriate for other cultures
- DNone of the other alternatives are correct
9Consider developing reading comprehension items that are based on this passage:
“In 1996, 46 percent of Japanese high school graduates went on to attend a two-year junior college or four-year university. Having a high level of education, such as a college diploma or a university degree, is critical for Japanese students, since education directly affects their future career and a university’s name value determines students’ future employment prospects. As a result, the competition to enter prestigious universities is extremely severe and creates many negative effects on Japanese high school students. Three of the major problems are student’s lack of creativity, lack of freedom, and lack of future vision.”
This passage is appropriate for inclusion in a cross-cultural educational test.- ATrue
- BFalse
10Consider the following completion exercise:
Fill in the blanks with the following words:
“The Chinese government has long kept tight reins on both traditional and new media to avoid potential _______ of its authority. Its tactics often entail strict media controls using monitoring systems and firewalls, shuttering publications or websites, and jailing dissident journalists, bloggers, and activists. Google’s battle with the Chinese government over internet censorship and the Norwegian Nobel Committee’s awarding of the 2010 Peace Prize to jailed Chinese activist Liu Xiaobo have also increased international _______ to censorship issues. At the same time, the country’s burgeoning _______ relies on the web for growth, and experts say the growing need for internet _______ is testing the regime’s control.”
[a] freedom [b] economy [c] attention [d] subversion
This exercise is not appropriate for inclusion in a cross-cultural educational test.- ATrue
- BFalse
11Consider developing reading comprehension items that are based on this passage:
“The Eiffel Tower is one of the most famous tourist attractions in the world. It is a steel tower with a height of three hundred and forty-two meters. The Eiffel Tower was erected on the occasion of the international exhibition held in Paris in 1889. It was founded by Gustav Eiffel and his assistant. It is the most visited site in France and enjoys a very impressive beauty and enjoys a very high reputation among all the world’s tourist sites. Although there are many tourist sites in Paris, the Eiffel Tower is the most important. The tower is open all year round for tourist attraction and receives millions of visitors from all over the world. It contains several restaurants and cafés, and many of the world’s most famous chefs serve in these restaurants.”
This passage is not appropriate for inclusion in a cross-cultural educational test.- ATrue
- BFalse
12A parameter is a measure referred to a sample.
- ATrue
- BFalse
13Usually, σ denotes the standard deviation of the population
- ATrue
- BFalse
14Statistical inference allows for making inferences about the behaviour of the sample, starting from the characteristics of the population from which the sample is drawn.
- ATrue
- BFalse
15The null and alternative hypotheses refer to the value of a statistic in two or more samples.
- ATrue
- BFalse
16α (the Greek letter alpha) is the probability of rejecting the null hypothesis when it is false
- ATrue
- BFalse
17The larger the sample size...
- Athe more likely it is that the null hypothesis is retained
- Bthe more likely it is that the null hypothesis is rejected
- Cthe larger the effect size
- Dthe smaller the effect size
- Ethe lower the power of the statistical test
18The t test for two independent samples tests the null hypothesis that two independent samples are selected from populations with different means
- ATrue
- BFalse
19Two samples, one made up of mothers and the other made up of their children, are independent samples
- ATrue
- BFalse
20In the t test for two independent samples (1 and 2), the sampling distribution of statistic t approximates a t-distribution with degrees of freedom df = \(n_1\) + \(n_2\) – 2
- ATrue
- BFalse
21The larger the absolute value of Cohen’s d, the larger the effect in the population
- ATrue
- BFalse
22According to Cohen (1988), d = —.4 denotes a very small effect in the population
- ATrue
- BFalse
23A psychoticism scale was administered to a sample of individuals from the United Kingdom and to a sample of individuals from North America. These statistics were observed.
Cohen's d is [blank_start]number[blank_end].
This effect size is:
[blank_start]size[blank_end] according to Cohen (1988)
[blank_start]size[blank_end] according to Sawilowsky (2009)
- A.197
- Bvery small
- Cvery small
24One-way univariate ANOVA tests the alternative hypothesis that two or more independent samples are selected from populations with different means
- ATrue
- BFalse
25In one-way univariate ANOVA, if the difference among the samples is smaller than the difference within the samples, the F statistic is smaller than 1
- ATrue
- BFalse
26In one-way univariate ANOVA, in an analysis comparing k = 5 groups, the degrees of freedom of the within-groups variance are k – 1 = 5 – 1 = 4
- ATrue
- BFalse
27The grand mean in one-way univariate ANOVA is the mean of the scores in the group with the largest number of individuals
- ATrue
- BFalse
28Assuming that \(SS_T\) = 55.34 and \(SS_W\) = 16.12, then \(SS_B\) = 39.22 (in one-way univariate ANOVA)
- ATrue
- BFalse
29\(\widehat{\eta}^2\) tends to underestimate the population effect size \(\eta^2\)
- ATrue
- BFalse
30For \(\widehat{\eta}^2\) (eta-squared), \(\widehat{\varepsilon}^2\) (epsilon-squared), and \(\widehat{\omega}^2\) (omega-squared) it is possible to compute a negative value
- ATrue
- BFalse
31\(\widehat{\omega}^2\) = .24 indicates that 24% of variance in the independent variable is accounted for by the dependent variable.
- ATrue
- BFalse
32A researcher conducted a one-way univariate ANOVA and computed \(\widehat{\eta}^2\), \(\widehat{\varepsilon}^2\) and \(\widehat{\omega}^2\) = x. He obtained the following values: .455, .501, and .464. However, he got a bit confused and does not know how to associate them with the three indicators. Could you help him?
\(\widehat{\eta}^2\) = [blank_start]x[blank_end]
\(\widehat{\varepsilon}^2\) = [blank_start]x[blank_end]
\(\widehat{\omega}^2\) = [blank_start]x[blank_end]- A.501
- B.464
- C.455
33A researcher wants to compute \(\widehat{\eta}^2\), \(\widehat{\varepsilon}^2\) and \(\widehat{\omega}^2\) for a one-way univariate ANOVA but he has only some data available. Could you help him?
• Four groups
• A total of 40 individuals
• SST = 641.7
• SSB = 242.6
Answers (to 4 decimal points):
\(\widehat{\eta}^2\) = [blank_start]x[blank_end]
\(\widehat{\varepsilon}^2\) = [blank_start]x[blank_end]
\(\widehat{\omega}^2\) = [blank_start]x[blank_end]- A.3781
- B.3262
- C.3207
34In a factorial design with two independent factors, the total deviance is the sum of the deviances of the main effects of the two factors and the within-groups deviance
- ATrue
- BFalse
35In a factorial design, the main effects are most appropriately interpreted when there is no interaction
- ATrue
- BFalse
36In factorial designs, there are two or more dependent variables and one independent variable
- ATrue
- BFalse
37In a factorial design with two factors, one having 3 levels and the other having 5 levels, there are 3 + 5 = 8 groups of individuals
- ATrue
- BFalse
38The output of a factorial design is presented.
For each of the following statements, indicate whether it is true or false:
1. Factor B consists of 3 levels: [blank_start]True[blank_end]
2. The overall sample consists of 30 individuals: [blank_start]True[blank_end]
3. Given a significance level at α = .001, the main effect of factor A and that of factor B are the only significant effects: [blank_start]False[blank_end]
- ATrue
- BFalse
- CTrue
- DFalse
- ETrue
- FFalse
39Depicted is the output of a factorial design with two factors. Compute \(\widehat{\varepsilon}^2\) and partial \(\widehat{\varepsilon}^2\) for the factor that is statistically significant α = .05, and interpret them according to the criteria by Field (2013) and to those by Cohen (1992)
Answers:
Statistically significant factor: Factor_[blank_start]A[blank_end]
\(\widehat{\varepsilon}^2\) :
value = [blank_start]x[blank_end]
Cohen (1992) interpretation = [blank_start]x[blank_end] effect size
Field (2013) interpretation = [blank_start]x[blank_end] effect size
partial \(\widehat{\varepsilon}^2\) :
value = [blank_start]x[blank_end]
Cohen (1992) interpretation = [blank_start]x[blank_end] effect size
Field (2013) interpretation = [blank_start]x[blank_end] effect size- AA
- B.1919
- Cmedium
- Dlarge
- E.2275
- Fmedium
- Glarge
40A researcher ran a factorial design with two factors but he only has some data available.
• N = 36
• \(df_A\) =2; \(df_B\) = 1; \(df_{A×B}\) = 1
• \(SS_A\) =8; \(SS_B\) = 2.78; \(SS_{A×B}\) = 4.22; \(SS_T\) = 35
He would like to compute partial \(\widehat{\omega}^2\) for factor A. Can you help him?
Answer:
\(\widehat{\omega}^2\) for factor A = [blank_start]x[blank_end]- A.216
41Whenever an item shows statistically significant DIF, item bias is present
- ATrue
- BFalse
42In DIF, the reference group is usually some type of minority group
- ATrue
- BFalse
43In both uniform and unidirectional nonuniform DIF, a group is always favoured over another group
- ATrue
- BFalse
44In crossing nonuniform DIF, a group is favoured at certain proficiency levels and disadvantaged at other proficiency levels
- ATrue
- BFalse
45DIF is a difference among groups of test takers for which the construct is supposed to differ
- ATrue
- BFalse
46A neuroticism scale consisting of 6 dichotomous items (0 = “No”, 1 = “Yes”) was administered to two samples of English speakers, one from the United Kingdom and the other from North America. The data were analysed with delta plot method, with the sample from North America as focal group, and the depicted. output was obtained
For each of the following statements, indicate whether it is true or false:
1. About 23% of individuals from the United Kingdom responded “No” to item ep7: [blank_start]True[blank_end]
2. About 85% of individuals from North America endorsed item ep1: [blank_start]False[blank_end]
3. Considering the fixed threshold at 1.5, no item is flagged for DIF: [blank_start]True[blank_end]
4. The delta point of item ep15 is 14.7965: [blank_start]False[blank_end]
5. Considering the threshold derived from data by assuming a normality distribution on the delta points and a significance level α = .05, which is .629, no item is flagged for DIF: [blank_start]True[blank_end]
- ATrue
- BFalse
- CTrue
- DFalse
- ETrue
- FFalse
- GTrue
- HFalse
- ITrue
- JFalse
47An extraversion scale consisting of 6 dichotomous items (0 = “No”, 1 = “Yes”) was administered to two samples of English speakers, one from the United Kingdom and the other from North America. The data were analysed with the standardization method, with the sample from North America as focal group, and the depicted output was obtained.
For each of the following statements, indicate whether it is true or false:
1. Items ep2, ep14, and ep17 favour individuals from the United Kingdom: [blank_start]True[blank_end]
2. Item ep4 is flagged for DIF when threshold at .05 and .1: [blank_start]False[blank_end]
3. Item ep2 is flagged for DIF when threshold at .05: [blank_start]True[blank_end]
4. According to the interpretation of the effect size of DIF by Dorans, Schmitt, & Bleistein (1992), no item shows large DIF: [blank_start]True[blank_end]
5. According to the interpretation of the effect size of DIF by Dorans, Schmitt, & Bleistein (1992), items ep2 and ep4 show negligible DIF: [blank_start]False[blank_end]
- ATrue
- BFalse
- CTrue
- DFalse
- ETrue
- FFalse
- GTrue
- HFalse
- ITrue
- JFalse
48A neuroticism scale consisting of 6 dichotomous items (0 = “No”, 1 = “Yes”) was administered to two samples of English speakers, one from the United Kingdom and the other from North America. The data were analysed with the Mantel-Haenszel method, with the sample from North America as focal group. This is part of the output.
For each of the following statements, indicate whether it is true or false:
1. Items ep7 and ep15 are flagged for DIF at a significance level of α = .05: [blank_start]True[blank_end]
2. Item ep1 favours the sample from North America: [blank_start]False[blank_end]
3. Item ep19 disadvantages the sample from the United Kingdom: [blank_start]True[blank_end]
4. According to the interpretation of the effect size of DIF by Holland & Thayer (1885), 1992), item ep10 shows moderate DIF: [blank_start]False[blank_end]
5. According to the interpretation of the effect size of DIF by Holland & Thayer (1885), item ep7 shows large DIF: [blank_start]True[blank_end]
- ATrue
- BFalse
- CTrue
- DFalse
- ETrue
- FFalse
- GTrue
- HFalse
- ITrue
- JFalse
49The logistic regression method for detecting DIF allows for detecting nonuniform DIF only
- ATrue
- BFalse
50The logistic regression method for detecting DIF evaluates uniform DIF by testing the statistical significance of the effect of the total test score
- ATrue
- BFalse
51In the logistic regression method for detecting DIF, if the slope of an item for the interaction between total test score and group membership is statistically significant, there is evidence of nonuniform DIF on that item
- ATrue
- BFalse
52In the logistic regression method for testing DIF: A ΔR2 of .10 is large according to the criteria by Jodoin and Gierl (2001) but moderate according to those by Zumbo and Thomas (1997)
- ATrue
- BFalse
53A ΔR2 of .02 is negligible according to both the criteria by Jodoin and Gierl (2001) and Zumbo and Thomas (1997)
- ATrue
- BFalse
54A neuroticism scale consisting of 6 dichotomous items (0 = “No”, 1 = “Yes”) was administered to two samples of English speakers, one from the United Kingdom and the other from North America. The data were analysed with the logistic regression method, and uniform DIF was tested. The sample from North America was set as focal group. This is part of the output.
For each of the following statements, indicate whether it is true or false:
1. Items ep7 and ep15 are flagged for uniform DIF at a significance level of α = .05: [blank_start]x[blank_end]
2. For item ep15, the size of DIF is negligible according to the criteria by Zumbo and Thomas (1997) but moderate according to those by Jodoin and Gierl (2001): [blank_start]x[blank_end]
3. If the significance level was set to α = .01, no item would show statistically significant uniform DIF: [blank_start]x[blank_end]
4. There is no item for which the slope for group membership is statistically significant at a significance level of α = .05: [blank_start]x[blank_end]
- ATrue
- BFalse
- CTrue
- DFalse
- ETrue
- FFalse
- GTrue
- HFalse
55A neuroticism scale consisting of 6 dichotomous items (0 = “No”, 1 = “Yes”) was administered to two samples of English speakers, one from the United Kingdom and the other from North America. The data were analysed with the logistic regression method, and nonuniform DIF was tested. The sample from North America was set as focal group. This is part of the output.
For each of the following statements, indicate whether it is true or false:
1. Items ep7 and ep15 are flagged for nonuniform DIF at a significance level of α = .05: [blank_start]x[blank_end]
2. For item ep15, the size of DIF is negligible according to both the criteria by Zumbo and Thomas (1997) and those by Jodoin and Gierl (2001): [blank_start]x[blank_end]
3. If the significance level was set to α = .01, no item would show statistically significant nonuniform DIF: [blank_start]x[blank_end]
4. There is no item for which the slope for the interaction between total test score and group membership is statistically significant at a significance level of α = .05: [blank_start]x[blank_end]
- ATrue
- BFalse
- CTrue
- DFalse
- ETrue
- FFalse
- GTrue
- HFalse
56A researcher applied the Lord’s chi-square test to the estimates of the 1PL model parameters and concluded that no item exhibited uniform or nonuniform DIF. This statement:
- ACan be correct
- BCannot be correct
- CCan be correct only if sample size is large enough for accurately estimating the item parameters of the 1PL model
- DCan be correct only if the 1PL model fits the data well
- EWe do not have enough information for establishing if the statement is correct or not
57The IRT methods for detecting DIF do not match test takers based on proficiency level
- ATrue
- BFalse
58In the IRT method, the larger the value of \(𝑐_𝑗\), the larger the probability of observing a 1 response to a moderate or difficult item by a test taker with a low proficiency level
- ATrue
- BFalse
59In the IRT method, assuming that the pseudo guessing parameter of an item is larger than 0, the probability of endorsing the item is .5 when the proficiency level of the test taker equals the difficulty parameter of the item
- ATrue
- BFalse
60The Lord’s chi-square test consists in evaluating the size of the area between the item characteristic curves of the reference and focal groups
- ATrue
- BFalse
61Which of the following statements is correct?
- AIn forward-backward translation, one bilingual translates the test from the source language to the target language and then the bilingual translates it back to the target language
- BThe two expressions “test translation” and “test adaptation” denote the same process
- CIdiomatic expressions often have a specific connotation in the source language that can be easily conveyed in the target language version
- DEnsured that all items and passages have been translated appropriately, the layout of the test and the order and page location of the items may vary greatly between the source and language versions
- ENone of the other alternatives are correct
62A researcher ran a one-way ANOVA with three independent samples and computed the following effect size measures: \(\widehat{\eta}^2\) = −0.95, \(\widehat{\varepsilon}^2\) = −2.34, and \(\widehat{\omega}^2\) = −3.22. Which of the following statements is correct?
- AFor sure, the researcher made some mistake
- BThe results of the researcher may be correct
- CResearcher’s findings are incomplete: The researcher must also compute partial \(\widehat{\eta}^2\), partial \(\widehat{\varepsilon}^2\), and partial \(\widehat{\omega}^2\)
- DResearcher’s findings are incomplete: The researcher must also compute Cohen’s d
- ENone of the other alternatives are correct
63A researcher runs a one-way ANOVA to compare the expression of positive emotions in three independent groups of individuals (i.e., Romanian ROMs, Moroccan immigrants, and Romanian immigrants). The output of the analysis conducted with R is shown.
\(\widehat{\omega}^2\) = [blank_start]x[blank_end]
- A.098
64A researcher runs a one-way ANOVA to compare the expression of negative emotions in three independent groups of individuals (i.e., Romanian ROMs, Moroccan immigrants, and Romanian immigrants). The output of the analysis conducted with R is shown.
\(\widehat{\varepsilon}^2\) = [blank_start]x[blank_end]
- A.028
65A researcher wanted to compare the expression of positive emotions in Moroccan immigrants and Romanian immigrants. The researcher obtained the shown statistics.
Cohen's d = [blank_start]x[blank_end]
- A.399
66Moroccan immigrants and Romanian immigrants were presented with a scale measuring the expression
of eight positive emotions. For each positive emotion, respondents were asked to state whether they used
to express it (1 – “Yes”) or not (0 – “No”). The data were analysed with the Mantel-Haenszel method, using
the function “difMH” from the R package “difR”. Romanian immigrants were set as focal group. Part of the
output is shown.
For each of the following statements, indicate whether it is true or false:
a) No item is flagged for DIF at a significance level of α = .01: [blank_start]x[blank_end]
b) Item PE4 favours Moroccan immigrants: [blank_start]x[blank_end]
c) Items PE2, PE4, PE5, and PE6 show statistically significant nonuniform DIF when α = .05: [blank_start]x[blank_end]
d) The MH-χ 2 ranges from .0274 to .2033: [blank_start]x[blank_end]
e) According to the interpretation of the effect size of DIF by Holland & Thayer (1885), items PE1, PE2, PE6, and PE7 show negligible DIF: [blank_start]x[blank_end]
- ATrue
- BFalse
- CTrue
- DFalse
- ETrue
- FFalse
- GTrue
- HFalse
- ITrue
- JFalse
67Moroccan immigrants and Romanian immigrants were presented with a scale measuring the expression of eight positive emotions. For each positive emotion, respondents were asked to state whether they used to express it (1 – “Yes”) or not (0 – “No”). Using the function “difLogistic” from the R package “difR”, the logistic regression method was used to detect the presence of nonuniform DIF. Romanian immigrants were set as focal group. Part of the output is shown.
For each of the following statements, indicate whether it is true or false:
a) If the significance level was set to α = .01, no item would show statistically significant nonuniform DIF: [blank_start]x[blank_end]
b) Items PE1 and PE4 are flagged for DIF at a significance level of α = .05: [blank_start]x[blank_end]
c) For item PE3, the R^2 of the logistic regression model including the intercept and the slope for the total test score is .0026: [blank_start]x[blank_end]
d) For all items, the size of DIF is negligible according to both the criteria by Zumbo and Thomas (1997) and those by Jodoin and Gierl (2001): [blank_start]x[blank_end]
e) For items PE1 and PE4, the slope for group membership is statistically significant at a significance level of α = .05: [blank_start]x[blank_end]
- ATrue
- BFalse
- CTrue
- DFalse
- ETrue
- FFalse
- GTrue
- HFalse
- ITrue
- JFalse
Information
- Description
- Compilation of exercises from the powerpoints and from moodle. I included the specific translation questions from the slides just in case even though he probably (hopefully) won't ask these
- Author
- Leigha C
- Language
- English
- Views
- 55
- Tags
- Rating
- No ratings yet Rate this quiz