RMB multiple choice questions

What is a dataset?

A) A theoretical construct used to explain an effect  

B) A collection of data acquired for a specific purpose  

C) A single measurement from an experiment  

D) A statistical test for comparing groups

B) A collection of data acquired for a specific purpose 

How is a variable defined in research?

A) A constant number that represents the same value always  

B) A quality that cannot be measured numerically  

C) A number or category that can vary across participants  

D) A method for data analysis

C) A number or category that can vary across participants

Which type of variable has categories with no inherent order?

A) Ordinal  

B) Interval  

C) Nominal  

D) Ratio

C) Nominal

An ordinal variable is best described as one that:

A) Has categories with a natural order but unclear magnitude differences  

B) Is measured on a continuous scale  

C) Has a true zero point and allows for ratio comparisons  

D) Contains unordered, categorical labels

A) Has categories with a natural order but unclear magnitude differences

Which scale of measurement allows you to interpret ratios because zero is meaningful?

A) Nominal  

B) Ordinal  

C) Interval  

D) Ratio

D) Ratio

If the true height of a person is measured continuously, but then recorded only as the nearest centimeter, what change occurs?

A) It changes from interval to nominal  

B) It changes from continuous to discrete  

C) It remains continuous and ratio  

D) It becomes ordinal

B) It changes from continuous to discrete

7. A continuous variable is defined as one that:

A) Only takes on a fixed set of numbers  

B) Can take any value within a range  

C) Only contains categories  

D) Is measured using arbitrary labels

B) Can take any value within a range

When measuring temperature in Celsius, which scale is used?

A) Nominal  

B) Ordinal  

C) Interval  

D) Ratio

C) Interval

Under what condition does an interval variable become a ratio variable?  

A) When it's differences are non interpretable  

B) When zero has a special, meaningful value  

C) When it is recorded in categories  

D) When it is measured on a discrete scale

B) When zero has a special, meaningful value

When researchers decide how a variable is measured, this is known as the:

A) Research design issue  

B) Variable transformation process  

C) Choice of measurement 

D) Statistical analysis decision

C) Choice of measurement

What is a scientific hypothesis?

A) A statement of fact proven by data  

B) A testable prediction derived from theory  

C) An unchangeable rule about nature  

D) A description of variables in a study

B) A testable prediction derived from theory

The null hypothesis in an experiment usually states that:

A) There is a significant effect due to the manipulation  

B) Variables are not measurable  

C) There is no effect or difference  

D) The alternative hypothesis must be true

C) There is no effect or difference

In an experiment, the variable that is deliberately manipulated by the researcher is the:

A) Dependent variable  

B) Confounding variable  

C) Outcome variable  

D) Independent variable

D) Independent variable

Which variable is typically expected to change as a result of the independent variable? 

A) Control variable  

B) Extraneous variable  

C) Dependent variable  

D) Constant variable

C) Dependent variable

Statistical tests in research are used to:

A) Conceal data trends  

B) Compare the data to the null hypothesis  

C) Verify the experimental procedure  

D) Convert qualitative data to quantitative data

B) Compare the data to the null hypothesis

Which error type occurs when we incorrectly reject a true null hypothesis?

A) Type II error  

B) Sampling error  

C) Type I error  

D) Random error

C) Type I error

Rejecting the null hypothesis when it is false is known as avoiding a:

A) Type II error (false negative)  

B) Type I error (false positive)  

C) Random error  

D) Systematic error

A) Type II error (false negative)

What is the primary purpose of manipulating an independent variable in an experiment?

A) To observe the differences in sampling methods  

B) To explore associations regardless of causality  

C) To determine its effect on the dependent variable  

D) To balance out measurement error

C) To determine its effect on the dependent variable 

In hypothesis testing, what does “accepting the experimental hypothesis” imply?

A) All observed differences are due to random chance  

B) The null hypothesis was rejected based on the data  

C) No modifications are needed in the research design  

D) The predictions were all incorrect

B) The null hypothesis was rejected based on the data

Which statement best explains the burden of proof in hypothesis testing?  

A) The researcher must prove the null hypothesis true  

B) The alternative hypothesis is assumed true until data says otherwise  

C) The null hypothesis is assumed true until evidence shows otherwise  

D) Neither hypothesis is ever objectively tested

C) The null hypothesis is assumed true until evidence shows otherwise

What is a population in research terminology?

A) The total group of people from which a sample is drawn  

B) A subset of participants selected for convenience  

C) A collection of data values  

D) Another term for the dataset

A) The total group of people from which a sample is drawn

A sample is best described as:

A) The ideal representation of the entire world  

B) The total set of people in the study  

C) A portion of the population used to estimate population parameters  

D) An unrepresentative group chosen without intention

C) A portion of the population used to estimate population parameters

Histograms are typically used to:

A) Display trends over time  

B) Represent the distribution of a data sample  

C) Present categorical comparisons  

D) Illustrate experimental procedures

B) Represent the distribution of a data sample

Which sampling method involves selecting every 5th participant from a list?

A) Random sampling  

B) Stratified sampling  

C) Systematic sampling  

D) Convenience sampling

C) Systematic sampling

In stratified sampling, participants are selected such that the sample:

A) Reflects the key characteristics of the overall population  

B) Includes only the most easily accessible individuals  

C) Follows a fixed numerical sequence  

D) Consists exclusively of volunteers

A) Reflects the key characteristics of the overall population

Recruiting participants based on who is most readily available is known as:

A) Random sampling  

B) Systematic sampling  

C) Cluster sampling  

D) Convenience sampling

D) Convenience sampling

Which sampling method involves recruiting entire groups (like a whole class or team) at once?

A) Stratified sampling  

B) Cluster sampling  

C) Systematic sampling  

D) Random sampling

B) Cluster sampling

Sampling bias can occur when:

A) The sample size is too large  

B) Additional variability in the population is not controlled  

C) Every group in the population is equally represented  

D) Random errors are minimised

B) Additional variability in the population is not controlled

A systematic bias in sampling refers to:

A) Random chance creating differences between the sample and population  

B) An inherent flaw in the sampling method that consistently over- or under-represents certain groups  

C) A statistical error corrected by increasing sample size  

D) The natural variability found within any sample

B) An inherent flaw in the sampling method that consistently over- or under-represents certain groups

In trying to obtain a representative sample, why is recruiting a larger sample sometimes recommended?

A) It completely eliminates systematic bias  

B) It increases the chances that any bias will be averaged out  

C) It is easier and less expensive  

D) It reduces the need for experimental controls

B) It increases the chances that any bias will be averaged out

How is the sample mean calculated?

A) Sum of all values divided by the number of observations  

B) The square root of the sum of values  

C) The most frequently occurring value  

D) The sum of squares divided by degrees of freedom

A) Sum of all values divided by the number of observations

Why is Bessel's correction used when estimating the sample standard deviation?  

A) To reduce the mean of the sample  

B) To correct the bias in the estimation, making the SD slightly larger  

C) To convert continuous data into discrete data  

D) To ensure the standard error is overestimated

B) To correct the bias in the estimation, making the SD slightly larger

The standard error of the mean (SEM) is defined as:

A) The sample standard deviation multiplied by the sample size  

B) The variance of the sample divided by the number of observations  

C) The sample standard deviation divided by the square root of the sample size  

D) The difference between the maximum and minimum values

C) The sample standard deviation divided by the square root of the sample size

In a one-sample t-test, the t-value is computed using which of the following formulas?  

A) (Sample mean – Comparison value) / (Sample variance)  

B) (Sample mean – Comparison value) / (Standard error of the mean)  

C) (Comparison value – Sample median) / (Standard deviation)  

D) (Sample mean + Comparison value) / (Degrees of freedom)

B) (Sample mean – Comparison value) / (Standard error of the mean) 

A larger t-value in a one-sample t-test typically indicates:

A) That the sample mean is very close to the comparison value  

B) That there is a larger difference between the sample mean and the comparison value relative to the SEM

C) That the test is non-parametric  

D) That the sample size is too small

B) That there is a larger difference between the sample mean and the comparison value relative to the SEM

When using a paired samples t-test, the analysis is comparing:

A) Two independent groups  

B) The difference between each pair’s values to zero  

C) The overall means of two unrelated samples  

D) Variances of two separate populations

B) The difference between each pair’s values to zero  

Which of the following best distinguishes a paired samples t-test from an independent samples t-test?

A) Paired samples require equal variances while independent samples do not  

B) Paired samples involve the same participants measured twice, while independent samples involve two separate groups  

C) Paired samples use nominal data, whereas independent samples use ratio data  

D) There is no difference between the two tests

B) Paired samples involve the same participants measured twice, while independent samples involve two separate groups

For an independent samples t-test, the degrees of freedom (assuming equal variances) are computed as:  

A) n₁ + n₂  

B) n₁ + n₂ – 1  

C) n₁ + n₂ – 2  

D) n₁ – n₂

C) n₁ + n₂ – 2

Cohen’s d is best described as a measure of:

A) The reliability of the data collection method  

B) The magnitude of the difference between two group means  

C) The p-value of a statistical test  

D) The sample size used in an experiment

B) The magnitude of the difference between two group means

Cohen’s d values of approximately 0.2, 0.5, and 0.8 are typically interpreted as:

A) Weak, moderate, and negligible effects respectively  

B) Large, very large, and enormous effects respectively  

C) Small, medium, and large effects respectively  

D) Insignificant, significant, and extremely significant effects respectively

C) Small, medium, and large effects respectively

The p-value in hypothesis testing represents:

A) The probability that the null hypothesis is true  

B) The probability of obtaining a test statistic at least as extreme as the one observed, assuming the null is true  

C) The effect size of the experimental manipulation  

D) The sample mean variation

B) The probability of obtaining a test statistic at least as extreme as the one observed, assuming the null is true

A common misconception about p-values is that they:

A) Indicate the degree of compatibility between the data and the null hypothesis  

B) Are influenced by sample size  

C) Express the probability that the observed effects were produced solely by chance  

D) Are computed assuming the null hypothesis is true

C) Express the probability that the observed effects were produced solely by chance

By convention, a p-value less than which threshold is typically deemed statistically significant?

A) 0.10  

B) 0.05  

C) 0.01  

D) 0.001

B) 0.05

When the assumptions for parametric tests are not met, a common alternative for a one-sample t-test is the:

A) Mann–Whitney U test  

B) Wilcoxon signed-rank test  

C) Chi-square test  

D) ANOVA

B) Wilcoxon signed-rank test

The Mann–Whitney U test is most appropriately used for comparing:

A) Two related samples  

B) More than two group means  

C) Two independent samples when the data are not normally distributed  

D) The variances of two groups

C) Two independent samples when the data are not normally distributed  

A key advantage of non-parametric tests is that they:  

A) Require a strict assumption of normal distribution  

B) Provide information about the mean and standard deviation  

C) Are robust to violations of normality  

D) Always have higher statistical power than parametric tests

C) Are robust to violations of normality

When comparing central tendencies for non-normal data, which measure is typically used? 

A) Mean  

B) Mode  

C) Median  

D) Range

C) Median 

The primary purpose of ANOVA is to:

A) Compare the medians of two groups  

B) Test for overall differences among three or more group means  

C) Calculate effect sizes only  

D) Replace all t-tests for any comparison

B) Test for overall differences among three or more group means

In ANOVA terminology, “SS_between” refers to:

A) The variability within each group  

B) The total sum of squared differences in the data  

C) The portion of total variability attributed to differences between group means  

D) The ratio of between-group variance to sample size

C) The portion of total variability attributed to differences between group means

The F-statistic in an ANOVA is computed as:

A) MSE within / MSE between  

B) MSE between / MSE within  

C) SS_total / Degrees of freedom  

D) Variance / Mean difference

B) MSE between / MSE within  

Post hoc tests in ANOVA are conducted to:

A) Verify the homogeneity of variance assumption  

B) Determine which specific group means differ from the others  

C) Calculate the overall F-statistic  

D) Transform non-parametric data into parametric data

B) Determine which specific group means differ from the others

Which of the following is an assumption that must be met for between‐subjects ANOVA?

A) Data observations are independent  

B) Variables are measured on an ordinal scale  

C) Groups have different variances  

D) The dependent variable is nominal

A) Data observations are independent

Levene’s test in the context of ANOVA is used to check:

A) Normality of the data  

B) Equality of variances across groups  

C) The sample mean  

D) The presence of outliers

B) Equality of variances across groups

Which qualitative method uses photography to explore people's environments and empower participants?  

A) Story completion  

B) Photovoice  

C) Focus groups  

D) Ethnography

B) Photovoice

A qualitative interview is best described as a method to:

A) Collect numerical data only  

B) Adapt a standardised questionnaire  

C) Explore participants’ experiences through in-depth conversation  

D) Randomly select survey items

C) Explore participants’ experiences through in-depth conversation

Qualitative surveys differ from quantitative surveys in that they:

A) Rely exclusively on numerical scales  

B) Emphasise open-ended responses and participant-led content  

C) Do not allow for any anonymity  

D) Use fixed-response items exclusively

B) Emphasise open-ended responses and participant-led content 

The story completion method in qualitative research involves:

A) Completing a narrative based on a provided story stem  

B) Writing a diary without any prompts  

C) Conducting a structured interview  

D) Rating pre-determined statements quantitatively

A) Completing a narrative based on a provided story stem

One advantage of solicited diaries in qualitative research is that they: 

A) Provide solely quantitative results  

B) Offer researchers complete control over data interpretation  

C) Give participants more control over how they record their experiences  

D) Eliminate the need for informed consent

C) Give participants more control over how they record their experiences

Modern diary methods increasingly use apps because they:

A) Are less secure than paper diaries  

B) Improve accuracy and ease of data entry compared to traditional methods  

C) Make it impossible to track timing of events  

D) Replace qualitative data with quantitative only

B) Improve accuracy and ease of data entry compared to traditional methods

Reflexive thematic analysis (TA) is characterized by:

A) Rigid adherence to coding reliability measures  

B) The researcher’s active engagement and subjectivity in interpreting data  

C) Only using pre-defined codebooks  

D) Ignoring researcher positionality

B) The researcher’s active engagement and subjectivity in interpreting data

One criticism of problematic uses of thematic analysis is that researchers sometimes treat TA as:

A) An entirely qualitative approach  

B) A flexible method that adjusts to researcher subjectivity  

C) A “one-size-fits-all” recipe that ignores deeper interpretative work  

D) A method that requires no reflexive thought

C) A “one-size-fits-all” recipe that ignores deeper interpretative work

Compared to reflexive TA, Interpretative Phenomenological Analysis (IPA) is more focused on:

A) Group-level discourses  

B) Patterns of language use in large datasets  

C) In-depth exploration of individual personal experiences  

D) Quantitative pattern extraction

C) In-depth exploration of individual personal experiences

A key difference between TA and discourse analysis (DA) is that DA places more emphasis on:

A) Organic, inductive theme development  

B) The social and performative functions of language  

C) The frequency counts of words  

D) Strict adherence to a fixed codebook

B) The social and performative functions of language

Reflexive TA is particularly appropriate when the research focus is on:

A) Pre-determined theoretical constructs only  

B) Understanding themes across a dataset without an idiographic focus  

C) Only coding numerical data  

D) Testing hypotheses statistically

B) Understanding themes across a dataset without an idiographic focus

The process of “generating initial themes” in TA implies that:

A) The themes are pre-existing and waiting to be discovered  

B) Themes emerge organically as patterns of shared meaning  

C) A rigid codebook is applied without researcher input  

D) Quantitative analysis is central to the method

B) Themes emerge organically as patterns of shared meaning

Meta-science is best defined as the study of:

A) How scientific methods and processes themselves can be evaluated and improved  

B) Only qualitative research methods  

C) The biological sciences  

D) A specific statistical test used in experiments

A) How scientific methods and processes themselves can be evaluated and improved

A reproducible result means that:

A) Different researchers obtain completely different outcomes  

B) The same analysis on the same dataset produces the same result  

C) The result cannot be verified by other teams  

D) One study consistently finds a significant effect in every context

B) The same analysis on the same dataset produces the same result

Replicability in research refers to:

A) Obtaining the same results when applying the same analysis to a new independent dataset  

B) The exact duplication of the original dataset  

C) Changing the analysis and obtaining a different result  

D) Using the same methods without any modifications

A) Obtaining the same results when applying the same analysis to a new independent dataset

Robust research findings mean that: 

A) Using different analysis approaches on the same dataset gives similar overall results  

B) The results are overly sensitive to slight analysis changes  

C) The effects only appear under one specific analysis method  

D) The sample size does not matter

A) Using different analysis approaches on the same dataset gives similar overall results

Generalisability in research is the extent to which results can be: 

A) Confined to the original study’s sample only  

B) Applied to different populations or settings in new studies  

C) Considered irrelevant outside a laboratory  

D) Eliminated by statistical corrections

B) Applied to different populations or settings in new studies

A p-curve analysis is used to assess:

A) The distribution of published p-values to determine evidential value  

B) The shape of the normal distribution explicitly  

C) The mean difference between groups  

D) The reliability of qualitative themes

A) The distribution of published p-values to determine evidential value

The file-drawer problem refers to:

A) The standard practice of storing datasets in drawers  

B) The tendency for non-significant findings to remain unpublished  

C) The process of pre-registering studies  

D) A method of qualitative analysis

B) The tendency for non-significant findings to remain unpublished  

HARKing stands for “Hypothesizing After the Results are Known” and is problematic because it:

A) Enhances the transparency of the study  

B) Undermines the integrity of hypothesis testing  

C) Is a necessary step in data analysis  

D) Only occurs in qualitative studies

B) Undermines the integrity of hypothesis testing  

P-hacking involves:

A) Rigorously pre registering one's methods  

B) Adjusting data or analyses until statistically significant results are obtained  

C) Conducting open and replicable research  

D) Testing multiple hypotheses without any bias

B) Adjusting data or analyses until statistically significant results are obtained 

Pre-registration in open science is important because it:

A) Eliminates the need for ethics approval  

B) Reduces flexibility in research design  

C) Helps to prevent practices like HARKing and p-hacking  

D) Guarantees that the null hypothesis will be rejected

C) Helps to prevent practices like HARKing and p-hacking

Open science practices typically encourage:

A) Keeping all research data secret  

B) Transparent sharing of methods, data, and code  

C) Only publishing significant findings  

D) Limiting access to research for non-experts

B) Transparent sharing of methods, data, and code

Ethical sampling in research is important because:

A) It guarantees that every group is over-represented  

B) It ensures that the findings do not reinforce inequalities or marginalise groups  

C) It solely focuses on convenience  

D) It removes the need for informed consent

B) It ensures that the findings do not reinforce inequalities or marginalise groups

A between-subjects (independent groups) design is characterised by:

A) Each participant taking part in all conditions  

B) Each participant contributing data to only one condition  

C) A design where participants are constantly switching between conditions  

D) Random assignment being unnecessary

B) Each participant contributing data to only one condition

A within-subjects (repeated measures) design can be limited by:

A) Practice or fatigue effects confounding the results  

B) The impossibility of counterbalancing  

C) Too few measurements of the dependent variable  

D) The inability to use statistical tests

A) Practice or fatigue effects confounding the results

Counterbalancing in a repeated measures design is used to: 

A) Ensure that order effects (e.g., practice or fatigue) are distributed evenly across conditions  

B) Randomly assign participants to totally independent groups  

C) Replace the need to calculate degrees of freedom  

D) Guarantee that the independent variable has no effect

A) Ensure that order effects (e.g., practice or fatigue) are distributed evenly across conditions