Question 1

What is the main goal of an experimental design?&#10;A) To assess relationships between naturally occurring variables&#10;B) To make observations of behaviour in a natural or laboratory setting without manipulating anything&#10;C) To compare two or more pre-existing groups of people&#10;D) To examine differences between conditions

Accepted Answer

The main goal of an experimental design is to examine differences between conditions, typically by manipulating one or more variables to determine their effect on certain outcomes. This allows researchers to infer causality.

Question 2

Which of the following statements is correct?&#10;A) In an experimental study, a dependent variable must be categorical, and an independent variable must be continuous.&#10;B) In an experimental study, an independent variable must be ordinal, and a dependent variable must be ratio data.&#10;C) In an experimental study, an independent variable must be categorical, and a dependent variable must be continuous.&#10;D) In an experimental study, an independent variable must be interval data, and a dependent variable must be continuous.

Accepted Answer

In an experimental study, the independent variable is manipulated by the researcher to observe its effect on the dependent variable. The independent variable is often categorical (e.g., treatment vs. no treatment), and the dependent variable is typically continuous, allowing for measurement of changes influenced by the independent variable.

Question 3

What is the difference between experimental and quasi-experimental research?&#10;A) In an experimental study, participants are randomly assigned to conditions, whereas they are not assigned randomly in a quasi-experimental study.&#10;B) In a quasi-experimental study, participants are randomly assigned to conditions, whereas they are not assigned randomly in an experimental study.&#10;C) There is no difference between them.&#10;D) A quasi-experimental study uses a repeated measures design, whereas an experimental study uses an independent measures design design.

Accepted Answer

In experimental research, the key feature is the random assignment of participants to different conditions or groups, which helps in establishing cause-and-effect relationships by controlling for extraneous variables. Quasi-experimental research, on the other hand, does not use random assignment, often due to practical or ethical limitations, making it harder to infer causality with the same level of confidence.

Question 4

What is familywise error?&#10;A) The approximate standard deviation of a statistical sample population&#10;B) The amount of variation or dispersion of a set of values&#10;C) The error of rejecting a null hypothesis when it is true&#10;D) The probability of making one or more false discoveries when performing multiple hypotheses tests

Accepted Answer

Familywise error refers to the probability of making at least one Type I error (rejecting a true null hypothesis) across multiple hypothesis tests. When multiple comparisons are made, the chance of incorrectly rejecting a true null hypothesis increases, hence the focus on controlling the familywise error rate.

Question 5

Which of the following tests is not a factorial design?&#10;A) A two-way independent measures ANOVA&#10;B) One-way independent measures ANOVA&#10;C) A three-way independent measures ANOVA&#10;D) A two-way repeated measures ANOVA

Accepted Answer

A factorial design involves two or more independent variables, also known as factors. A one-way independent measures ANOVA (Choice B) only involves one independent variable, making it not a factorial design. Choices A, C, and D involve two or more independent variables, fitting the definition of factorial designs.

Question 6

When should you have a two-tailed hypothesis?&#10;A) When your data is not normally distributed&#10;B) When the previous research findings are inconsistent&#10;C) When the previous findings are consistent&#10;D) When you have a directional prediction

Accepted Answer

A two-tailed hypothesis is appropriate when previous research findings are inconsistent, as it allows for the possibility of an effect in either direction, not presupposing a specific direction of the effect.

Question 7

What are the assumptions of parametric statistical analyses?&#10;A) The normal distribution, homogeneity of variance, and independence of observations&#10;B) The normal distribution and homogeneity of variance&#10;C) The normal distribution, homogeneity of variance, independence of observations, and interval or ratio data&#10;D) The normal distribution and interval or ratio data

Accepted Answer

Parametric statistical analyses assume the normal distribution of data, homogeneity of variance (equal variances across groups), independence of observations (each observation is collected without influence from the others), and that the data are measured on an interval or ratio scale, which allows for the use of mean values and standard deviations.

Question 8

Which of the following options is not one of the approaches to deal with confounding variables?&#10;A) Test-retest approach&#10;B) Randomly allocate participants.&#10;C) Use a matched participants design.&#10;D) Run an analysis of covariance (ANCOVA).

Accepted Answer

The test-retest approach is not a method to deal with confounding variables; it is a method used to assess the reliability of a measurement by testing the same individuals at two points in time. The other options (B, C, D) are legitimate approaches to address confounding variables in research designs.

Question 9

Which types of validity and reliability are particularly important for experimental studies?&#10;A) External validity and inter-rater reliability&#10;B) Internal validity and internal consistency&#10;C) Internal validity and test-retest reliability&#10;D) Ecological validity and test-retest reliability

Accepted Answer

Internal validity is crucial for ensuring that the results of an experiment are due to the manipulation of the independent variable and not other factors. Test-retest reliability is important for ensuring that the results are consistent over time.

Question 10

Which of the following options is not an ethical responsibility of a researcher?&#10;A) Gain informed consent from participants.&#10;B) Fully inform participants about the aims and hypotheses of the study before they take part.&#10;C) Protect participants from risks to physical and/or psychological harm or distress.&#10;D) Assure the confidentiality of information.

Accepted Answer

Option B is incorrect because researchers often do not fully inform participants about the aims and hypotheses of the study before they take part, especially in studies involving deception. This is sometimes necessary to avoid biasing the participants' responses. However, ethical guidelines require that participants are debriefed after their participation, where they are fully informed about the study's aims and any deception that was involved.

Deck 5: Experimental Design