TYPES OF EXPERIMENT:

LABORATORY, FIELD EXPERIMENTS, NATURAL AND QUASI-EXPERIMENTS

 Laboratory, field, natural and quasi-experiments all investigate relationships between variables by comparing groups of scores. Still, there are also significant differences between different types of experiments, such as how respected they are.

• Laboratory experiments fulfil all the criteria of an actual experiment but have problems with external validity.

• Field experiments are true but don't occur in a controlled environment or have a random allocation of participants.

• Natural and quasi-experiments cannot prove or disprove causation with the same confidence as a lab experiment.

• Natural experiments don't manipulate the IV; they observe changes in a naturally occurring IV.

• Quasi-experiments don't randomly allocate participants to conditions.

QUASI-EXPERIMENTS

The prefix "quasi" implies "resembling" or "similar to." Therefore, quasi-experimental research shares similarities with experimental research but does not meet all the criteria of true experimental research. Quasi-experiments are frequently conducted to assess the effectiveness of a treatment, such as a particular form of psychotherapy or an educational intervention.

There are many quasi-experiments, but we will discuss just two of the most common ones below.

• A non-equivalent-group quasi-experiment ( when you can’t randomly allocate groups to conditions).

• A between-subjects quasi-experiment ( when you don’t want to allocate groups to conditions randomly).

A BETWEEN SUBJECT QUASI EXPERIMENT. In "true experiments," participants are randomly assigned to conditions (in an independent group design), and the resulting groups' reactions to the independent variable (IV) are compared with the dependent variable (DV). In such cases, researchers typically regard these groups as similar. For example, the groups are derived from a single pool of participants and then randomly divided into two. As a result, each group's characteristics are similar or equivalent.

However, when researchers cannot manipulate the characteristics of their participants; for example, they cannot make people left-handed or right-handed nor change a person's biological sex. Therefore, if the focus of an experiment is to compare the different dynamics between two or more groups of participants rather than how they behave when presented with two different conditions, then it falls under a between-subjects quasi-experiment. The objective of between-subjects quasi-experiments is to establish if there are differences in pre-existing group variables.

For example, a study might explore the variance in IQ scores between male and female participants, with biological sex as the IV and IQ scores as the DV. Since the researcher cannot manipulate predetermined group membership, the design is not considered a true experiment. It's important to note that participants in a between-subjects quasi-experiment engage in the same task or condition.

In this design, participants are assigned to different conditions, but the assignment is not random. Researchers choose to assign participants based on pre-existing characteristics. These differences between groups of people are termed naturally occurring IVs, which refer to individual differences. The 'differences' under investigation typically involve participant characteristics such as gender, age, sexual orientation, or group membership (e.g., university graduates, children from single-parent homes, ethnic groups, nationality, marital status, homeowners vs. renters, sports team fans, etc.). The researcher typically seeks to determine whether the groups differ, or sometimes, whether they do not differ, on measured variables such as self-esteem, extraversion, intelligence, kindness, well-being, depression, IQ, and more.

Remember, a between-subject quasi-group design means the groups are the independent variable. Consequently, researchers consider the groups to be non-similar.

EXAMPLES:

Effect of Classroom Environment on Student Learning:

This study aimed to investigate the influence of classroom environment on student learning outcomes by comparing students in traditional classroom settings with those in experimental classroom designs. Researchers selected schools with different classroom environments, such as traditional lecture-style classrooms versus active learning classrooms. They assessed student learning outcomes, including academic performance and engagement, and compared them between the two groups.

Reference: Freeman, S., Eddy, S. L., McDonough, M., Smith, M. K., Okoroafor, N., Jordt, H., & Wenderoth, M. P. (2014). Active learning increases student performance in science, engineering, and mathematics. Proceedings of the National Academy of Sciences, 111(23), 8410–8415.

Impact of Teaching Methods on Reading Comprehension:

This study investigated the effectiveness of different teaching methods on reading comprehension by comparing students taught using traditional methods with those taught using innovative instructional approaches. Researchers randomly assigned students to different instructional conditions within their classrooms. They administered pre-tests and post-tests to assess reading comprehension skills and compared the performance between the groups.

Reference: Chall, J. S., Jacobs, V. A., & Baldwin, L. E. (1990). The Reading Crisis: Why Poor Children Fall Behind. Harvard University Press.

Evaluation of Technology Integration in Education:

This study aimed to evaluate the impact of technology integration in education by comparing students exposed to technology-rich learning environments with those in traditional classroom settings. Researchers selected schools with varying degrees of technology integration and assessed student outcomes, such as academic achievement and technology proficiency. They compared the performance and attitudes of students between the two groups.

Reference: Tondeur, J., van Braak, J., Ertmer, P. A., & Ottenbreit-Leftwich, A. (2017). Understanding the Relationship Between Teachers’ Pedagogical Beliefs and Technology Use in Education: A Systematic Review of Qualitative Evidence. Educational Technology Research and Development, 65(3), 555–575

NON-EQUIVALENT GROUP DESIGN QUASI-EXPERIMENTS.
To conduct a true experiment, you would typically randomise half of the patients in a mental health clinic to receive the new treatment while the other half—the control group—receives the standard treatment for depression. Patient progress is then monitored over time by collecting data on symptoms to assess whether the new treatment produces significantly different outcomes than the standard one.

However, ethical considerations may prevent the directors of the mental health clinic from allowing random assignment of patients to treatments. In such cases, conducting a true experiment becomes impractical.

Instead, a quasi-experimental design can be employed. In this design, participants are not randomly assigned to conditions. Rather, existing groups or conditions are compared, and participant differences are not controlled. For instance, researchers may seek to compare the effectiveness of a new type of psychotherapy. They might utilize patients from two different hospitals, with one hospital implementing the new therapy and the other using the old one. Since random assignment is not feasible, participants are not allocated randomly to these conditions, potentially leading to group differences. In this setup, the researcher selects comparable pre-existing groups. Still, only one group receives the treatment, highlighting the challenge of uncontrolled participant differences due to the absence of random assignment.

Here is another example: Imagine a researcher aiming to assess the efficacy of a new reading program for preschool-aged children. One approach might involve conducting a study with a group of preschool students from one school exposed to the new reading curriculum. In contrast, another group from a different school is the control, adhering to the standard reading program. This design would be a non-equivalent quasi-experiment because the students cannot be randomly assigned to different schools by the researcher, likely due to parental objections, which means there could be important differences between them. For example, one school could have higher achieving or more motivated students. The other school might have more “troublemakers.” The teachers’ styles, and even the classroom environments, might be very different and cause different levels of achievement or motivation among the students.

Please note that in some cases, researchers omit random allocation because it is an oversight; for example, Brady's study on "Ulcers in executive monkeys." In this study, conducted by J. V. Brady in 1958, two monkeys were placed in restraining chairs and subjected to shocks every 20 seconds. One monkey, referred to as the "executive," had control over a lever that could postpone the shocks for a short period, while the other monkey received the shocks without any control over the lever. Both monkeys received the shocks, but only the "executive" monkey experienced the psychological stress of deciding when to press the lever.

The study abruptly stopped when many of the monkeys suddenly died. A post-mortem examination revealed raised gastrointestinal hormone levels and ulcers as the cause of death. Interestingly, the ulcers were not attributed to the physical restraint, as other monkeys had been kept in similar restraining chairs for up to six months without any fatalities.

The term "executive" in this study” refers to the monkeys' ability to learn and adapt quickly rather than in a human occupational sense. It's important to note that the monkeys were not randomly selected for the study; the "executive" was chosen because it showed faster learning of an avoidance response.

The lack of random allocation of the monkeys in this study raises questions about the validity of the results. The physiological differences between the "executive" and the yoked "non-executive" monkey could have influenced the outcomes, potentially affecting the interpretation of the findings regarding the relationship between electric shocks, stress, and the development of ulcers.

EXAMPLES:

Impact of Bilingual Education on Academic Achievement:

This study evaluated the effectiveness of bilingual education programs by comparing the academic achievement of students enrolled in bilingual education schools with those in traditional monolingual schools. Researchers selected schools with existing bilingual education programs and matched them with similar monolingual schools based on demographic characteristics. Academic achievement outcomes, such as standardized test scores and graduation rates, were compared between the two groups.

Reference: Thomas, W. P., Collier, V. P. (2002). A National Study of School Effectiveness for Language Minority Students' Long-Term Academic Achievement. Center for Research on Education, Diversity & Excellence, University of California, Santa Cruz.

Impact of Parenting Styles on Child Behavior:

• This study investigated the influence of different parenting styles on child behaviour by comparing children raised by authoritative parents with those raised by authoritarian parents. Researchers recruited participants from community settings and assessed parenting styles through self-report measures and behavioural observations. Child behaviour outcomes, such as aggression, compliance, and emotional regulation, were compared between the two groups.

• Reference: Baumrind, D. (1967). Childcare practices are implementing three patterns of preschool behaviour. Genetic Psychology Monographs, 75(1), 43–88.

Effect of Socioeconomic Status on Academic Achievement:

• This study examined the impact of socioeconomic status (SES) on academic achievement by comparing students from low-income families with those from high-income families. Researchers selected schools serving diverse socioeconomic populations and collected data on family income, parental education level, and student academic performance. Academic achievement measures, such as grades and standardized test scores, were compared between students from different SES backgrounds.

• Reference: Sirin, S. R. (2005). Socioeconomic Status and Academic Achievement: A Meta-Analytic Review of Research. Review of Educational Research, 75(3), 417–453

By the way, AQA only refers to between-subject quasi-experiments in the examination and specification, so just learn about this type if needs be.

ETHICS: Quasi-experiments may be chosen when it would be unethical to randomly assign participants to conditions, mainly when providing or withholding treatment could pose ethical concerns.

ADVANTAGES: Because the independent variable is manipulated before the dependent variable is measured, quasi-experimental research eliminates the directionality problem. External validity is usually higher than most true experiments involving real-world interventions rather than artificial laboratory settings. Plus, quasis allows for better control of confounding variables. Quasi-experiments may also be preferred when accurate experimental designs are impractical or too costly to implement. For researchers with limited funding or resources, conducting an accurate experimental study may be unfeasible due to financial constraints or logistical challenges. Additionally, recruiting and designing experimental interventions for sufficient subjects can be labour-intensive and time-consuming, making quasi-experimental designs a more practical option in some cases.

DISADVANTAGES:

Participants not randomly assigned: Because participants aren't randomly assigned, the groups being compared in a quasi-experiment may differ in ways other than the studied variable. These additional differences, known as confounding variables, can affect the outcomes and make it challenging to attribute any observed effects solely to the independent variable.

Experimental status: Quasi-experiments sit somewhere between correlational studies and true experiments in terms of their experimental status. Here's what that means:

Correlational studies: These studies observe the relationship between variables but do not involve experimental manipulation. They look at how variables naturally co-vary.

True experiments: Researchers manipulate the independent variable and randomly assign participants to conditions, allowing for stronger causal inferences.

Quasi-experiments: Quasi-experiments involve some degree of experimental manipulation, similar to true experiments, but lack random assignment. This makes them more controlled than correlational studies but less rigorous than true experiments in establishing causality. Therefore, they fall somewhere between the two regarding their experimental status.