Research Design Overview

Research Design Overview

Correlational Design

• Definition: Involves examining relations between variables that naturally exist; commonly used in mental health research.

• Limitations: Cannot assign individuals to healthy or non-healthy groups or manipulate health statuses.

• Examples of Variables:

  • Mental well-being and academic performance.

  • Living with depression and social interactions.

Correlation Coefficient (small r)

• Purpose: Denotes the direction and strength of the relationship between two variables.

• Interpretation:

  • Positive correlation: as one variable increases, the other also increases.

  • Negative correlation: as one variable increases, the other decreases.

  • No correlation: no relationship exists between the variables.

• Visual Representation:

  • Positive Correlation: Line slopes upwards.

  • Negative Correlation: Line slopes downwards.

  • No Correlation: Line is flat.

• Consideration of Significance:

  • Must assess the correlation coefficient alongside the p-value; significance is established when p < 0.05.

Correlation Characteristics

• Positive Correlation: r > 0 (indicates that both variables increase together).

• Negative Correlation: r < 0 (indicates that one variable increases while the other decreases).

• No Correlation: 0 < r < 1 or -1 < r < 0

• Importance of Causation: Correlation does not imply causation.

  • Example: Children with academic success might have more friends and vice versa; direction of influence is unclear.

  • Risk of a third variable influencing both correlations—e.g., quality of parenting might improve academic skills and social connections.

Experimental Design

• Definition: A method of research that allows for causal conclusions due to controlled manipulation of variables.

• Types of Experimental Research:

  • Randomized Experiments:

  • Participants are assigned to different groups randomly.

  • Ensures that groups represent the larger sample without bias in selection.

  • Quasi-Experimental Research:

  • Participants are not randomly assigned; often involves pre-defined groups (e.g., boys vs. girls).

  • Common in mental health research, especially with subject-specific groups (e.g., children with specific disorders).

Components of Experimental Research

• Independent Variable (IV): The manipulated variable in the experiment, often a group assignment.

• Dependent Variable (DV): The outcome variable of interest; what the researcher measures.

• Purpose: To test differences between groups and determine if the effects observed are due to manipulation or chance.

Example of Experimental Design Study

• Study Focus: Sharing behavior between children with a friend versus a non-friend.

• Setup:

  • Participants assigned to either "friends condition" or "no friends condition."

  • Create a standardized setting for both groups to control external variables.

• Manipulation:

  • Independent variable: Type of play partner (friend vs. non-friend).

• Dependent Measurement:

  • Time taken for the child to share a toy with the partner.

• Expected Outcome:

  • Hypothesis: Children in the "friends condition" will share sooner than those in the "no friends condition."

• Statistical Analysis:

  • Comparison of results between conditions to identify significant differences.

Case Study Research

• Definition: An in-depth examination of a single participant or a very small group where traditional methods are not viable.

• Purpose: Useful when researching rare conditions or unique cases (e.g., children with schizophrenia or uncommon disorders such as eating disorders in blind individuals).

• Applications:

  • Can involve experimental manipulation but typically lacks a control group.

  • Suitable for unique interventions (e.g., new treatments for mobility issues in disabled children).

• Example of Case Study:

  • Studying the effectiveness of a new robotic walking aid for children with cerebral palsy to determine practical applications for broader use.