Descriptive Research Strategies PDF

CHAPTER 13 DESCRIPTIVE RESEARCH STRATEGY The descriptive research strategy aims to describe the characteristics, behaviors, or phenomena of a population or situation without attempting to establish cause-and-effect relationships. It answers questions like “What exists?”, “What is happening?”, and “H...

CHAPTER 13 DESCRIPTIVE RESEARCH STRATEGY The descriptive research strategy aims to describe the characteristics, behaviors, or phenomena of a population or situation without attempting to establish cause-and-effect relationships. It answers questions like “What exists?”, “What is happening?”, and “How do people behave?”. This strategy is particularly useful in the early stages of research to provide a foundation for hypothesis generation. Key Features 1. Purpose: o To describe variables as they naturally occur. o Does not manipulate variables or establish causal relationships. 2. Use Cases: o Understanding trends. o Identifying patterns or behaviors. o Documenting phenomena for later experimental analysis. 3. Examples of Research Questions: o What are the common stressors among college students? o How often do people use social media daily? o What is the demographic composition of urban neighborhoods? Key Terms Term Definition Example Any characteristic or phenomenon that Variable Age, height, hours spent studying. can be measured. Population The entire group of interest. All college students in the U.S. A subset of the population used to collect 500 college students surveyed about Sample data. stress. A data collection method involving direct Watching children on a playground to Observation recording of behavior. study social behavior. A method of collecting data using Asking employees about job Survey questionnaires or interviews. satisfaction. An in-depth study of a single individual Examining a patient with a rare Case Study or small group. psychological disorder. Types of Descriptive Research 1. Observational Research  Definition: Systematic observation and recording of behaviors as they occur naturally. Subtypes: o Naturalistic Observation: Observing behavior in its natural environment. ▪ Example: Studying animal behavior in the wild. o Participant Observation: Researcher becomes part of the group being observed. ▪ Example: Joining a community to study its culture. o Contrived Observation: Observations occur in a controlled environment( to ensure behavior will occur) ▪ Example: Observing children in a lab setting. Advantages: o High ecological validity (especially naturalistic). o Provides rich, qualitative data. Disadvantages: o Time-consuming. o Observer bias may influence results. 2. Survey Research Definition: Collecting self-reported data from participants using questionnaires or interviews. Common Formats: o Closed-ended questions (e.g., multiple-choice). o Open-ended questions (e.g., “Describe your daily routine”). Advantages: o Can reach a large sample size. o Cost-effective and efficient. Disadvantages: o Response bias (e.g., social desirability). o Limited depth compared to other methods. 3. Case Study Definition: In-depth exploration of an individual, group, or situation. Purpose: Often used to study rare or unique phenomena. Examples: o Studying a child prodigy to understand early cognitive development. o Examining a survivor of a natural disaster for trauma recovery. Advantages: o Provides detailed, in-depth information. o Can generate hypotheses for future research. Disadvantages: o Limited generalizability due to focus on a single case. o Potential researcher bias. Comparison Chart: Types of Descriptive Research Type Definition Example Advantages Disadvantages Studying Observing and High ecological Time-consuming, classroom Observational recording behavior validity potential observer behavior in naturally or in a lab (naturalistic) bias students Collecting data via Polling voters Reaches large Response bias, Survey questionnaires or about political populations, cost- limited depth interviews preferences effective In-depth study of one Analyzing the Rich, detailed Limited Case Study individual or small brain injury of information generalizability group one patient Example Scenario Research Question: What are the common stressors among college students? Observational Approach: Observe behaviors in a library during exam week to identify signs of stress (e.g., pacing, fidgeting). Survey Approach: Distribute a questionnaire asking students to rank their top stressors (e.g., exams, finances). Case Study Approach: Conduct an in-depth interview with a single student experiencing extreme academic stress. Strengths and Weaknesses of Descriptive Research Strengths Weaknesses Provides rich data and insights into phenomena. Cannot establish causation. Useful for hypothesis generation. Prone to biases (e.g., observer, response). Flexible methods (observation, survey, case Generalizability may be limited in some study). cases. Active Recall Practice 1. What are the three main types of descriptive research? Provide an example of each. 2. How does a naturalistic observation differ from a structured observation? 3. What are the strengths and weaknesses of using surveys for descriptive research? 4. In what scenarios would a case study be the best descriptive research method? CHAPTER 14 SINGLE CASE EXPERIMENTAL RESEARCH DESIGN Single-case experimental research designs are methods used to study the effects of an intervention on an individual or a small group. These designs are commonly used in clinical, educational, and behavioral research where detailed examination of a single participant or case is needed. Unlike group designs, single-case designs focus on within-subject variations and typically involve repeated measures of the dependent variable. Key Features 1. Repeated Measures: o The dependent variable is measured multiple times before, during, and after the intervention. o Example: Tracking a student's test performance weekly during a behavior modification program. 2. Baseline Phase (A): o A period where the behavior is measured without any intervention. o Establishes a control for comparison. o Example: Observing the frequency of tantrums in a child before implementing a reward system. 3. Intervention Phase (B): o The period during which the treatment or intervention is applied. o Example: Introducing a token economy system for managing classroom behavior. 4. Focus on Individual Behavior: o Emphasis on understanding changes within a single participant or small group rather than across large samples. 5. Graphical Analysis: o Data is often analyzed visually using line graphs to identify trends and changes. Types of Single-Case Designs 1. AB Design: o Structure: Baseline phase (A) followed by an intervention phase (B). o Advantages: Simple and easy to implement. o Limitations: Cannot establish causal relationships due to lack of replication. Example: Measuring a patient’s anxiety before and after starting a mindfulness o program. 2. ABA (Reversal) Design: o Structure: Baseline (A) → Intervention (B) → Baseline (A).  o Purpose: Demonstrates causality by observing if behavior returns to baseline when intervention is removed. o Example: Studying the effects of positive reinforcement on a student’s participation, then withdrawing reinforcement to see if participation declines. 3. ABAB (Reversal) Design: o Structure: Baseline (A) → Treatment (B) → Baseline (A) → Treatmemt (B). o Purpose: Replicates the intervention to strengthen causal inference. o Example: Evaluating a fitness app's effect on exercise habits with alternating periods of usage and non-usage. 4. Multiple Baseline Design: o Structure: Baseline and interventions are staggered across behaviors, settings, or participants. o Purpose: Establishes causality without removing the intervention. o Example: Examining the effect of a reading program across multiple classrooms, introducing the program at different times for each class. Types of Multiple Baseline Multiple Baseline Across Behaviors Description: o The same intervention is applied to multiple behaviors exhibited by a single individual. o Baselines are established for each behavior, and the intervention is introduced one behavior at a time. Example: o A researcher studies a child with autism and targets three behaviors: eye contact, verbal greetings, and following instructions. The intervention is first applied to eye contact, then verbal greetings, and finally following instructions. Advantages: o Demonstrates that changes are specific to treated behaviors. Challenges: o Requires distinct, independent behaviors to avoid generalization across baselines. 2. Multiple Baseline Across Settings Description: o The same behavior is measured across different environments or contexts, and the intervention is introduced sequentially in each setting. Example: o A teacher aims to reduce disruptive behavior in a student across different settings (e.g., classroom, cafeteria, and playground). The intervention is introduced first in the classroom, then in the cafeteria, and finally on the playground. Advantages: o Highlights the intervention's effectiveness in various real-world contexts. Challenges:  o Behavior may generalize across settings before the intervention is formally applied. 3. Multiple Baseline Across Participants Description: o The same behavior is measured for multiple participants, and the intervention is introduced at different times for each participant. Example: o A therapist introduces a relaxation technique to reduce anxiety in three clients. The intervention is applied first to Client A, then to Client B, and finally to Client C. Advantages: o Demonstrates effectiveness across a diverse group of participants. Challenges: o Individual differences may influence results, requiring careful interpretation. 4. Mixed Multiple Baseline Designs Description: o Combines elements of multiple baseline across behaviors, settings, or participants. o Allows for flexibility in designing interventions targeting multiple levels. Example: o A therapist measures different behaviors (e.g., self-talk, task persistence) across multiple participants and applies the intervention sequentially across both behaviors and individuals. Advantages: o Allows testing multiple variables simultaneously. Challenges: o Complexity in interpretation and design. Key Features of Multiple Baseline Designs Staggered Intervention: Treatment is introduced at different times to prevent simultaneous changes across baselines, strengthening causal inferences. Non-Reversal Design: Unlike reversal designs (e.g., ABA designs), MBDs do not withdraw the intervention, making them suitable for irreversible behavior changes. Internal Validity: Changes occurring only after intervention and aligned with staggered implementation provide evidence of treatment effectiveness.  5. Changing Criterion Design: o Structure: Gradually changes the performance criteria for reinforcement. o Purpose: Evaluates if the behavior systematically follows the changing criteria. o Example: Gradually increasing the number of completed homework problems required for a reward. Advantages and Limitations Advantages Tailored to the individual; suitable for unique cases. Allows for detailed analysis of behavior over time. Useful when large sample sizes are unavailable. Facilitates immediate application of results in practice. Limitations Limited generalizability (external validity) due to the focus on a single or few cases. Potential for observer bias in data collection. Some designs (e.g., AB) cannot establish causation. Key Terms Baseline (A): A phase where no treatment is applied; used to establish a reference for comparison. Intervention (B): The phase where the treatment or experimental condition is applied. Replication: Repeating the intervention phase to strengthen causal conclusions. Visual Analysis: Interpretation of trends, levels, and variability in graphical data. Examples for Practice Design Type Description Example Baseline followed by Observing tantrum frequency before and after AB Design intervention. implementing a reward system. ABA Baseline → Intervention → Measuring exercise levels with and without (Reversal) Baseline. fitness app usage. ABAB Baseline → Intervention → Studying classroom participation with (Reversal) Baseline → Intervention. alternating periods of reward and no reward.  Design Type Description Example Multiple Baselines and interventions Testing a new reading program introduced at Baseline staggered across subjects. different times in different classrooms. Changing Gradual changes in criteria for Increasing daily step goals incrementally for a Criterion reinforcement. fitness intervention. Comparison Chart of Single-Case Designs Multiple Changing Aspect AB Design ABA Design ABAB Design Baseline Criterion A→B→A→ A→B A → B (gradual Structure A → B A→B→A B (staggered) criteria changes) Moderate Strong (no Moderate Weak (no Strong (repeated Causation (reversal shows need for (systematic replication) replication) causality) reversal) behavior change) Strongest Ethical (no Tailored to Easy to Shows effect Strength evidence of removal of progressive implement removal causality treatment) behaviors Limited to Unethical if No control for Complex to Requires behaviors that Limitation treatment is confounds manage phases careful timing can follow beneficial gradual steps Classroom Reading Anxiety Exercise behavior program Gradual increase Example before/after with/without with/without across in daily steps treatment fitness app rewards classrooms Active Recall Questions 1. What is the purpose of a baseline phase in single-case designs? 2. Compare the strengths and limitations of AB designs and ABAB designs. 3. Why might a researcher choose a multiple baseline design over a reversal design? 4. Provide an example of a changing criterion design and explain its purpose. CHAPTER 15 1. Descriptive vs. Inferential Statistics Descriptive Statistics: o Summarizes and organizes data (e.g., mean, median, mode, range, standard deviation). o Example: Reporting the average exam score of a class. Inferential Statistics: o Makes predictions or generalizations about a population based on sample data. o Involves hypothesis testing, confidence intervals, and estimation. o Example: Using a sample of 100 students to estimate the average exam score of all college students. Active Recall Questions: How do descriptive and inferential statistics differ in purpose? Provide examples of each in a behavioral science context. 2. Key Statistical Terms and Concepts Population vs. Sample: o Population: The entire group of interest. o Sample: A subset of the population studied to draw conclusions. Variables: o Independent Variable (IV): Manipulated or grouped by the researcher. o Dependent Variable (DV): Measured outcome affected by the IV. Scales of Measurement: o Nominal: Categories (e.g., gender). o Ordinal: Ranked order (e.g., class ranking). o Interval: Numerical values with equal intervals, no true zero (e.g., temperature). o Ratio: Numerical values with a true zero (e.g., weight). Active Recall Questions: What are the four scales of measurement, and how do they differ? Identify examples of independent and dependent variables in behavioral science research. 3. Steps in Hypothesis Testing 1. State the Hypotheses: o Null Hypothesis (H0H0): No effect or relationship. o Alternative Hypothesis (H1H1): There is an effect or relationship. 2. Set the Significance Level (αα): o Typically α=0.05α=0.05. 3. Collect Data and Conduct Analysis: o Use appropriate statistical tests (e.g., t-tests, ANOVA). 4. Compare P-Value to αα:  o If pα, fail to reject H0H0. 5. Draw Conclusions: o Summarize findings and relate them to the research question. Active Recall Questions: What does it mean to reject the null hypothesis? Explain how the p-value is used in hypothesis testing. 4. Common Statistical Tests T-Tests Compares the means of two groups. Types: o Independent Samples T-Test: Compares two separate groups. o Paired Samples T-Test: Compares measurements within the same group. Analysis of Variance (ANOVA) Tests differences among three or more group means. Produces an F-Ratio to determine if at least one group differs significantly. Correlation Measures the strength and direction of a relationship between two variables. o Pearson’s rr: Linear relationships (range: -1 to +1). Chi-Square Test Tests the association between categorical variables. Regression Analysis Predicts a dependent variable based on one or more independent variables. Active Recall Questions: When would you use a t-test versus ANOVA? What does Pearson’s rr indicate, and how is it interpreted? 5. Effect Size and Statistical Power Effect Size: o Measures the magnitude of a relationship or difference. o Examples: Cohen’s dd (mean difference), r2r2 (variance explained). Statistical Power: o Probability of correctly rejecting H0H0 when it is false. o Increases with a larger sample size, stronger effect, or reduced variability. Active Recall Questions: What is the purpose of calculating effect size? How does increasing the sample size affect statistical power? 6. Reporting and Interpreting Results APA Style Guidelines: o Present test statistics, degrees of freedom, p-values, and effect sizes.  o Example: “A t-test showed a significant difference in test scores between groups, t(28)=2.85,p=.01,d=0.75t(28)=2.85,p=.01,d=0.75.” Use Tables and Graphs to enhance data interpretation. Active Recall Questions: Why is it important to include effect size when reporting statistical results? What elements should be included in an APA-style results section?