NR Midterm 4 PDF

# Types of Experimental Designs ## Randomized Controlled Trials (RCTs) ### True Experimental Design - Most rigorous and strong experimental designs because of equating the groups through random assignment. - Because you randomly assign individuals to the groups, most of the threats to internal va...

# Types of Experimental Designs ## Randomized Controlled Trials (RCTs) ### True Experimental Design - Most rigorous and strong experimental designs because of equating the groups through random assignment. - Because you randomly assign individuals to the groups, most of the threats to internal validity do not arise. ### Characteristics of True Experimental Designs 1. **Intervention** - Experimenter does something to some participants by manipulating the independent variable. 2. **Control** - Experimenter introduces controls into the study. - Devising an approximation to a counterfactual. - **Experimental group:** (+) experimental treatment. - **Control group:** (-) experimental treatment. 3. **Randomization** - Experimenter assigns participants to a control group or experimental condition on a random basis. - Every participant has an equal chance of being included in any group. - Aka random assignment. ### Example of True Experimental The use and non-use of external flushing on post-partum mothers to determine the extent of post-partum infections. - **EG:** Mothers who will not use external flushing. - **CG:** Mothers who will use external flushing. *PICO/PIO scheme* ### Types of True Experimental 1. Pre-test Post-test Control Group Design 2. Post-test only Control Group Design 3. Solomon Four Group Design 4. Crossover Design ### True Experimental: Pre-test Post-Test Control Group Design - **Aim:** To study the effect of an influence on a carefully controlled sample. - This design has been called "the old workhorse of traditional experimentation". - If effectively carried out, this design controls threats of internal validity. - Data are analyzed by analysis of co-variance on post-test scores with the pre-test the covariate. ### True Experimental: Pre-test Post-Test Control Group Design (cont.) - **Elements:** 1. Subjects are randomly assigned to both groups: (R) 2. Pre-observation is given to both groups: (01) 3. Experimental treatment is given to experimental group: (X) 4. Control group will receive no treatment 5. Post-observation is given to both groups: (02) ### Example of Pre-test Post-Test Control Group Design Effectiveness of the use of guava leaves for external flushing to post-partum patients to prevent infection. | Group | A | B | C | D | |---|---|---|---|---| | EG | R | 01 | X | 02 | | CG | R | 01 | 02 | ### True Experimental: Post-test only Control Group Design - **Aim:** To evaluate a situation that cannot be pre-tested. - Used where pre-test sensitization may be a problem. - An adaptation of the last two groups in the Solomon four-group design. - Randomness is critical. - Probably, the simplest and best test for significance in this design is the t-test. ### True Experimental: Post-test only Control Group Design (cont.) - **Elements:** 1. Subjects are randomly assigned to both groups: (R) 2. Experimental treatment is given to experimental group: (X) 3. Control group receive no treatment 4. Post-observation is given to both groups: (01) ### Example of Post-test only Control Group Design Health teachings on patients with urinary incontinence. | Group | A | B | C | |---|---|---|---| | EG | R | X | 01 | | CG | R | 01 | ### True Experimental: Solomon Four Group Design - **Aim:** To minimize the effect of pre-testing. - This is an extension of the pre-test post-test control group design. - Probably the most powerful experimental approach. - Data are analyzed by analysis of variance on post-test scores. ### Example of Solomon Four Group Design Effects of genetic counselling and pre-natal supervision on the incidence of maternal complications in high-risk women. | Group | A | B | C | D | |---|---|---|---|---| | EG-1 | R | 01 | X | 02 | | CG-1 | R | 01 | 02 | | EG-2 | R | X | 01 | | CG-2 | R | 01 | ### True Experimental: Crossover Design - Involves exposing people to more than one treatment. - Order of treatment administration is called a sequence. - Time of a treatment administration is called a period. ### True Experimental: Crossover Design (cont.) - **Elements:** 1. Subjects are randomly assigned to different orderings of treatment to be either in the EG or CG first: (R) 2. Uniform within sequences and within periods: AB and BA (2-period, 2-treatment): (2X2) or ABB and BAA (3-period, 2-treatment): (3X2) etc. 3. Washout period: (W) ### Example of Crossover Design Compare the effects of music on patients with dementia. **Design 1** | | Period 1 | Period 2 | |---|---|---| | R | Sequence 1: A | Sequence 2: B | | R | Sequence 2: B | Sequence 1: A | **Design 2** | | Period 1 | Period 2 | Period 3 | |---|---|---|---| | R | Sequence 1: A | Sequence 2: B | Sequence 1: B| | R | Sequence 2: B | Sequence 1: A | Sequence 2: A| # Pre-Experimental Design - Loose in structure and could be biased. - **Characteristics:** 1. Intervention 2. No control: Experimental group only (single group) 3. No randomization ### Types of Pre-Experimental 1. One-Shot Case Study 2. One-Group Pre-test Post-test Design ### Pre-Experimental: One-Shot Case Study - **Aim:** To attempt to explain a consequent by an antecedent. - An approach that prematurely links antecedents and consequences. - The least reliable of all experimental approaches. ### Pre-Experimental: One-Shot Case Study (cont.) - No attempt is made to randomly assign subjects as comparison. - Highly useful in practice settings since it provides the least measure to a new treatment of the group in question. - **Elements:** 1. Experimental group is exposed to an experimental treatment: (X) 2. Observation done after the experimental treatment: (0) ### Example of One-shot Case Study A group of patients with COPD receiving Lagundi was observed and monitored throughout the treatment process. | Group | A | B | |---|---|---| | EG | X | 0 | ### Pre-Experimental: One-Group Pre-test Post-test Design - Comparison of group before and after experimental treatment. - **Elements:** 1. Observation done before experimental treatment: (01) 2. Experimental treatment is given: (X) 3. Observation done after experimental treatment: (02) ### Example of One-Group Pre-test Post-test Design Diet counselling and exercise regimen on patients with Diabetes Mellitus. | Group | A | B | C | |---|---|---|---| | EG | 01 | X | 02 | # Quasi-Experimental Design - In education, many experimental situations occur in which researchers need to use intact groups. - Might happen because of the availability of the participants or because the setting prohibits forming artificial groups. - Experimenter cannot artificially create groups for the experiment. ### Quasi-Experimental Design (cont.) - **Comparison group** is often used in lieu of control group - Refers to the group against which outcomes in the treatment group are evaluated. - Also known as **Trials without Randomization** (in medical literature). ### Characteristics of Quasi-Experimental Design 1. Intervention 2. Control: - **Experimental group:** (+) experimental treatment - **Comparison group:** (-) experimental treatment - *Except for Single-Group Interrupted and Equivalent Time Series Design.* 3. No randomization (lacks random assignment) ### Types of Quasi-Experimental 1. Non-Equivalent Control Group Design 2. Time Series Design: - Single-Group Interrupted - Control-Group Interrupted - Equivalent ### Quasi-Experimental: Non-Equivalent Control Group Design - **Aim:** To investigate a situation in which random selection and assignment are not possible. - One of the strongest and most widely used quasi-experimental designs. - Differs from experimental designs because test and control groups are not equivalent. ### Quasi-Experimental: Non-Equivalent Control Group Design (cont.) - Comparing pretest results will indicate degree of equivalency between experimental and control groups. - **Elements:** - Similar to Pre-test Post-test Control Group Design - Handpicked: (H) ### Example of Non-Equivalent Control Group Design Effects of primary nursing on staff nurses satisfaction. | Group | A | B | C | D | |---|---|---|---|---| | EG | H | 01 | X | 02 | | CG | H | 01 | 02 | ### Quasi-Experimental: Time Series Design - **Aim:** To determine the influence of a variable introduced only after a series of initial observations and only where one group is available. - If substantial change follows introduction of the variable, then the variable can be suspect as to the cause of the change. - To increase external validity, repeat the experiment in different places under different conditions. ### Quasi-Experimental: Time Series Design (cont.) - Experimental treatment is administered between series of observation - Also known as “Epidemiological Research Design". - **Types:** - Single-Group Interrupted - Control-Group Interrupted - Equivalent ### Example of Single-Group Interrupted Time Series Design Hospital implemented rapid response teams (RRTs) in its acute care units and wanted to learn the effects on patient outcomes (mortality). | Group | A | B | C | D | E | F | G | H | |---|---|---|---|---|---|---|---|---| | EG | H | 01 | 02 | 03 | X | 04 | 05 | 06 | ### Example of Control-Group Interrupted Time Series Design Community health nurses assess and evaluate the health programs implemented to determine incidence of Dengue infections between Brgy. A and Brgy. B. | Group | A | B | C | D | E | F | G | H | |---|---|---|---|---|---|---|---|---| | EG | H | 01 | 02 | 03 | X | 04 | 05 | 06 | | CG | H | 01 | 02 | 03 | 04 | 05 | 06 | 07 | ### Example of Equivalent Time Series Design Hospital implemented rapid response teams (RRTs) in its acute care units and wanted to learn the effects on patient outcomes (mortality). | Group | A | B | C | D | E | F | G | H | |---|---|---|---|---|---|---|---|---| | EG | H | 01 | X | 02 | X | 03 | X | 04 | # Non-Experimental Design - No manipulation (intervention) of variables. - Also known as **Observational Design**. - Describes the nature of phenomenon under investigation after a survey of current trends, practices, and conditions that relate to that phenomenon. ### Tools used in Observational Design 1. Test papers 2. Survey questionnaires 3. Interview 4. Observation schedules 5. Check lists 6. Score cards 7. Rating Scale # Types of Non-Experimental Designs ## Observational Designs ### Comparative Design - Examine two or more intact groups to find out the difference in performance between and among the studies in certain dependent variables of interest. - No manipulation of independent variables because characteristics of the subjects are inherent such as personality type, educational level, and medical condition. ### Categories of Comparative Design 1. **Retrospective Design / Ex Post Facto Design** - An effect (outcome) observed in the present is linked to a potential cause occurring in the past. - Past (Independent Variable) and Present (Dependent Variable). - e.g., "A study between DMSFI and SPC student nurses class 2022 and their performance in Nursing Licensure Exam in 2022." 2. **Prospective Design / Cohort Design** - Start with a presumed cause and then go forward to the presumed effect. - Present (Independent Variable) and Future (Dependent Variable). - e.g., "Risk factors associated with pressure injury in patients with traumatic brain injury." 3. **Case-Control Design** - Cases with a certain condition are compared to controls without. - Researchers try to identify controls who are similar as possible to cases with regard to confounding variables (age or gender). - e.g., "Exploratory study of gene expression in patients with Irritable Bowel Syndrome (IBS)." ### Correlational Design - Examine the extent of relationship between variables by determining how changes in one variable relate to changes in another variable. - Does X and Y vary together. - **Two Categories:** 1. Positive (Direct): as X increases, the Y increases 2. Negative (Inverse): as X increases, the Y decreases ### Example of Correlational Design "Relationship between age and assertiveness level among nurses." 1. *Positive Correlation (Direct)* - *Interpretation*: increased age and increased assertiveness level 2. *Negative Correlation (Inverse)* - *Interpretation*: increased age and decreased assertiveness level # Methodological Design - Concerned with the development, testing and evaluation of methods, procedures, guidelines, and instruments after which an evaluative judgement is done. - **Aim:** To revise, modify existing programs or develop more effective programs, methods, and procedures in nursing for more efficient and effective delivery of healthcare. - Also known as **Evaluative** or **Developmental Design**. ### Examples of Methodological Design - "Training programs for new graduate nurses and their clinical proficiency." - "Psychometric testing of a new scale for faculty performance." # Survey Design - Obtains quantitative information about the prevalence, distribution, and interrelations of variables within a population. - e.g., "political opinion polls" - Obtain information about people's actions, knowledge, intentions, and opinions by self-report. - **Types:** 1. Cross-sectional Survey Design 2. Longitudinal Survey Design ### Types of Survey Design 1. **Cross-sectional Survey Design** - Subjects are observed at only one point in time. - The researcher does not have to worry about patients dropping-out during the course of the study. - e.g., "Asking nursing students their choices of field of practice after passing the licensure exam." 2. **Longitudinal Survey Design (Follow-up Study)** - Subjects are studied over long periods or extended period of time. - This allows the researcher to measure change in variables over time. - **Types:** - Trend Study - Cohort Study - Panel Study ### Longitudinal Survey Design: Trend Study - Involves identifying a population and examining changes within that population over time. - e.g., 1, "Studies on maternal compliance to breastfeeding and newborn screening as healthcare policy." - e.g., 2, "Gallup Poll, which is used during elections to monitor trends in the population of voters from the primary to the final election." ### Longitudinal Survey Design: Cohort Study - A researcher identifies a subpopulation based on some specific characteristic and then studies that subpopulation over time. - Must have the common characteristic (such as same age on the same year). - e.g., "A cohort group of 18-year-olds is studied in the year 2001. Five years later (in 2006), a group of 23-year-olds is studied. Five years after that (in 2011), a group of 28-year-olds is studied." ### Longitudinal Survey Design: Panel Study - The researcher examines the same people over time. - Reveal changes (characteristics or behavior) at the individual level. - Most rigorous of the three longitudinal designs. - e.g., "Examine how adolescents with learning disabilities made the transition from vocational-technical schools to work. Two groups of high school seniors: one with learning disabilities and one without learning disabilities" ### Longitudinal Survey Design: Panel Study (cont.) - **Advantage:** - The individuals studied will be the same each time, allowing the researcher to determine actual changes in specific individuals. - **Disadvantage:** - Individuals may be difficult to locate, especially over long periods of time. # Qualitative Design - **Qualitative Design** - Case Study - Historical - Ethnography - Phenomenology - Descriptive - Narrative - Grounded Theory - Critical Theory - Feminist Research