L1 | QUANTITATIVE RESEARCH

avatar
Created by
sandra

Cards (33)

  • QUANTITATIVE RESEARCH
    • Explaining phenomena by collecting numerical data that are analyzed using mathematically based methods
  • MATHEMATICAL FORMULAS
    1. Descriptive
    2. Inferential Statistics
  • CHARACTERISTICS OF QUANTI RESEARCH
    1. Reliable and objective
    2. Uses statistics to generalize a finding
    3. Reduces complex problem to a limited number of variables
    4. Looks at the connections bw variables and establishes cause and effect relationships in highly controlled circumstances
    5. Test theories or hypothesis
    6. Assumes that the sample is representative of the population
    7. Subjectivity of its methodology is secondary concern
    8. Deals with the details of the subject
  • ADVANTAGES
    1. Allows to measure data to arrive at an objective answer
    2. Result is reliable; Uses big sample of population
    3. Standards are used in choosing instruments; replicable
    4. Personal biases can be avoided
    5. Processes are simplified
    6. Results can be reduced through statistical treatments
  • DISADVANTAGES
    1. Context of the study is ignored
    2. Requires to spend more resources
    3. Results are limited; based on analysis of numbers
    4. Less elaborate accounts of human perceptions
    5. Preset answers may not reflect true answers of participants
  • NON EXPERIMENTAL DESIGN
    • Explore events, people, situations as they naturally occur
    • Test relationships and differences among variables
    • Independent v is not manipulated
    • Subjects are not randomized
    • No control group
  • DESCRIPTIVE RESEARCH DESIGN
    1. Survey
    2. Correlational
    3. Comparative
    4. Evaluation
    5. Methodological
  • SURVEY
    • Provide a numeric description of trends of a population
    • Data are collected with questionnaires or personal interviews
    • May be descriptive, exploratory, or comparative surveys
    • Uses data to justify current conditions and practices
  • CORRELATIONAL
    • Explores relationships bw variables
    • Variables is not controlled
    • Extent to which different variables are related to one another
    • 3 TYPES:
    1. BIVARIATE CORRELATIONAL STUDIES
    2. PREDICTION STUDIES
    3. MULTIPLE REGRESSION PREDICTION STUDIES
  • BIVARIATE CORRELATIONAL STUDIES
    • 2 variables are correlated
    • Obtain scores then use them to calculate a correlation coefficient
  • PREDICTION STUDIES
    • Use correlation coefficient to show how 1 predictor var predicts criterion var
  • COMPARATIVE
    • Comparing and contrasting 2 or more samples of the study subjects on one or more variable, often at a single point of time
  • EVALUATION
    • Elicit useful feedback from respondents
    • MOST COMMON USED:
    1. FORMATIVE EVALUATION
    2. SUMMATIVE EVALUATION
  • FORMATIVE EVALUATION
    • Determine the quality of implementation of a project; efficacy and effectiveness
  • SUMMATIVE EVALUATION
    • Whether the program achieved its goals
    • How the program's impact compares to diff programs
    • Understand process of change
  • METHODOLOGICAL
    • Forms critical part of achieving the goal of developing a scaled match approach, where data from diff disciplines can be integrated
  • EXPERIMENTAL RESEARCH DESIGN
    • Uses scientific method to test cause and effect relationships under conditions controlled
    • Treatment is given to a controlled group
  • EXPERIMENTAL RESEARCH DESIGNS
    1. Pre experimental research design
    2. Quasi experimental design
    3. True experimental design
  • PRE EXPERIMENTAL DESIGN
    • Carried out before the main experiment
    • Either single or multiple groups are observed subsequent to treatment presumed to cause change
    • Least internal validity
  • TYPES OF PRE EXPERIMENTAL DESIGN
    1. One shot case study design
    2. One group pretest posttest design
    3. Static group comparison
  • ONE SHOT CASE STUDY DESIGN
    • A single group is studied after some treatment that is presumed to have caused change.
    • Is compared to general expectations of what the case would have looked like if treatment didn't occurred
    • No control or comparison group is employed.
  • ONE GROUP PRETEST POSTTEST DESIGN
    • Single case is observed at 2 time points:
    • Before treatment
    • After treatment
    • Changes are the result of the intervention
    • No control or comparison group is employed
  • STATIC GROUP COMPARISON
    • Group that experienced treatment is compared with one that has not
    • Observe differences bw the groups are assumed to be a result
  • QUASI EXPERIMENTAL DESIGN
    • Researcher can collect more data
    • Involves selecting groups, upon which a variable is tested, without any random pre selection processes
    • Used for test of causality
    • Independent v is not manipulated
  • 2 TYPES OF QUASI EXPERIMENTAL DESIGN
    1. NON EQUIVALENT CONTROL GROUP DESIGN
    2. INTERRUPTED TIME SERIES DESIGN
  • NON EQUIVALENT CONTROL GROUP DESIGN
    • Chance failure of random assignment to equalize the conditions by converting a true experiment into this, for purposes of analysis
  • INTERRUPTED TIME SERIES DESIGN
    • Employs measures before and after experimental intervention
    • Time threats such as history appear as regular changes in the measures prior to the intervention
  • EX POST FACTO
    • Latin: after the fact
    • Causal comparative
    • Investigation starts after the fact has occurred without interference
    • How iv affects dv
    • Do not use random assignment
  • TRUE EXPERIMENTAL DESIGN
    • Relies on statistical analysis to approve or disprove a hypothesis
    • Most accurate experimental design
    • Require random assignment
    • Basic components
    • Pretest
    • Posttest
    • Control group
    • Experimental group
  • TYPES OF TRUE EXPERIMENTAL RS DESIGN
    1. Pretest posttest control group design
    2. Posttest only control group design
    3. Solomon four group design
  • PRETEST POSTTEST CONTROL GROUP DESIGN
    • Subjects are randomly assigned to the 2 groups, both are presented, but only the experimental group is treated.
    • After close observation, both groups are post-tested to measure the degree of change in each group.
  • POSTTEST ONLY CONTROL GROUP DESIGN
    • Subjects are randomly assigned to the 2 groups, only exp grp is treated
    • Both groups are post tested
    • Conclusion is drawn from the difference bw these groups
  • SOLOMON FOUR GROUP DESIGN
    • Combination of pretest only and the pretest-posttest control groups
    • Randomly selected are placed in 4 groups
    • First 2: posttest only method
    • Last 2: pretest posttest method