Research Designs

Quantitative Research

Survey Research

Survey Research involves collecting data to test hypothesis or to answer qewstions about people’s opinions on some probblem or issue.

Cross Sectional Surveys

Cross-sectional Surveys collect data at one point in time.

Longitudinal Surveys

Longitudional Surveys collect data at more than one to measure growth or change. Classification depends on sampling and administration of the research.

  • Trend Survey
  • Cohort Survey
  • Panel Survey
  • Follow-up Survey

Correlational Research

Correlational research involves collecting data to determine whether, and to what degree, a relationship exists between two or more quantifiable variables.

It does not cause a casual relationship.

Its purpose could be to determine relations among variables or to use these relations to make predictions.

The larger the sample, the more closely it approximates the population.

Common variance (shared variance) indicated the extent to which variables vary in a systematic way.

Statistical significance refers to the probabilty that the results would have occured simply due to chance.

Pearson R & Spearman rho (Pearson r, a measure of correlation that is appropriate when both variables to be correlated are expressed as continous “i.e. ratio or interval” data. If the data for at least one variable are expressed as rank or ordinal data, the appropriate correlation coefficiant to use is the rank difference correlation, usually referred to as the Spearman rho.)

Curvilinear relation

Attenuation is the reduction in correlation coefficients that tend to occur if the measures have low reliability.

  • At least 30 Participants
  • Correlation coefficent:
  • +/-0.0 , +/-0.35 = weak
  • +/-0.35 , +/-0.65 = moderate
  • +/-0.65 , +/-1.00 = strong
  • p=0.05 => 95% confidence level
  • Regression 
  • Correlation

Casual Comparative Research

Casual Comparative Research attempts to determine the cause or reason for existing differences in the behavior or status of groups or individuals.

Retrospective casual comparative

Starting with effects and investigating causes is referred as restrospective casual comparative research. This tyoe is much more common in educational research.

Prospective casual comparative

Starting with causes and inverstigating effects is called as prospective casual comparative research.

  • Not randomly assigned
  • Grouping variable instead of the term independent variable.
  • Grouping variables cannot be manipulated or should not be manipulated or simply not manipulated although could be.
  • It fails to give a true experimantal data. (causality?)ö
  • Organismic variable (age,sex etc)
  • Pair-wise matching of participants
  • Comparing homogeneous groups & subgroups: Factoral Analysis of Covariance
  • Analysis of Covariance 
  • T-test & ANOVA

Experimental Research

In experimental research, the researcher manipulates at least one independent variable, controls other relevant variables, and observes the effect on one or more dependent variable.

Pre-experimental Research Design

  • (One-shot Case Study Research Design) One Group Post Test Only Design
  • One-group Pretest-posttest Research Design:
  • Post test only design with Nonequivalent groups (Static-group Comparison??):

Quasi-experimental Research Design

  • Non-equivalent control group design
  • The counterbalanced design
  • The time series design

True Experimental Research Design

  • The posttest-only Control Group Design
  • The pretest-posttest Control Group Design
  • Solomon four-group Design

Factorial Designs

 Threats

  • Treatment Defusion : Treatment diffusion is where the control group is affected by the treatment. This could happen because individuals in the control groups and treatment groups talk to each other about the treatment. As such, this is usually an issue in research involving training or informational programs (Borg, 1984).
  • Experimenter Bias : Observer bias and other “experimenter effects” occur when researchers‘ expectations influence study outcome. (Holman, Head, Lanfear & Jennions, 2015)
  • Hawthorne Effect: The Hawthorne effect occurs when people change their behaviors because they know they are being watched during experiment.
  • John Henry: The John Henry Effect refers to the tendency for people based in a control group to perceive themselves at a disadvantage to the experimental group and work harder in order to overcome the perceived deficiency.
  • Placebo Effect: a clinically significant response to a therapeutically inert substance or nonspecific treatment (placebo), deriving from the recipient’s expectations or beliefs regarding the intervention. It is now recognized that placebo effects accompany the administration of any drug (active or inert) and contribute to the therapeutic effectiveness of a specific treatment.
  • Novelty Effect: Because of given a novel task, paying more attention to the task.
  • Effect Size : any of various measures of the magnitude or meaningfulness of a relationship between two variables. For example, Cohen’s d shows the number of standard deviation units between two means. Often, effect sizes are interpreted as indicating the practical significance of a research finding. Additionally, in meta-analyses, they allow for the computation of summary statistics that apply to all the studies considered as a whole. See also statistical significance.

Kaynakça

© MAKALESKOP

Leave a comment