1/29
Looks like no tags are added yet.
what are threats to validity (4)?
-threats to construct validity
-threats to statistical conclusion validity
-threats to internal validity
-threats to external validity
threats to construct validity
construct validity (aka conceptual variable)- although it is claimed the measured variables or the experimental manipulations relate to the conceptual variables of interest, they actually may not
threats to conclusion validity
conclusions regarding the research may be incorrect because a type 1 or type 2 error was made
threats to internal validity
although it is claimed the independent variable caused the dependent variable, the dependent variable may have actually been caused by a confounding variable
threats to external validity
although it is claimed the results are more general, the observed effects may actually only be found under limited conditions or for specific groups of people
what is internal validity impacted by (2) ?
-confounding variables (type of extraneous variable)
-extraneous variables
what is internal validity increased by (3) ?
-experimental controls
-using valid and calibrated instruments
-calibrated examiners
controlling extraneous variables
-select from limited, and therefore relatively homogenous, population (eg. college students, purchased white mice)
-use before-after research designs
-standardization of conditions
define before-after research designs
dependent variable assessed before and after the experimental manipulation
multiple-group before-after design

common threats to internal validity (3)
-placebo effects
-demand characteristics
-experimenter bias: naive experiments, blind, and double-blind experiments
define external validity
extent to which the study results can be generalized accurately to other situations and people
-how well does your sample represent the total population?
true/false: high internal validity = high external validity
false! high internal validity does not always mean you have external validity
define replication
-the process of repeating previous research
-tests external validity
-tests generalization and limitations of research findings
define probability sampling
have to have a sampling frame and everyone in the population has an equal chance of being selected to participate in the research
goal of probability sampling
make sample representative of population
what does it mean if the sample is representative of population?
we can generalize findings to other people within the population (Yay! good external validity!)
when is non-probability sampling used?
-used when sampling frame is not present
-sample is NOT representative of population
-therefore, cannot generalize to population (NO external population)
what are ethics in research?
norms of conduct that distinguish between acceptable and unacceptable behavior in research
belmont report
-respect for persons
-beneficence
-justice
what is the IRB?
Institutional Review Board
-monitors researchers to ensure a high ethical standard
basic goal of the IRB
determine the cost-benefit ratio of proposed research
what are the standards of ethical conduct of research?
-respect and dignity
-informed consent
-voluntary participation
-confidentiality/anonymity
-protection of human research participants
-social justice
-research misconduct
respect and dignity
human participants should be treated with respect and dignity
informed consent
required, including full disclosure of the research plan and a description of the risks and benefits of participation
voluntary participation
participation must be completely voluntary, and they may withdraw from a study for any reason at any time without repercussion
confidentiality/anonymity
must be protected during and after the study, including relation to reporting results of the study
protection of human research participants
participants must be protected to assure beneficence, nonmalficence, and a risk-benefit ratio that favors the benefits side
social justice
individuals/groups must be treated fairly and equitably in terms of bearing the burdens and receiving the benefits of research
research misconduct
must be avoided, including plagerism, copyright or patent infringement, falsifying or fabricating data, misrepresenting data and conducing frivolous research