Research Flashcards
Systematic error
deals with accuracy ( decreases accruacy)
random error
Random and could not be induced by a particular experimental modification. example: system malfunction.
decreases precision
precision
how closely individual measurements of the same value agree with each other.
accuracy
how true to original value
experimental study
scientists manipulate one or more variables in prder to observe the outcome
Observational study
- nonexperimental
- do not manipulate but just observe the variables
Types of observational study
- cross sectional study
- cohort study
- case-control study
Cross sectional study
studies a sample of the population at one point in time
cohort study
studies a sample of population over time
case-control study
studies two sample populations, one with and one without an outcome.
when is a t test used?
most appropriate to compare means for each of the variables.
- compare teh means of two groups when the dependent variable is continuous.
when is a chi test used
used when variables are categorical
when is a chi test used
used when variables are categorical
Paired t test - commonly used in before and after studies
- compares the distributoin of two groups when each value within a group has a natural partner in the other group.
statistical signficance = null hypothesis is rejected
the difference between two different groups is signficant.
example if p=0.04, 4 % probability of any difference between group occurs by chance, and reject the null hypothesis.
statistical signficance = null hypothesis is rejected
the difference between two different groups is signficant.
example if p=0.04, 4 % probability of any difference between group occurs by chance, and reject the null hypothesis.
what does it mean when the p value is 0.01?
there is one percent chance that the null hypothesis is correct. reject the null hypothesis. The difference between groups could be due to random chance.
what does it mean when the p value is 0.01?
there is one percent chance that the null hypothesis is correct. reject the null hypothesis. The difference between groups could be due to random chance.
define confounding variable
a variable that is correlated with independent variable and has a casual effect on the dependent variable.
internal validity
refers to whether a casual relationship between the independent and dependent variable can be justifiably concluded from an experiment.
- it can be greatly affected by confounding variables
External validity
refers to the generalizability of results from a sample to a wider population, and is determined by factors like whether or not the characteristics of sample are representative of those of the population.
Consent must be OBTAINED prior to the commencement of a study if there is a potential for emotional/physical harm for the participant in the study.
`
Consent must be OBTAINED prior to the commencement of a study if there is a potential for emotional/physical harm for the participant in the study.
`
When an experimental design of a study does not actually test the situation it purpots - what happens?
it lacks construct validity
Scientic method
- asks question
- do background research
- construct hypothesis
- test hypothesis via experiment
- analyze data/draw conclusion
- communicate results
Criterion Validity
refers to whether a variable is able to predict a certain outcome
mediating variable -
one that explains relationship between 2 other variables
moderator variable
one that influences the strength of a relationship between 2 other variables
confounding variables
- one which is an extraneous variable that is related to both dependent and independent variable.
