Quantitative Data Analysis Flashcards
Null hypothesis
the hypothesis that suggests there is no difference between two sample groups
Alternate hypothesis
the hypothesis that the difference between two samples is not due to random factors alone
Type I error
the chance that the null hypothesis is true but rejected wrongly
Type II error
the chance that the null hypothesis is false but accepted wrongly
Two tailed tests
tests which determine whether or not two samples have difference means outside a certain range
One mean may be greater than or smaller than the other
Univariate analysis
analysis invoving only on dependent variable
Multivariate analysis
analysis involving more than one dependent variable
Degrees of freedome
df
the number of independently valued units in a sample (usually n-2)
affects the level of significance or a result and the probability of error
T tests
when you compare two samples or a sample to some required value
To determine how significant the difference between the samples is
Parametric test, requiring data to be normally distributed
Paired or unpaired test
use when the two column of data are matched
The mean difference between the two repeated observations is observed and compared
two tailed or one tailes
test the critical regions in the two tails at the far ends of the curve
used to clarify the one tailed test where we would want to know at which end the score is
Non-parametric tests
e.g Chisquare test
used when data is nor normally distributed
Chi Square test
for non parametric data
used whether there is a significant difference between two data samples, when the two data samples are independent of eachother
Dose not use mean or standard deviation
