PARAMETRIC Pt.1 Flashcards
2 types of hypothesis Tests
o Parametric Test
o Nonparametric test
PARAMETRIC TESTS
- Assumed distribution is NORMAL
- Assumed variance is homogenous
- Typical data is/are ratio or interval
- Data set relationships are usually independent
- Usual central measure is mean
- Benefits: can draw more conclusions
- Assumed distribution is NORMAL
- Assumed variance is homogenous
- Typical data is/are ratio or interval
- Data set relationships are usually independent
- Usual central measure is mean
- Benefits: can draw more conclusions
PARAMETRIC TESTS
Analysis where we compare against our historical or global value
o t-test
o z-test
ONE SAMPLE: PARAMETRIC TEST
Analysis where we compare a control group versus test group
TWO SAMPLE: PARAMETRIC TEST
2 samples have no relationship
with each other
Independent Samples
Samples are dependent to each
other
Paired Samples
Normal
Homogeneous
Ratio or Interval
Independent
Mean
Can draw more conclusions
Parametric
Any
Homogenous and Heterogeneous
Ordinal or Nominal
Any
Median
Simplicity: Less affected by outliers
Non-parametric
Samples must be independent of each other. There can be no relationship between the subjects in each sample
Z TEST FOR TWO MEANS
Z TEST FOR TWO MEANS: The standard deviations of both populations must be
known
Z TEST FOR TWO MEANS: Samples must be _______________ of each other. There can be no relationship between the subjects in each sample
independent
Z TEST FOR TWO MEANS: If the sample sizes are _____ than 30, the population must be normally or approximately normally distributed.
less
observed value –
mean difference
expected value –
hypothesis
If there is no difference in population means (based on the second hypothesis), subtracting them will give the difference of ____
zero
T OR F| But if there is difference in population means, subtracting them will give a number other than zero
T
Z TEST FOR TWO MEANS: Using __ value to compute for p-value
z-value
FOR Z TEST FOR TWO MEANS: P-value to compare with ______
alpha
a parametric test that is usually used to measure significant difference of small sample sizes.
T TEST
Compares same variable from same group
Dependent t-test
Compares same variable but different group
Independent t-test
Use T-test when?
✓ When standard deviation is not known
✓ When sample size is less than 30
is used for the comparison of two variance or standard deviation
F test
In statistics, the number of ________________ is the number of values in the final calculation of a statistic that are free to vary (sample size – 1).
degrees of freedom
HOW TO USE THE F TEST
→ For the comparison of two sample / population variances or standard deviations which should be _______________ from each other
independent
Characteristics of the F Distribution
1. The values of F cannot be _______, because variances are always ___________ or zero.
2. The distribution is ________ skewed.
3. The mean value of F is approximately equal to __.
4. The F-distribution is a family of curves based on the degrees of freedom of the variance of the numerator and the degrees of freedom of the variance of the denominator
- negative/ positive
- positively
- 1
