Chapter 2.2 -- Regression.Testing Flashcards
How can a random error be controlled?
By statistical significance or by confidence interval
Hypothesis testing (recap)
How do we: MEASURE HOW FAR DATA ARE FROM WHAT YOU EXPECT UNDER Ho
State Ho and H1
Choose alpha level related to CI (typically 1% or 5%)
Calculate test statistic, find p-value
Explain the z-test
slide 25
What does the degrees of freedom mean?
It is a function of sample size determining how the spread of the distribution is.
CI and 2-Sided Tests
A level alpha 2-sided test rejects H0: π = π0 exactly when the β¦
value π0 falls outside a level 1 β alpha confidence interval for π.
slide 27
Differentiate between type I and type II errors
Type I error - You reject the null hypothesis when the null hypothesis is actually true.
Type II error - You fail to reject the null hypothesis when the alternative hypothesis is true.
π‘-Tests
Formula is slightly different for each:
* Single sample: β¦different from a pre-existing value
* Paired samples:
β tests the β¦
* β¦:
β tests the relationship between 2 independent populations (Welchβs t-test)
β tests whether a sample mean is significantly β¦
relationship between 2 linked samples, e.g., means obtained in 2 conditions by a single group of participants
Independent samples
Selected Statistical Tests
Parametric Tests
* the family of π‘-tests: β¦
Non-parametric Tests:
Tests of the Probability Distribution
* Kolmogorov-Smirnov and Chi-square test: β¦
compares two sample means or tests a single sample mean * F-test: compares the equivalence of variances of two samples
- Wilcoxon signed-rank test for 2 paired i.i.d samples
- Mann-Whitney-U test is used for 2 independent i.i.d samples
- Kruskal-Wallis-Test for several i.i.d non-normally distributed samples
used to determine whether two underlying probability distributions differ, or whether an underlying probability distribution differs from a hypothesized distribution
