Error and Power

Question 1

Type 1 error and type 2 error

Answer 1

Type 1: Finding convincing evidence that Ha is true when in reality Ha is not true (rejecting Ho when Ho is actually true)

Type 2: Not finding convincing evidence that Ha is true when in reality Ha is true, (failing to reject Ho when Ha is true)

Question 2

Power

Answer 2

Probability of avoiding a type 2 error = probability of finding convincing evidence that Ha is true when in reality Ha is true

Question 3

Factors that affect Power

Answer 3

Sample size: To increase power increase sample size
Significance level alpha: A larger value of alpha increases power
Effect size: The farther the true value is from the hypothesized value the larger the power
Data Collection: Using blocking rather than a completely randomized design can increase power.

Question 4

Paired T-Test, Identification hints Ho and Ha

Answer 4

Key Phrase: Mean Difference
Two lists of numbers are paired (each row could have a unique label) Ho = mewD = 0
Ha: mewD < 0, >0 or not equal to 0.
mewDiff = The true mean difference in _

Question 5

Chi - Square tests (conditions)

Answer 5

Random: Data from a random sample(s) or randomized experiment.
10%: The sample must be less than or equal to 10% of the population
Large counts: All expected counts are at least 5

Question 6

Two Sample T-Test Identification hints, Ho and Ha

Answer 6

Key Phrase: Difference in means
Two lists of numbers have no association (Could be scrambled)
Ho: mew1-mew2=0
Ha: mew1-mew2<0,>0 or not equal to 0.
mew1-mew2 = The true diffreccne in mean ___ for __ and ___.

Question 7

Types of Chi Square Tests

Answer 7

Goodness of Fit: Use to compare the distrbutioon of a categorical variable in one population to a hypothesized distribution.
Homogeneity: Use to compare distribution of a ccategoriccal variable in for 2 + populations or treatments.
Independence: Use to test the association between two categorical variables in one population

Question 8

Chi - Square Tests , df and expected counts

Answer 8

1. Goodness of fit:
   df = # of categories - 1
   Expected counts: Sample size times hypothesized proportion in each category.
2. Homogeneity or Independencce:
   df = (# of rows - 1)(# of columns - 1)

Expected counts: (row total)(column total)/table total

Question 9

Inference for regression with computer output

Answer 9

Using foot length (x) to predict height (y) with n=15

Question 10

Inference for regression conditions

Answer 10

Linear: Association between the variables in linear, check with residual plot.
Independent: observations. 10% contrition if sampling without replacement.
Normal: Responses vary noraakky around the regression line for all x-values. Chek with graph of residuals,
Equal SD: Around the regression line for all x-vallues check with residual plot.
Random: Data from a random sample or randomized experiment.