Reading...
Play button
Play button
Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
25 Cards in this Set
- Front
- Back
|
correlation coefficient
|
r: measures the degree of linear association between two metric variables
positive association r>0 negative association r<0 |
|
|
when to use correlation coefficient
|
when exploring linear association between two metric variables
|
|
|
hypothesis
|
-Suggested explanation
-Reasoned correlation -Possible Explanation |
|
|
what makes a good hypothesis?
|
it is good if it is falsifiable and is capable of rejection
ex. there are no cars in the park vs. there are cars in the park |
|
|
why is a bad hypothesis bad?
|
absence of evidence is not the evidence of absence
|
|
|
null hypothesis
|
nothing happened
-no difference between the observed and the expected distribution |
|
|
alternative hypothesis
|
something happened
|
|
|
p-value
|
an estimate that a particular result could have occurred by chance if the null hypothesis is true
|
|
|
chi-square test
|
compare the observed distribution in the sample with the 'expected' distribution
|
|
|
number of groups symbol
|
G
|
|
|
degrees of freedom
|
df
-number of groups - 1 |
|
|
when to reject the null
|
when the test statistic is larger than the critical value
|
|
|
df for association
|
r-1*c-1
where r = rows and c = columns ex. a 2x2 table would have 1 df |
|
|
steps for hypothesis testing of a single mean
|
1.formulate hypotheses
2. select appropriate formula 3. select significance level 4. calculate z or t statistic 5.calculate degrees of freedom (t-test) 6.obtain critical value from table 7. make decision regarding the null hypotheses |
|
|
z-test vs. t-test
|
use a z-test when the variance of the distribution is known, otherwise use a t-test
-for a large sample, t-test is equivalent to a z-test |
|
|
how large must t be to reject the null
|
t must be larger than t-critical (threshold)
|
|
|
what does t-critical depend on
|
-significance level (typically .05)
-degrees of freedom (n-1) -whether t-test is one sided or two sided -go to t-tables |
|
|
Critical value of t
|
two sided test:
t-critical = t a/2,n-1 one sided test: t-critical =t a,n-1 |
|
|
probability type 1 error
|
probability of rejecting the null when it is actually true
|
|
|
what does a low a mean?
|
higher confidence level, lower chance of rejecting the null if it is true
(false positive) |
|
|
type II error
|
probability of not rejecting the null when it is false
(false negative) |
|
|
regression analysis
|
statistical technique that is used to infer a relationship among two or more variables
builds a model that can be used to: -describe -predict -control |
|
|
5 key steps of regression modeling
|
1.hypothesize deterministic component-IV
2.estimate unknown model parameters 3.specify probability distribution of random error term-estimate std. dev. of error 4.evaluate model 5. use model for prediction and estimation |
|
|
where do independent variables come from
|
-managerial experience
-research -common sense |
|
|
R^2
|
amount of variance of Y explained through the regression
|
