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;
18 Cards in this Set
- Front
- Back
|
1 Std deviation fitsnhow many % of data |
68% data ( but whether its always check) |
|
|
P value |
|
|
|
Co variance variance relation |
Slope equals covariance / variance |
|
|
Solve p value |
Why sigma / √n yet to feel.??????? |
|
|
Normal distribution formula |
|
|
|
Standard error of estimate |
((Y - y. )^2 = Unexplained variation )/(n-2)^1/2 |
|
|
Coefficient of determination r^2 |
|
|
|
Anova f test |
|
|
|
Confidence interval and hypothesis testing |
|
|
|
Cdf cumulative distribution function |
|
|
|
P test one tail 2 tail? |
For 2 tail 2 * ans |
|
|
Ppf |
This gives for significant level sigma value which will accomodate |
|
|
TSS , RSS( explained error), sse ( unexplained error) , standard error, r square |
(SSe/n-2) power 0.5. , rss/tss |
|
|
F test, |
Explained/ unexplained variance, always positive,explained variance is significant without noise, if with more noise then valueo will be 1 |
|
|
Why standard error in regression dof is n-2????? |
X bar and y bar used to calculate (y-y hat ) square so it's minus 2 |
|
|
Machine learning supervised and unsupervised |
Regression, cart classification and regression tree, random forest, neural network, clustered algorithm, dimension reduction , Specificity, confusion matrix, duc, , auc? Ridge regression , lasso regression , penalty term , |
|
|
Time series terms |
Linear , log linear, autoregression, Autocorrelation, mean inversion? , covariance stationary, autoregression , linear vs log linear, White noise, random walks , homoskedasticity . |
|
|
Linear, loglinear |
Log linear1. Regression errors should not be correlated2. R square sometimes less or more don't matter |
