isye 6414 midterm 1 study notes
"All models are wrong, _________________" - questions and answers-but some are useful
Are linear models a true representation of reality? - questions and answers-no
assumptions of simple linear regression - questions and answers--linearity/mean zero
assumption
-constant variance assumption
-independence assumption
-normal distribution of error
can residual analysis check independence assumption? - questions and answers-no, all that
can be assessed with residual analysis is uncorrelated errors.
confidence interval - questions and answers-provides an interval estimate for the true average
value of y for all instances of a particular x
constant variance assumption - questions and answers-the variance (σ-squared) of the error
terms or deviances is constant
correlation coefficient - questions and answers-a statistic that efficiently summarizes how well
the Xs are linearly related to y
the square of the correlation coefficient is R-squared: p² = R²
data structure of simple linear regresion - questions and answers-pairs of data - one response
variable value, one predicting variable value
estimated regression line - questions and answers-average estimated mean response for all
settings of the predicting variable
estimation uncertainty source - questions and answers-parameter estimation
fitted values - questions and answers-ŷ_i = B̂₀ + B̂₁(x_i)
regression line where the parameters are replaced by their estimated values
fixed variable - questions and answers-does not change with the response, but is set before the
response is measured
, hat - questions and answers-differentiates between estimated parameters and the true
parameters
how do we check normality? - questions and answers-- quantile plot/normal probability plot -
should be a straight line
- histogram - should be symmetric, unimodal, no gaps
- use both!
how do we diagnose the assumptions? - questions and answers-evaluate the residuals
(differences between observed and fitted responses -- this is NOT error term because we don't
actually know β₀ and β₁) by plotting them against both fitted and predictive values and checking
if the scatter plot is random around the zero line (it should be!)
if the assumptions don't hold up.... - questions and answers-the regression could still be useful
with some transformation of y or x.
independence assumption - questions and answers-response variables are independently
drawn
responses are not related to each other (unlike in time series)
influential points - questions and answers-data points far from the mean of x or y data that
influence the regression model fit significantly
- change estimated parameter values
-change significance
-change sign
-etc.
large |t-value| - questions and answers-reject the null hypothesis
leverage points - questions and answers-data points far from the mean of x data
Linearity/Mean zero assumption - questions and answers-Means that the expected value
(deviances) of errors is zero
mean squared error - questions and answers-(sum of squared residuals) / (n-2)
δ_hat² --> estimator for δ²
multiple linear regression - questions and answers--more than one predicting variable
-estimate the relationship with a plane
y= β0 + β1(x1) + β2(x2) + ε
The benefits of buying summaries with Stuvia:
Guaranteed quality through customer reviews
Stuvia customers have reviewed more than 700,000 summaries. This how you know that you are buying the best documents.
Quick and easy check-out
You can quickly pay through credit card or Stuvia-credit for the summaries. There is no membership needed.
Focus on what matters
Your fellow students write the study notes themselves, which is why the documents are always reliable and up-to-date. This ensures you quickly get to the core!
Frequently asked questions
What do I get when I buy this document?
You get a PDF, available immediately after your purchase. The purchased document is accessible anytime, anywhere and indefinitely through your profile.
Satisfaction guarantee: how does it work?
Our satisfaction guarantee ensures that you always find a study document that suits you well. You fill out a form, and our customer service team takes care of the rest.
Who am I buying these notes from?
Stuvia is a marketplace, so you are not buying this document from us, but from seller lizmwikali72. Stuvia facilitates payment to the seller.
Will I be stuck with a subscription?
No, you only buy these notes for $7.99. You're not tied to anything after your purchase.