Statistical Modeling
- Confidence Intervals for Distributions
- Confidence Intervals
- Hypothesis Testing
- Interval Estimation
- Normal Confidence Intervals
- Statistical Modeling
Setup:
Parameter:
A statistical model:
todo
[!example]
Suppose that we toss a coin 100 times and we are interested in finding
then we have
[!example]
Suppose we look at the data and it appears to be normal, then
with
Notes:
- Attributes of the population that you are interested in are typically the parameters of your model
- Finding a model is an empirical question, not theoretical
Estimation
Problem:
Data:
goal: construct
Notes:
- unknown constant -> will never be known, otherwise we don't need to estimate it
[!example]
A coin is tossed 100 times with
We do the experiment and observe 60 heads
Suppose
If
Idea: likelyhood ->
where
Setup:
what are we given:
What is the model?
What is the objective?
To estimate
Likelyhood Function
If
Maximum Likelihood Estimate (MLE)
The value of
[!properties]
- Consistency: As
, - Efficiency
- Invariance: if
is the MLE of , then is the MLE of
Binomial MLE
Suppose
solution
suppose
Likelyhood:
Log likelyhood:
so
now set:
which is exactly
todo organize, understand
Poisson MLE
Suppose
solution
todo calculus
Continuous MLEs
Model:
Exponential MLE
Suppose
Suppose
- Find median, m
F(m) & = \frac{1}{2}, \quad \text{where } F(m) = P(Y \le m) \
1 - e^{-\lambda m} & = \frac{1}{2} \
m & = -\frac{1}{\lambda} \ln\left( \frac{1}{2} \right)
\end
Remember that
For large enough
since
[!example]
Suppose a coin is tossed 200 times and we observe
We have
This is the relative likelihood of
wtf is bro waffling about I don't get it