MGSC 291 Exam 3-Farnoush - COPY

0.0(0)
Studied by 0 people
call kaiCall Kai
learnLearn
examPractice Test
spaced repetitionSpaced Repetition
heart puzzleMatch
flashcardsFlashcards
GameKnowt Play
Card Sorting

1/108

encourage image

There's no tags or description

Looks like no tags are added yet.

109 Terms

1
New cards

Point Estimate

The estimate of units sold is a one-number "best-guess" units sold.

2
New cards

What is the goal with statistical analysis?

To reduce it where you can quantify it always.

3
New cards

Sampling Distribution

-Allows us to quantify uncertainty using just one sample.

-It is a theoretical distribution that represents the possible values of a statistic calculated from multiple samples.

4
New cards

Sampling Distribution of the Sample Mean

-the distribution of all possible sample means of size n from the sample population.

-is a theoretical probability distribution.

5
New cards

Central Limit Theorem (CLT)

For any population, the sampling distribution of the sample mean is approximately normal if the sample size n>30.

6
New cards

Based on CLT, the sampling distribution of the same mean is -?

-Normally distributed

- With mean of μ -Standard deviation of ⁄√𝜎 𝑛

7
New cards

What does ignoring dependencies in the data lead you to?

Underestimate uncertainty.

8
New cards

The null hypothesis (H0)

The belief that has been around for some time (the status quo) will be called the null.

H0: μ = 100

H0: β = 0

H0: μ1 - μ2 = 0

9
New cards

The alternative hypothesis (Ha)

What we want to prove.

HA: μ ≠ 100

HA: μ < 100

HA: μ > 100

10
New cards

Let's say a researcher has reason to believe the population mean is different from what has been expected....

-They set a hypothesis.

-They collect data

-They make use of a test statistic and p-value as evidence to reject H0.

-They make a decision between H0 and Ha and reject or fail to reject the H0.

11
New cards

Test Statistic

Measures the distance (the difference measured in units of errors) between the null hypothesis and your parameter estimates.

12
New cards

The correlation of data with a lagged version of itself is called

Autocorrelation

13
New cards

Suppose you have a time series model and the lag1 coefficient is B=1.2. What type of series do you have?

Diverging

14
New cards

Which of the following is the most useful type of series for modeling?

Mean-Reverting

15
New cards

Use logistic regression when

The response is binary.

16
New cards

What is a sampling distribution?

The distribution of a statistic.

17
New cards

If your sample size is n=250, what is the approximate shape of the distribution for the sample mean?

Normal

18
New cards

Dependencies in the data often lead to an

Underestimate of uncertainty.

19
New cards

How do you estimate the standard error of the sampling distribution using a bootstrap?

calculate the standard deviation of the bootstrap estimates

20
New cards

Which of the following is a pre-specified cut-off to determine statistical significance for a hypothesis test?

significance level

21
New cards

In hypothesis testing, a low p-value means

a rare result if the null were true

22
New cards

Increasing the sample size will

increase the chance of finding statistical significance

23
New cards

If a researcher collects more data or tries different analyses just to achieve statistical significance, this is known as

p-hacking

24
New cards

Suppose the p-value reported for a beta coefficient in summary.glm is

the predictor's coefficient is statistically different from 0

25
New cards

What are the 2 types of frequentist standard errors we learned?

Theoretical & bootstrap

26
New cards

The bootstrap is used to

estimate sampling distributions

27
New cards

If you set a seed when running a bootstrap, you will get

the exact same results if you run it several times

28
New cards

What is the Achilles' heel of the bootstrap?

when you have dependent observations

29
New cards

What is a benefit of increasing B, the number of bootstrap samples, in a bootstrap?

it will decrease Monte Carlo error

30
New cards

Which of the following is a way to allow subjective beliefs to be incorporated mathematically into a probability calculation?

Bayesian statistics

31
New cards

Using a very large set of predictors in a regression model will likely lead to

poor performance of the model on new data

32
New cards

If you have taken the log of the response variable in regression and use the regression to make a prediction, it's important to

use the exp() function on the predicted value from the predict() function

33
New cards

Which of the following is the correct interpretation for PPV (positive predictive value) of a medical test for COVID?

the chance you have COVID if you test positive

34
New cards

What method uses penalized deviance minimization?

regularization

35
New cards

What does the "free" argument accomplish?

it allows certain coefficients to be unpenalized

36
New cards

The vertical line in the plot indicates

the model chosen using the AICc (the corrected AIC), not the BIC

37
New cards

frequentist uncertainty

if we were to repeatedly draw samples of the same size from the same population, we might obtain slightly different sample means each time.

38
New cards

A trade group states that back-to-school spending averages $606.40 per family. If this is wrong, a different economic model is needed. Is there evidence the average spending is higher this year? State the hypotheses.

•H0: μ = $606.40

•HA: μ > $606.40

39
New cards

"If the P is low......"

the null must go

40
New cards

In hypothesis testing, a common way to use p-values is to compare them to a

significance threshold α

-commonly α = 0.05 or α = 0.01

41
New cards

The symbols like *** or * that you see next to the p-value in the R output indicates whether

each coefficient is significant at different thresholds.

42
New cards

p-hacking

where people look at many tests and report only those that are significant which have a p-value less than some cut-off, usually 0.05.

43
New cards

What does p-hacking lead to?

a high proportion of false discoveries in the published literature

44
New cards

How close is a sample statistic to a population parameter?

The statistic from our sample is probably off by some levels of error.

Point Estimate +/- Margin of Error

45
New cards

Confidence level

the probability that the true population parameter falls within the interval.

•Ex: 95 CI: 95% confidence level, means we want to be right 95% of the time

•α= 1- 95%

46
New cards

Margin of Error

critical value*se

47
New cards

$fit

1

33326

Point estimate

48
New cards

$se.fit

[1] 1330.901

Standard Error

49
New cards

> certpredfit+c(−2,2)∗certpredfit + c(-2,2)*certpredse.fit

[1] 30664.2 35987.8

What does this tell us?

We are 95% confident that the average sales price of certified used cars is between $30,664.20 and $35,987.80.

50
New cards

Bootstrap

•uses resampling with replacement from your current sample to mimic the sampling distribution.

•It allows you to create a version of the sampling distribution on your computer, so that you can draw from it as needed to understand the properties of your analysis.

51
New cards

Using set.seed will allow the user to

get the exact same sequence of random numbers generated afterwards each time. necessary if, for example, you need to replicate the exact sample to test the impact of code changes.

52
New cards

Monte Carlo variation

The variability in the bootstrap estimates

53
New cards

When choosing this sample size, you are trading between

computation time and precision.

-Larger B decrease Monte Carlo variation and increases computation time

54
New cards

nonparametric bootstrap

does not rely on any assumptions about the underlying distribution of the population.

55
New cards

Bootstrap provides..

robust standard errors. it estimates the sampling distribution for your estimator of interest.

56
New cards

getBeta

produces your statistic of interest.

57
New cards

statistical bias

the difference between the expectation of your estimator and the expectation of the target that you are trying to estimate.

58
New cards

Bootstrapping Regression Model

Advantage: The bootstrap doesn't make any parametric modeling assumptions and thus provides standard errors that are robust to many sources of mis-specification such as nonconstant error variance.

Disadvantage: The bootstrap takes more computation time.

59
New cards

Achilles' heel

the bootstrap makes no parametric modeling assumptions, but it has an Achilles' heel: it relies on an assumption of independence between observations.

60
New cards

How to fix Achilles' heel

instead of resampling individual observations, you resample blocks of observations that are potentially correlated with each other.

61
New cards

percentile bootstrap confidence interval

to calculate the bounds directly on your sample of bootstrap estimates.

62
New cards

Unbiased estimator

the expected value of the estimator is equal to the true value of the parameter being estimated.

63
New cards

Bias-adjusted

difference between the original price estimate and the estimated bias

64
New cards

Bayesian uncertainty

characterizes probabilities over models and parameters by appealing to the idea of subjective beliefs rather than repeated trials.

65
New cards

How to solve a linear regression problem?

Model (construct a linear equation model), Estimate the unknown coefficients, Predict (making an educated guess using our formula)

66
New cards

An underfit in the model is said to have

high bias

67
New cards

An overfit model is said to have

high variance

68
New cards

Out-of-sample data (test data)

is new data that your model hasn't seen before and needs to make predictions on.

69
New cards

We can use the gamlr library to run our lasso regression to predict..

fail from the inputs.

70
New cards

Sparse model matrix

Does not store any 0's to save on memory, since in many applications, your input matrix will contain mostly 0's.

71
New cards

lambda

the sequence of fitted λt penalties

72
New cards

alpha

the sequence of fitted intercept terms

73
New cards

beta

the sequence of fitted regression coefficients

74
New cards

In gamlr, the "free" argument lets you

exclude certain columns from being penalized in the regression fit by specifying their column indices or names

75
New cards

AIC

is an attempt to approximate the average OOS deviance on new data.

76
New cards

The AIC is the most commonly applied IC, but....

you should not use the AIC.

77
New cards

The BIC can be useful for..

model selection in small sample settings.

-it tends to underfit and choose overly simple models

78
New cards

drop(yhat)

removes sparse formatting

79
New cards

exp(drop(yhat))

exponentiate to get predicted prices.

80
New cards

When is a log-log model appropriate?

When the response and explanatory variable move multiplicatively together.

81
New cards

When should you use logistic regression?

Binary response (yes/no, 1/0, true/false)

82
New cards

Why do you need to exp() to predictions that are on the log scale?

-Because e^log(y) = y

-Puts prediction back on scale the data were measured in

83
New cards

What's the difference between frequentist statistics and Bayesian statistics?

-Frequentist relies on thought experiment of repeatedly sampling from a DGP.

-Bayesian incorporates prior (subjective) beliefs to update probability.

84
New cards

Se.fit=T

gets standard errors

85
New cards

Regularization

-Uses penalized deviance minimization

-Penalizes for complexity (number of predictors)

-Provides paths - sets of candidate models

86
New cards

Overfit vs underfit

-Overfit is high variance

- Underfit is high bias

87
New cards

How do you compute a bootstrap confidence interval?

use percentiles.

88
New cards

What B is and what it means to have a smaller versus larger B?

-B = number of bootstrap samples

-Bigger B lowers Monte Carlo variation

89
New cards

Why not always have a really large B?

Computational time

90
New cards

What is Set.seed used for?

to ensures someone can replicate the results of a procedure that uses random sampling

91
New cards

monte Carlo method

Uses repeated sampling to estimate sampling distribution

92
New cards

"95% confidence" versus "95% probability"

-Technically, once you compute the CI, it no longer has a 95% chance of containing the parameter (it either happened or it didn't)

-However, the procedure is such that if you compute many confidence intervals 95% of them will contain the parameter

93
New cards

What does the sample size do to the p-value?

Easier to achieve statistical significance (get a low p-value)

94
New cards

practical versus statistical significance

Statistical significance is low p-value

95
New cards

Significance level

A pre-specified cut-off for how low the p-value needs to be to say you think the alternative is true

96
New cards

Low vs High P-value

Low p-value means you observed a rare result if the null were true

-High p-value is a common result if the null is true

97
New cards

What does dependence among observations do to SE?

Makes SE smaller than it should be

98
New cards

What is a confidence interval estimating?

The true population parameter

99
New cards

Prediction intervals are wider than confidence intervals because:

They include variability of individual observations

100
New cards

What does set.seed() do?

Makes results reproducible