ANOVA
Confidence Intervals
Correlation
Simple Regression
Potpourri
100

What is the Ha in an ANOVA test?

at least one mean differs

100

If you want to have more confidence in your estimate, build this.

Confidence Interval

100

What is the name of the variable that links two highly correlated variables?

Confounding variable

100

What is the difference between correlation and regression

You use regression to predict. Correlation only gives us strength of relationship between two variables.

100

How can the number four be half of five?

IV, the Roman numeral for four, which is “half” (two letters) of the word five.

200

A Nova

200

What is x-bar called when used to construct a confidence interval?

Point Estimate

200

What is the hypothesized value of correlation in testing for significance?

0 (zero)

200

There are always an equal number of positive and negative error terms in a regression.  T or F?

False

200

Yes!

300

In an ANOVA test, if the significance level is 5% and the p-value is 2.3%, what can be concluded?

since p-value is less than significance level, we can reject the Ho and accept the Ha. 

Ha: at least one mean differs

300

the t-score for a 95% confidence interval, with a sample size of 12.



2.201, from:

alpha = 1-.95 = 0.05

alpha/2 = 0.025

n-1=11

11 and 0.025 intersects at 2.201 on a t-table

300

What happens to the sample correlation as the number of observations increases, if little bias in the sample?

it gets closer to the value of the population correlation, ie. becomes more stable

300

what does the "hat" over the response variable mean?

predicted (or estimated)

300

It was announced yesterday that this artist will have the new number 1 song on Billboard's next Hot 100

Jimin (from BTS group)

400

A researcher is trying to determinine if there is a difference in popularity between different levels of Cacao in the company's line of chocolate bars.  Participants were completely randomized and then given 1 of 3 levels of Cacao.  They were asked to to give a favorability rating between 1 and 100.  Below are their results: 

1) How many observations are in the study

2) In the context of the study, what difference of means are we testing for?


9 observations.

Testing to see if there is a difference in popularity levels (between levels of Cacao)

400

t-score for a 90% confidence interval if n=15 

1.761, from:

alpha = 1-.90 = 0.10

alpha/2 = 0.05

n-1=14

14 and 0.05 intersects at 1.761 on a t-table


400

In lecture, there was an image showing a high correlation between chocolate consumption in a country and number of Nobel winners from a country.  What was the confounding variable?

High GDP, high quality of life

400

interpret the slope coefficient with the below information:

b1 = 2.5

x is debt (in $000's)

y in income (in $000's)

As debt increases by $1,000, income increases by $2,500

400
This Ironman actor celebrates his birthday today

Robert Downey Jr.

500

A researcher is trying to determinine if there is a difference in popularity between different levels of Cacao in the company's line of chocolate bars.  Participants were completely randomized and then given 1 of 3 levels of Cacao.  They were asked to to give a favorability rating between 1 and 100.  Below are their results: 

What do you think the result of the ANOVA test will be?  Why do you think that?

At least one mean differs.

There looks to be much more "between-variation" vs. "within-variation" - hence, at least one mean will probably differ (the Ha)

500

This component of the Confidence Interval is everything to the right of the plus/minus sign


Margin of Error

500

Which has a stronger correlation, -0.74 or +0.63

-0.74

500

If we summed up all the error terms against a true regression line, they would approximate this number.

0 (zero)

500

How did the cake turn out?


M
e
n
u