Stats/301

Front 1

Correlation

Back 1

quantifies/describes the degree of a relationship between two variables.

i.e Ice cream sales and temprature have a strong correlation

Front 2

Linear regression

Back 2

is the graph or model of a linear relationship between two variables.

Front 3

Pearson Correlation Coefficient

Back 3

(r)-basically the slope, tells how the rate of change occurs with respect to to variables

calculated by means and standard deviation

r=(􏰒SUM of all)((Z score for X)×(Z score for Y))

Front 4

Spearman’s rank correlation

Back 4

strength of a relationship between two ranks of variables.

Front 5

What makes the correlation between X and Y

Back 5

X causes Y

Y causes X

its a coincidence

final: C causes x and y relations.

Front 6

experimental study

Back 6

variables/induviduals have a treatment and we observe response

we can fix values of variables we want to control

for example you give a football player a oxygen tank during breaks and compare it to fatigue of non -oxygenated

Front 7

observational study

Back 7

Natural observation, no external influence imposed

Front 8

Y = intercept + slopeX + error:

this equation represents what?

Back 8

the linear regression equation

Front 9

the error in the linear regression equation assums

Back 9

Error is the random influence on Y

Normal distrubution

Equal variance for all data points

Independent

Front 10

what are Residuals and how do we use them? equations ?what do they mean?

Back 10

Residuals are basically, how far a point is from the Line of best fit. It basically can depict to us how relaible our line of best fit is. 􏰒

SUM of all(Y-Y^=u^)^2=(Y − intercept − slope · X)^2

The higher the residual the more error and less reliable our line of best fit.

Front 11

What is the concept of least squares?

Back 11

When we construct our line of best fit We should fine the mean and slope that minimizes the residuals; which reduces the variability and increases certainty

=(Y − intercept − slope · X)^2

Front 12

What does a slope of zero mean?

Back 12

It means that there is no visible relationship between two variables.

Front 13

P value assumes what? and what does changes in the P value mean

Back 13

P-value assumes there is no existing relationship between variables.

The logic indicates that as P-value increases there it is more likely there is no relationship. As P-value decreases it indicates alternatively that the chances of the there being no relationship decrease meaning the relationship is strong and chances of that being caused by chance are unlikely.

Front 14

What is Type I error and how is it different then type II?

Back 14

Type i IS when u reject the null but it was actually true, and Type II is when u accept the null but it was false

Front 15

How large do samples need to be?

Back 15

Generally, Large samples are not always better then small ones. The main thing is, is how the sample is produced.

Front 16

what is power

Back 16

power is the probability of jecting the null, when it is false.