Module 3 Samplingdistribution

Question 1

Standard error of the mean SEM

Answer 1

calculated by dividing the standard deviation of a population by the square root of the number of samples taken from the population

With more samples, the number of the equation becomes larger causing Sem to decrease. A larger SEM indicated the data has a lot of variability. ( curve it wide)

Question 2

point estimation

Answer 2

a single value that estimates a population parameter eg using a sample mean to estimate a true population mean. can vary due to random chance and does not tell you about sampling variability

Question 4

interval estimation

Answer 4

a range of values that are likely to contain a population parameter commonly effected to as confidence intervals (cis) which consist of the point estimate and a range of values that estimate the variability around the point estimate to some degree of confidence.

Question 5

what level of confidence is used

Answer 5

95% level of confidence meaning that you are 95% confident that the true population mean falls within a certain range of values. are conservative and less likely to be wrong than a single point estimate

Question 6

hypothesis testing

Answer 6

a way to estimate population parameter

Question 7

fail to reject null hypothesis

Answer 7

you did not find enough evidence to suggest there is a detectable difference beyond that of random choice

Question 8

null hypothesis

Answer 8

suggests that the true population mean is equal to the hypothesized population mean.

there are no differences or relationship between the variables.

Question 9

alternative hypothesis

Answer 9

the population parameter is not equal to the hypothesized value. the alternative hypothesis can be written in three ways

Question 10

three ways to write alternative hypothesis

Answer 10

one tailed alternative hypothesis

two tailed alternative hypothesis
one tailed alternative hypothesis

Question 13

What are the th ree types of probability distributions

Answer 13

Binomial, poissom, gaussian

Question 14

This distribution is of random continuous variables with infinite number of possible outcomes and is normal

Answer 14

Gaussian

Question 20

type 1 error

Answer 20

when you reject the null when it is true

Question 21

type 2 error

Answer 21

when you fail to reject the null when it’s false

Question 22

what is beta

Answer 22

beta is 0.2 meaning there is a 20 percent chance that you say there are no differences when there actually are

Question 23

which error is worse type one or two

Answer 23

type 1 error (rejecting null when it’s true) is worse than type 2. it’s worse to convince an innocent person than not convince someone who is guilty.

Question 24

type one error is dependent on what

Answer 24

alpha ( or the significance level which is 0.05) saying there’s a 5%chance of saying there is a difference when there isn’t