Central Limit Theorem - the sampling distribution of the mean Selecting a random sample from SRS Table

will always be normally distributed, as long as the sample size ● Population is from 1 - 50
is large enough (n>30). ● Starting on line 2 of the table, select the first 3 people
(will be selecting a two-digit numbers between 1-50)
Mean of sampling distribution of mean - equal to the
population mean (µ) Line 1: 45624 56918 34901 43899 28790
Line 2 52311 43620 61099 23404 48910
Standard deviation of sampling distribution of mean Line 3: 31900 75762 78017 23412 44876
● standard error of the mean
● calculated by dividing the population standard ● The 1st two #s in line 2 are 52 which is outside of the
deviation by the square root of the sample size range, so can’t use it
● formula: σ/√n ● The next two numbers are 31 (within range), 14 (within
range), and 36 (within range)
Probability that average score is > value of x ● The first 3 random people selected would be 31, 14, an
36
1: Identify parameters
● Population mean (µ) Median
● Population standard deviation (σ) ● Arrange the data points from smallest to largest.
● Sample size (n) ● If the number of data points is odd, the median is the
● Value of x middle data point in the list.
● If the number of data points is even, the median is the
2: Calculate standard deviation of sampling distribution of mean average of the two middle data points in the list.
● formula: σ/√n
Quartile 1 (Q1):
3: Calculate Z-score ● refers to the value below which 25% of the data falls
● z = (x - µ) / σ/√n ● Q1 represents the median of the lower half of the data
● Formula: (n + 1) / 4
4: Look up z-score on normal distribution table

5: Find the probability above x Quartile 3 (Q3):

● Since the probability shoul be greater than x, subtract ● value below which 75% of the data falls
the value from the z-table from 1. ● Q3 represents the median of the upper half of the data.
● Formula: 3(n + 1) / 4

Probability of selecting an individual from the population is Outliers

< value of x ● Identify outliers through the Interquartile Range (IQR)
1: Identify parameters ● Find IQR = Q3 - Q1
● Population mean (µ) ● Find lower range # = Q1 - (1.5 * IQR)
● Population standard deviation (σ) ● Find higher range # = Q3 + (1.5 * IQR)
● Sample size (n) ● Outliers will be any numbers below the lower range #
● Value of x and higher than the higher range #

2: Calculate Z-score Box Plot

● z = (x - µ) / σ /n

3: Look up z-score on normal distribution table

Labeling to select a Simple Random Sample (SRS)

● assign each individual in the population a unique
numerical label
● typically starting from 1 and going up to the total
number of individuals in the population

Histogram Intervals
● R = Max. range # - Min. range #
● # of intervals = R / = square root of # of data points
Null Hypothesis (H0): Dice - complete table using fractions w/ common
● a statement that there is no significant difference or denominator for probability of spots showing (example
effect between variables table)
● represented with an equal sign (=)
# spots 2 4 6 8 10
Alternate Hypothesis (Ha or H1)
● the opposing claim that there is a significant difference Prob 1/36 6/36 13/36 12/36 4/36
or effect or .028 or .167 or .361 or .333 or .111
● denoted by symbols like <, >, or ≠,
● Symbol depends on the direction of the test (increases, Dice - expected value and variance of distribution
decreases) Expected Value = Sum of (x * p(x) from the table or 2(.028) + 4
(.167) + 6 ( .361) + 8 (.333) + 10 (.111) = 6.664
Calculate z value for test and determine 1 sided p-vale for
test: Variance of the distribution
● z = (sample mean - population mean) / (population
standard deviation / sqrt(sample size)); to find the one- Probability that you roll a 2 or 10
sided p-value, look up the calculated z-value on a P (x=2) + P (x=10) = 0.28 + .111 = .139
standard normal distribution table (z-table), depending
on whether your test is left-tailed or right-tailed, and Graph on interval 0 ≤ x ≤ 3 anf function
use the corresponding area under the curve as the p- f(x)= x^2 +9
value.
● Calculating z-value: Does graph represent legitimate probability model
○ Formula: z = (x̄- μ) / (σ / √n)
○ Where:
■ x̄ is the sample mean
■ μ is the population mean
■ σ is the population standard deviation = 1/9 * 9 = 1
■ n is the sample size
● Finding the p-value: Mean of the model
○ One-tailed test:
■ For a right-tailed test: p-value
= 1 - P(Z ≤ z)
■ For a left-tailed test: p-value
= P(Z ≤ z)
= 2.25
Significance - is there evidence
● Interpreting p-value: A smaller p-value indicates Variance of the model
stronger evidence against the null hypothesis.

Power of the test if we want to detect a difference of 2 from

the null hypothesis

● Power = 1 - Beta (Beta is the probability of making a

Type II error, and Beta is calculated based on the
desired effect size (in this case, a difference of 2)

99% confidence level

● ± (2.576 * Standard Error), where "2.576" is the
critical z-score for a 99% confidence level and
"Standard Error" is calculated as the population
standard deviation divided by the square root of the
sample size (σ/√n
● Formula for Confidence interval: 2.576 * σ/√n
● Propose mean - confience interval ≤ μ ≤
Propose mean + confience interval