math day 19

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

1/25

encourage image

There's no tags or description

Looks like no tags are added yet.

26 Terms

1
New cards

when to know which standard error to use

Categorical Data (Proportions / Percentages): The question gives a proportion (p=0.40p = 0.40) and asks about a sample proportion (p^\hat{p}). Since this counts "yes/no" categorical responses (whether a student used marijuana or not), you use the standard error formula for proportions:


quantitative Data (Means / Averages): You only use σn\frac{\sigma}{\sqrt{n}} when the problem provides a population mean (μ\mu) and standard deviation (σ\sigma) measured in continuous numerical units (like test scores, heights, or minutes).

<p><span><strong>Categorical Data (Proportions / Percentages):</strong> The question gives a proportion (</span><span style="line-height: 1.15;">$p = 0.40$</span><span>) and asks about a sample proportion (</span><span style="line-height: 1.15;">$\hat{p}$</span><span>). Since this counts "yes/no" categorical responses (whether a student used marijuana or not), you use the standard error formula for proportions:</span></p><p></p><p><span>q<strong>uantitative Data (Means / Averages):</strong> You only use </span><span style="line-height: 1.15;">$\frac{\sigma}{\sqrt{n}}$</span><span> when the problem provides a population mean (</span><span style="line-height: 1.15;">$\mu$</span><span>) and standard deviation (</span><span style="line-height: 1.15;">$\sigma$</span><span>) measured in continuous numerical units (like test scores, heights, or minutes).</span></p>
2
New cards

sampling distribution of the sample proportion symbol

p̂

<p>p̂</p>
3
New cards

sampling distribution

the fraction or percentage of individuals or items in a specific sample that have a certain characteristic of interest

4
New cards

sample proportion vs sample mean

A sample proportion (p̂) and a sample mean (x̄) are both statistics used to estimate unknown population parameters, but they measure fundamentally different types of data


Sample Proportion (p̂)

Sample Mean (x̄)

Data Type

Categorical (binary, yes/no, or success/failure)

Quantitative (numerical measurements)

What it Measures

The fraction or percentage of items in a sample that possess a specific characteristic.

The arithmetic average value of a set of numerical observations in a sample.

symbol

p̂

x̄

Population Parameter

p (population proportion)

μ (population mean)

dif formulas as well

5
New cards

Sampling Distribution: Mean and SD

The mean of “the sampling distribution of the sample proportion”

will always be equal to the population proportion:


The standard deviation of “the sampling distribution of the sample

proportion” is:

It is also called standard error of p

<p>The mean of “the sampling distribution of the sample proportion”</p><p>will always be equal to the population proportion:</p><p></p><p>The standard deviation of “the sampling distribution of the sample</p><p>proportion” is:</p><p>It is also called standard error of p </p>
6
New cards

Central Limit Theorem for Proportion

If n is sufficiently large, satisfying the condition:

“np ≥ 15 and n(1-p) ≥ 15”,


then the sampling distribution for the sample proportion is approximately normal with the mean and standard deviation


can use z score too

<p>If n is sufficiently large, satisfying the condition: </p><p>“np ≥ 15 and n(1-p) ≥ 15”, </p><p></p><p>then the sampling distribution for the sample proportion is approximately normal with the mean and standard deviation</p><p></p><p>can use z score too </p>
7
New cards

statistical inference

involves drawing conclusions about population parameters from analyzing the sample data.

8
New cards

3 main types of inferences

point estimation

interval estimation

hypothesis testing

9
New cards

point estimation

Estimate the unknown parameter based on a point estimator.


Format: A single number (e.g., sample mean x̄ = 13 or sample proportion p̂ = 0.6755


While simple, it does not tell you how close the estimate actually is to the true parameter because it lacks a measurement of uncertainty or error

10
New cards

interval estimation

Estimate the unknown parameter based on an interval estimator, typically expressed as an estimator with its margin of error.

11
New cards

hypothesis testing

Determine whether sample data provide sufficient evidence to support or reject a claim about a population parameter.

12
New cards

target parameter

The unknown population parameter of interest

13
New cards

Point estimator (estimator)

a statistic based on a random sample intended for estimating the target parameter.


Once a particular sample is observed, we obtain a specific value of the point estimator.

14
New cards

two types of target parameters and point estimators


<p></p>
15
New cards

Point Estimation vs. Interval Estimation

Point estimation by itself is not sufficient because it doesn’t tell us how close the estimate is likely to be to the parameter.


An interval estimation is more useful, it incorporates a margin of error which helps us to gauge the precision of the point estimation.

<p>Point estimation by itself is not sufficient because it doesn’t tell us how close the estimate is likely to be to the parameter.</p><p></p><p>An interval estimation is more useful, it incorporates a margin of error which helps us to gauge the precision of the point estimation.</p>
16
New cards

interval estimator

consider an interval estimator called a (1-α) confidence interval:

point estimator ± margin of error

17
New cards

margin of error

a statistical measurement that expresses the amount of random sampling error or potential inaccuracy in a survey, poll, or scientific estimate

18
New cards

Confidence Interval for Population Prop.

o The target parameter, population proportion p, is unknown.

o We use our sample proportion p̂ to make an inference on the target

parameter.

o Therefore, p̂ is the point estimator of (1-α) confidence interval for

population proportion.

19
New cards

confidence level

the degree of confidence we wish to have in our interval estimation.

o Conventionally, we use 0.9=90%, 0.95=95% or 0.99=99%


since (1-α):

• When α=0.1, we will have a 90% confidence interval.

• When α=0.05, we will have a 95% confidence interval.

• When α=0.01, we will have a 99% confidence interval.

20
New cards

Confidence Interval: Cut-Off

The cut-off is Z(α/2) is determined by the desired confidence level.

Margin of Error = Cut Off × Standard Error

21
New cards

Confidence Interval for P: Step One

Check the assumptions

22
New cards

what must be true to have confidence intervals

1. The variable must be categorical

➔ Because we are dealing with proportions.

2. Data must be obtained through randomization

➔ This implies a random sampling.

3. We MUST make sure that np ≥ 15 and n 1 − p ≥ 15

➔ This ensures that p follows a bell-shaped distribution by C.L.T.

23
New cards

Confidence Interval for P: Step Two

Calculate the three components

24
New cards

Confidence Interval for P: Step Three

Compute the confidence interval and provide interpretation:

25
New cards

Explain why you need stronger evidence to make the prediction when you want greater confidence.

The more confident you want to be about the results, the wider the confidence interval will be.


  • Higher Confidence Level —>Larger Critical Value (z^*) —> Wider Interval

  • Wider Interval —>Higher chance 0.50 falls inside —>Requires a stronger, larger lead to predict a winner


26
New cards

Standard error shows what?

It estimates how much the sample proportion from samples like this vary from sample to sample.