• Home
  • About
    • Yerim Oh photo

      Yerim Oh

      Happy and worthwhile day by day :)

    • Learn More
    • Email
    • LinkedIn
    • Instagram
    • Github
    • Youtube
  • Posts
    • All Posts
    • All Tags
  • Projects

[11] STATISTICS: One-Sample Tests_๐œŽ Unknown (t test)

02 Mar 2020

Reading time ~3 minutes

Table of Contents
  • ๋ชฉ์ฐจ
  • Fundamentals of Hypothesis Testing: One-Sample Tests
  • ๊ฐœ์š”
  • INTRO
  • t Test of Hypothesis for the Mean
  • When we use
  • Formula
    • Critical Value approach
    • example

๋ชฉ์ฐจ

  • Fundamentals of Hypothesis Testing: One-Sample Tests
  • ๊ฐœ์š”
  • INTRO
  • t Test of Hypothesis for the Mean
  • When we use
    • Critical Value approach
    • example

๐Ÿ‘€, ๐Ÿคทโ€โ™€๏ธ , ๐Ÿ“œ, ๐Ÿ“
์ด ์•„์ด์ฝ˜๋“ค์„ ๋ˆ„๋ฅด์‹œ๋ฉด ์ •๋‹ต, ๊ฐœ๋… ๋ถ€๊ฐ€ ์„ค๋ช…์„ ๋ณด์‹ค ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค:)



Fundamentals of Hypothesis Testing: One-Sample Tests

์ฆ‰, ๊ฐ€์„ค๊ฒ€์ฆ์ด๋‹ค.
test๋ผ๋Š” ์œ„๋”ฉ์ด ๋“ค์–ด๊ฐ”๋‹ค๋Š” ๊ฒƒ์€ ์ด ์ถ”์ •์˜ ๊ฒฐ๊ณผ๋กœ ์ธํ•œ ์˜์‚ฌ๊ฒฐ์ •๊นŒ์ง€ ํ•œ๋‹ค๋Š” ๊ฒƒ์ด๋‹ค.

One-Sample Tests: ๋ฐ์ดํ„ฐ ์„ธํŠธ๊ฐ€ ํ•˜๋‚˜์ด๋‹ค.

  • One-Sample Tests: ์šฐ๋ฆฌ๋‚˜๋ผ ์‚ฌ๋žŒ์˜ ์•„์ดํ๊ฐ€ 100 ์ด์ƒ์ด๋‹ค -> ์šฐ๋ฆฌ๋‚˜๋ผ ์‚ฌ๋žŒ์˜ ์•„์ดํ๋ผ๋Š” ํ•˜๋‚˜์˜ ๋ฐ์ดํ„ฐ ์„ธํŠธ๊ฐ€ ํ•„์š”ํ•˜๋‹ค
  • Two-Sample Tests: ์šฐ๋ฆฌ๋‚˜๋ผ์™€ ์ผ๋ณธ์˜ ์•„์ดํ๋ฅผ ๋น„๊ตํ•ด๋ณด๋ฉด ์šฐ๋ฆฌ๋‚˜๋ผ๊ฐ€ ๋” ๋†’๋‹ค -> ์šฐ๋ฆฌ๋‚˜๋ผ ์•„์ด์ฟ  ๋ฐ์ดํ„ฐ ์„ธํŠธ์™€ ์ผ๋ณธ์˜ ์•„์ดํ ๋ฐ์ดํ„ฐ์„ธํŠธ๊ฐ€ ํ•„์š”ํ•˜๋‹ค. ์ฆ‰, ๋น„๊ต, ๋ณ€ํ™” ๊ฒ€์ฆ์— ๋งŽ์ด ์“ฐ์ธ๋‹ค.

๊ฐœ์š”

์•„๋ž˜์˜ ๋„์‹์„ ํ•˜๋‚˜์”ฉ ์ž์„ธํžˆ ์•Œ์•„๋ณผ ๊ฒƒ์ด๋‹ค.
image

  • ฯƒ known: Fundamentals of Hypothesis Testing Methodology
  • ฯƒ Unknown: t-Test of Hypothesis for the Mean
  • One-Tail Tests(๋„์‹ ์ „์ฒด์— ์ ์šฉ)
  • Population Proportion: Z-Test of Hypothesis for the Proportion
  • Potential Hypothesis Testing Pitfalls and Ethical Issues(์ถ”๊ฐ€)

INTRO

[ฯƒ UNknown]
Convert sample statistic (\(x ฬ…\)) to a \(t_{STAT}\) test statistic
image



t Test of Hypothesis for the Mean

t-Test: t-table์„ ๋ณด๊ณ  ํ•˜๋Š” ๊ฒƒ image

โž• z-test์™€ ๋น„๊ตํ•˜๊ธฐ



When we use

ฯƒ UNknown์ผ ๋•Œ
As long as the sample size is not very small and the population is not very skewed, the t-test can be used.

  • To evaluate the normality assumption:
    • Determine how closely sample statistics match the normal distributionโ€™s theoretical properties.
    • Construct a histogram or stem-and-leaf display or boxplot or a normal probability plot.


Formula

์ž ์ด์ œ ์œ„์˜ ๊ฐœ๋…์„ ์‹คํ˜„ํ•  ๋ฐฉ๋ฒ•์„ ์†Œ๊ฐœํ•˜๊ฒ ๋‹ค.

๊ฐ„๋‹จํ•˜๊ฒŒ ๋งํ•˜๋ฉด,
1๏ธโƒฃ rejection area ๊ตฌํ•จ
2๏ธโƒฃ ๋‚ด test statistic ์„ ๊ตฌํ•ด์„œ ์ด ๊ฐ€์„ค์ด \(H_0\)๋ฅผ ๋ฐ›์•„๋“ค์ผ์ง€ ๊ฑฐ๋ถ€ํ•  ์ง€๋ฅผ ํŒ๋‹จ
์ธ๋ฐ ์ด๋ฅผ ๋‘๊ฐ€์ง€ ๋ฐฉ๋ฒ•์œผ๋กœ ๊ตฌ์ฒดํ™”ํ•ด ๋ณผ ๊ฒƒ์ด๋‹ค

โž• z-test์™€ ๊ฐ™์ง€๋งŒ ๊ทธ์ € table์„ z-table๋Œ€์‹  t-table์„ ์“ฐ๋Š” ๊ฒƒ์ด๋‹ค.


Critical Value approach

image [๊ณผ์ •]
1) State the null hypothesis, \(H_0\) and the alternative hypothesis, \(H_1\)
2) Choose the level of significance, ฮฑ, and the sample size, n.
The level of significance is based on the relative importance of Type I and Type II errors
3) Determine the appropriate test statistic and sampling distribution
4) Determine the critical values that divide the rejection and nonrejection regions
5) Collect data and compute the value of the test statistic
6) Make the statistical decision and state the managerial conclusion.

  • If the test statistic falls into the nonrejection region, do not reject the null hypothesis H0
  • If the test statistic falls into the rejection region, reject the null hypothesis.
  • Express the managerial conclusion in the context of the problem

์œ„์˜ ๊ณผ์ •๋งŒ ๋ณธ๋‹ค๋ฉด ์ดํ•ด๊ฐ€ ์ž˜ ์•ˆ ๋  ๊ฒƒ์ด๋‹คโ€ฆ
๊ทธ๋Ÿฌ๋ฏ€๋กœ ์˜ˆ๋ฅผ ๋“ค์–ด ์ดํ•ดํ•ด ๋ณด์ž!


example

The average cost of a hotel room in New York is said to be $168 per night. To determine if this is true, a random sample of 25 hotels is taken and resulted in an of $172.50 and an ๐Ÿ“Œ S of $15.40. Test the appropriate hypotheses at a = 0.05.
(Assume the population distribution is normal)

(This is a two-tail test)

1) State the null hypothesis, \(H_0\) and the alternative hypothesis, H1

  • \(H_0\): ฮผ = 168
  • \(H_1\): ฮผ โ‰  168

2) Choose the level of significance, ฮฑ, and the sample size, n.

  • Suppose that ฮฑ = 0.05 and n = 25 are chosen for this test
  • ๐Ÿ“Œ df = 25-1=24

3) Determine the appropriate test statistic and sampling distribution

  • ฯƒ is assumed known so this is a t test.

4) Determine the critical values that divide the rejection and nonrejection regions

  • For ฮฑ = 0.05 the critical t values are 2.0639
    • ฮฑ๋Š” ์–‘ ๋์˜ ์˜ค๋ฅ˜๊ฐ’์„ ํ•ฉํ•ฉ ๊ฐ’์ด๋‹ˆ ํ•œ์ชฝ ์˜ ๊ฐ’์€ ฮฑ/2= 0.025์ด๋‹ค.(ฮฑ๊ฐ’์€ ํ˜„์‹ค์€ ํ•™์ž๊ฐ€ ๊ฒฐ์ • ์šฐ๋ฆฌ๋Š” ๋ฌธ์ œ์—์„œ ์คŒ)
    • ๊ทธ๋Ÿฌ๋ฏ€๋กœ ์ด 0.025๋ฅผ t-table์—์„œ ์ฐพ์œผ๋ฉด 2.0639์ด๋‹ค

5) Collect data and compute the value of the test statistic

  • Suppose the sample results are n = 25, \(x ฬ…\) = 172.50 , S = 15.4
  • So the test statistic is:
    image

6) Make the statistical decision and state the managerial conclusion.
image โžก๏ธ Since \(t_{STAT}\) = 1.46 < 2.0639, Do NOT reject the null hypothesis and ๐Ÿ“Œconclude there is insufficient evidence๐Ÿ“Œ that true mean cost is different from $168

๐Ÿ“Œconclude there is sufficient evidence๐Ÿ“Œ: reject the null hypothesis
๐Ÿ“Œconclude there is insufficient evidence๐Ÿ“Œ: Do NOT reject the null hypothesis

ํ™•๋ฅ ์€ ์ด๋ ‡๊ฒŒ ํ‘œํ˜„ํ•œ๋‹ค๋Š” ๊ฒƒ์— ์ฃผ์˜ํ•˜์ž!!



Mathematics Share Tweet +1