Presentation is loading. Please wait.

Presentation is loading. Please wait.

Chapter 6 The Standard Deviation as a Ruler and the Normal Model.

Similar presentations


Presentation on theme: "Chapter 6 The Standard Deviation as a Ruler and the Normal Model."— Presentation transcript:

1

2 Chapter 6 The Standard Deviation as a Ruler and the Normal Model

3 Comparing Quantitative Variables  Example 1: Last season (2006) Barry Bonds hit 26 home runs. Also last season (2006) Alex Rodriquez hit 35 home runs. Who had the better season?

4 Comparing Quantitative Variables  Example 2: I am 67 inches tall. My husband is 68 inches tall. Who is taller?

5 Standardizing Observations  y = observation of quantitative variable  How does the value of y relate to the mean value?  How does the value of y for this quantitative variable relate to another observation of a different quantitative variable.

6 Standardizing Variables  z has no units (just a number)  Puts observations on same scale. Mean (center) at 0. Standard deviation (spread) of 1.  Does not change overall shape of the distribution.

7 Standardizing Variables  z = # of standard deviations observation is away from mean. Negative z – observation is below mean.  Ex. z = -2  Ex. z = -0.5 Positive z – observation is above mean.  Ex. z = 2  Ex. z = 0.5

8 Example 1  Barry Bonds HRs Per Season  Alex Rodriquez HRs Per Season

9 Example 1

10 Example 2  Height of women  Height of men

11 Example 2

12 Distributions and Standardizing  Standardizing Allows you to make comparisons of observations between different variables. Without the distribution information, you still don’t know anything about the percentile value of your observation. This percentile value depends on the distribution.

13 Distributions and Standardizing  One exception:  When the shape of the distribution is symmetric, unimodal and bell- shaped, the standardized value of the observation tells you the percentile value of the observation as well.  Distribution is called the NORMAL DISTRIBUTION

14

15 Height of 150 Stat 101 Women  Distribution Shape  ______________ Center around _________ Spread from __________________  Model with a Normal Distribution

16 Models  Approximations to reality.  No quantitative variable has exactly a normal distribution.  If distribution is close to a normal distribution, we gain by using the normal distribution.  Gain = ability to go back and forth between standardized values and percentiles, without using the data.

17 Normal Distributions  Bell Curve  Physical Characteristics Ex. _______________  Most important distribution in statistics.

18 Normal Distributions  Two parameters (not calculated) Mean μ (pronounced “meeoo”)  Locates center of curve  Splits curve in half Standard deviation σ (pronounced “sigma”)  Controls spread of curve  Ruler of distribution  Write as N( μ,σ)

19 Example – Height of Men

20 68-95-99.7 Rule for Normal Distributions.  Approx. 68% of observations are within 1 s.d. σ of the mean μ  For N(70,3) this is between ____ and _____.  For N(0,1) this is between _____ and ______.

21 68-95-99.7 Rule for Normal Distributions.  Approx. 95% of observations are within 2 s.d. σ of the mean μ  For N(70,3) this is between _____ and ______.  For N(0,1) this is between _____ and ______.

22 68-95-99.7 Rule  99.7% of observations are within 3 s.d. σ of the mean μ  For N(70,3) this is between _____ and _____.  For N(0,1) this is between _____ and _____.

23 Standard Normal Distribution  Puts all normal distributions on same scale. z has center (mean) at 0 z has spread (standard deviation) of 1

24 Standard Normal Distribution  z = # of standard deviations away from mean μ Negative z = number is below the mean Positive z = number is above the mean  Written as N(0,1)

25

26 Standardizing Y is N(70,3). Standardize y = 68.

27 Standardizing Y is N(70,3). Standardize y = 74.

28 Normal Values Table  Going between standard values and percentiles on the normal distribution  Table gives amount or area of curve below a particular standardized value z. (the percentile for the value z) z values range from –3.90 to 3.90 Row – ones and tenths place for z. Column – hundredths place for z.

29 Area (z < -1.50)

30 Area (z < 1.98)

31 Area (z > -1.65)

32 Area (z > 0.73)

33 Area (0.5 < z < 1.4)

34 Area (-2.3 < z < -0.05)

35 Finding z from a given area

36

37

38

39

40

41 Example #1  The height of men is known to be normally distributed with mean 70 and standard deviation 3. Y is N(70,3)

42 Example #1A  What percent of men are shorter than 66 inches?

43 Example #1B  What percent of men are taller than 74 inches?

44 Example #1C  What percent of men are between 68 and 71 inches tall?

45 Example #1C

46 Example #1D  What are the values of the median, Q1 and Q3 for the height of men?

47 Example #1D – Q1

48 Example #1D – Q3

49 Example #2  Scores on SAT verbal are known to be normally distributed with mean 500 and standard deviation 100.  X is N(500,100)

50 Example #2A  Your score was 650 on the SAT verbal test. What percentage of people scored better?

51 Example #2B  What would you have to score to be in the top 5% of people taking the SAT verbal?

52 Example #3  Cereal boxes are labeled 16 oz. The boxes are filled by a machine. The amount the machine fills is normally distributed with mean 16.3 oz and standard deviation 0.2 oz.

53 Example #3A  What is the probability a box of cereal is underfilled?  Underfilling means having less than 16 oz.

54 Example #3B  A consumer group wants to the company to change the mean amount of cereal the machine fills so that only 3% of boxes are underfilled. What do we need to change the mean to?

55 Example #3B

56 Example #3C  Company president feels that is too much cereal to put in each box. She wants to set the mean weight on the machine to 16.2, but only have 3% of the boxes underfilled.  How??

57 Example #3C


Download ppt "Chapter 6 The Standard Deviation as a Ruler and the Normal Model."

Similar presentations


Ads by Google