Chapter 10: Basics of Confidence Intervals

Slides:



Advertisements
Similar presentations
CHAPTER 14: Confidence Intervals: The Basics
Advertisements

Inferential Statistics & Hypothesis Testing
Objectives (BPS chapter 24)
1 Copyright © 2010, 2007, 2004 Pearson Education, Inc. All Rights Reserved. Section 7.3 Estimating a Population mean µ (σ known) Objective Find the confidence.
ProportionMisc.Grab BagRatiosIntro.
The standard error of the sample mean and confidence intervals
Chapters 9 (NEW) Intro to Hypothesis Testing
BHS Methods in Behavioral Sciences I
8 - 10: Intro to Statistical Inference
Basic Biostat8: Intro to Statistical Inference1. In Chapter 8: 8.1 Concepts 8.2 Sampling Behavior of a Mean 8.3 Sampling Behavior of a Count and Proportion.
BPS - 3rd Ed. Chapter 131 Confidence intervals: the basics.
Chapter 12 Inferring from the Data. Inferring from Data Estimation and Significance testing.
The Sampling Distribution Introduction to Hypothesis Testing and Interval Estimation.
Introduction to Statistical Inference Chapter 11 Announcement: Read chapter 12 to page 299.
PARAMETRIC STATISTICAL INFERENCE
Instructor Resource Chapter 5 Copyright © Scott B. Patten, Permission granted for classroom use with Epidemiology for Canadian Students: Principles,
© 2008 McGraw-Hill Higher Education The Statistical Imagination Chapter 10. Hypothesis Testing II: Single-Sample Hypothesis Tests: Establishing the Representativeness.
Chapter 14Introduction to Inference1 Chapter 14 Introduction to Inference.
The Practice of Statistics Third Edition Chapter 10: Estimating with Confidence Copyright © 2008 by W. H. Freeman & Company Daniel S. Yates.
June 16. In Chapter 8: 8.1 Concepts 8.2 Sampling Behavior of a Mean 8.3 Sampling Behavior of a Count and Proportion.
1 Chapter 10: Introduction to Inference. 2 Inference Inference is the statistical process by which we use information collected from a sample to infer.
Introduction to Inferential Statistics Statistical analyses are initially divided into: Descriptive Statistics or Inferential Statistics. Descriptive Statistics.
Chapter 10: Basics of Confidence Intervals
BPS - 3rd Ed. Chapter 131 Confidence Intervals: The Basics.
Statistical Inference for the Mean Objectives: (Chapter 9, DeCoursey) -To understand the terms: Null Hypothesis, Rejection Region, and Type I and II errors.
Lecture PowerPoint Slides Basic Practice of Statistics 7 th Edition.
Chapter 10: Confidence Intervals
: An alternative representation of level of significance. - normal distribution applies. - α level of significance (e.g. 5% in two tails) determines the.
© 2008 McGraw-Hill Higher Education The Statistical Imagination Chapter 8. Parameter Estimation Using Confidence Intervals.
1 Probability and Statistics Confidence Intervals.
10.1 – Estimating with Confidence. Recall: The Law of Large Numbers says the sample mean from a large SRS will be close to the unknown population mean.
Statistical Inference for the Mean Objectives: (Chapter 8&9, DeCoursey) -To understand the terms variance and standard error of a sample mean, Null Hypothesis,
16/23/2016Inference about µ1 Chapter 17 Inference about a Population Mean.
Inference: Conclusion with Confidence
CHAPTER 8 Estimating with Confidence
Introduction For inference on the difference between the means of two populations, we need samples from both populations. The basic assumptions.
More on Inference.
Inference for the Mean of a Population
ECO 173 Chapter 10: Introduction to Estimation Lecture 5a
Confidence Intervals with Means
Inference: Conclusion with Confidence
Chapter 8: Inference for Proportions
Week 10 Chapter 16. Confidence Intervals for Proportions
Tests of significance: The basics
ECO 173 Chapter 10: Introduction to Estimation Lecture 5a
Statistics in Applied Science and Technology
Introduction to Inferential Statistics
More on Inference.
Ch. 8 Estimating with Confidence
Statistical Inference for the Mean Confidence Interval
Data Analysis and Statistical Software I ( ) Quarter: Autumn 02/03
Introduction to Inference
CHAPTER 14: Confidence Intervals The Basics
ESTIMATION
Elementary Statistics
CHAPTER 22: Inference about a Population Proportion
Inference on Proportions
Essential Statistics Introduction to Inference
The Practice of Statistics in the Life Sciences Fourth Edition
Test of Hypothesis Art of decision making.
Chapter 10: Basics of Confidence Intervals
CHAPTER 8 Estimating with Confidence
Intro to Confidence Intervals Introduction to Inference
Chapter 8: Estimating With Confidence
S.M.JOSHI COLLEGE,HADAPSAR Basics of Hypothesis Testing
Comparing Two Proportions
Chapter 8: Confidence Intervals
5: Introduction to estimation
BUS-221 Quantitative Methods
Presentation transcript:

Chapter 10: Basics of Confidence Intervals December 18 12/31/2018Basic Biostat 10: Intro to Confidence Intervals

In Chapter 10: 10.1 Introduction to Estimation 12/31/2018 In Chapter 10: 10.1 Introduction to Estimation 10.2 Confidence Interval for μ (σ known) 10.3 Sample Size Requirements 10.4 Relationship Between Hypothesis Testing and Confidence Intervals 12/31/2018 Basic Biostat

Statistical Inference Recall the goal of statistical inference: using statistics calculated in the sample We want to learn about population parameters… Statistical inference is the logical process by which we make sense of numbers. It is how we generalize from the particular to the general. This is an important scientific activity. Consider a study that wants to learn about the prevalence of a asthma in a population. We draw a SRS from the population and find that 3 of the 100 individuals in the sample have asthma. The prevalence in the sample is 3%. However, are still uncertain about the prevalence of asthma in the population; the next SRS from the same population may have fewer or more cases. How do we deal with this element of chance introduced by sampling? A similar problem occurs when we do an experiment Each time we do an experiment, we expect different results due to chance. How do we deal with this chance variability? Our first task is to distinguish between parameters and statistics. Parameters are the population value. Statistics are from the sample. The statistics will vary from sample to sample: they are random variables. In contrast, the parameters are invariable; they are constants. To help draw this distinction, we use different symbols for parameters and statistics. For example, we use “mu” to represent the population mean (parameter) and “xbar” to represent the sample mean (statistic). 12/31/2018

Recall: We introduce estimation concepts with the The distinction between a sample statistic (e.g., sample mean “x-bar”) and population parameter (e.g., population mean µ) The two forms of statistical inference: Hypothesis testing (Introduced in Ch 9) Estimation (Introduced in this chapter) We introduce estimation concepts with the the one-sample z CI for µ Statistical inference is the logical process by which we make sense of numbers. It is how we generalize from the particular to the general. This is an important scientific activity. Consider a study that wants to learn about the prevalence of a asthma in a population. We draw a SRS from the population and find that 3 of the 100 individuals in the sample have asthma. The prevalence in the sample is 3%. However, are still uncertain about the prevalence of asthma in the population; the next SRS from the same population may have fewer or more cases. How do we deal with this element of chance introduced by sampling? A similar problem occurs when we do an experiment Each time we do an experiment, we expect different results due to chance. How do we deal with this chance variability? Our first task is to distinguish between parameters and statistics. Parameters are the population value. Statistics are from the sample. The statistics will vary from sample to sample: they are random variables. In contrast, the parameters are invariable; they are constants. To help draw this distinction, we use different symbols for parameters and statistics. For example, we use “mu” to represent the population mean (parameter) and “xbar” to represent the sample mean (statistic). 12/31/2018

Estimating µ, σ known Objective: to estimate the value of population mean µ under these conditions Simple Random Sample (SRS) Population Normal or large sample The value of σ is known The value of μ is NOT known Statistical inference is the logical process by which we make sense of numbers. It is how we generalize from the particular to the general. This is an important scientific activity. Consider a study that wants to learn about the prevalence of a asthma in a population. We draw a SRS from the population and find that 3 of the 100 individuals in the sample have asthma. The prevalence in the sample is 3%. However, are still uncertain about the prevalence of asthma in the population; the next SRS from the same population may have fewer or more cases. How do we deal with this element of chance introduced by sampling? A similar problem occurs when we do an experiment Each time we do an experiment, we expect different results due to chance. How do we deal with this chance variability? Our first task is to distinguish between parameters and statistics. Parameters are the population value. Statistics are from the sample. The statistics will vary from sample to sample: they are random variables. In contrast, the parameters are invariable; they are constants. To help draw this distinction, we use different symbols for parameters and statistics. For example, we use “mu” to represent the population mean (parameter) and “xbar” to represent the sample mean (statistic). 12/31/2018

Estimating µ Two forms of estimation Point estimation ≡ most likely value of parameter µ (i.e., sample mean x-bar) Interval estimate ≡ the sample mean is surrounded with a margin of error to create a confidence interval (CI) 12/31/2018

(1 – α)100% Level of Confidence 12/31/2018

Common Levels of Confidence Confidence level 1 – α Alpha level α Z value z1–(α/2) .90 .10 1.645 .95 .05 1.960 .99 .01 2.576 12/31/2018

(1 – α)100% CI for µ margin of error m where: 12/31/2018

95% CI for µ (Example) Body weights of 20-29-year-old males Unknown μ, σ = 40 SRS of n = 64  calculate x-bar =183 margin of error m We have 95% confidence µ is in this interval 12/31/2018

99% CI for µ (Example) Body weights of 20-29-year-old males Unknown μ, σ = 40 SRS of n = 64  sample mean x-bar =183 margin of error m We have 99% confidence µ is in this interval 12/31/2018

How 95% CIs behave 12/31/2018

How CIs behave (cont.) The curve represents the sampling distribution of the mean Five 95% CIs for µ from the sampling distribution are shown below the curve The third CI failed to capture μ 12/31/2018

Sample Size Requirements How large a sample is need for a (1 – α)100% CI for µ with margin of error m? Examples (next slide) use these assumptions: σ = 40 95% confidence  z1–.05/2 = z.975 = 1.96 Varying m 12/31/2018

Examples: Sample Size Requirements Round-up to next integer so m no greater than stated Smaller m requires larger n Square root law: quadruple n to double precision 12/31/2018

10.4 Relation Between Testing and Confidence Intervals Rule: Reject H0 at the α level for significance when μ0 falls outside the (1−α)100% CI. Illustrations: Next slide 12/31/2018

Example: Testing and CIs Illustration: Test H0: μ = 180 This CI excludes 180 Reject H0 at α =.05 Retain H0 at α =.01 This CI includes 180 12/31/2018