MAT140: Applied Statistical Methods Summary of Calculating Confidence Intervals and Sample Sizes for Estimating Parameters

Similar documents
5.1 Identifying the Target Parameter

4. Continuous Random Variables, the Pareto and Normal Distributions

Review. March 21, S7.1 2_3 Estimating a Population Proportion. Chapter 7 Estimates and Sample Sizes. Test 2 (Chapters 4, 5, & 6) Results

Chapter 8 Hypothesis Testing Chapter 8 Hypothesis Testing 8-1 Overview 8-2 Basics of Hypothesis Testing

3.4 Statistical inference for 2 populations based on two samples

Statistical Confidence Calculations

2 Sample t-test (unequal sample sizes and unequal variances)

Biostatistics: DESCRIPTIVE STATISTICS: 2, VARIABILITY

HYPOTHESIS TESTING: CONFIDENCE INTERVALS, T-TESTS, ANOVAS, AND REGRESSION

Week 4: Standard Error and Confidence Intervals

THE FIRST SET OF EXAMPLES USE SUMMARY DATA... EXAMPLE 7.2, PAGE 227 DESCRIBES A PROBLEM AND A HYPOTHESIS TEST IS PERFORMED IN EXAMPLE 7.

Confidence Intervals for Cp

Standard Deviation Estimator

One-Way ANOVA using SPSS SPSS ANOVA procedures found in the Compare Means analyses. Specifically, we demonstrate

Odds ratio, Odds ratio test for independence, chi-squared statistic.

Lecture Notes Module 1

Confidence Intervals for the Difference Between Two Means

How To Check For Differences In The One Way Anova

Point and Interval Estimates

Chapter Study Guide. Chapter 11 Confidence Intervals and Hypothesis Testing for Means

p ˆ (sample mean and sample

6.4 Normal Distribution

Two-Sample T-Tests Assuming Equal Variance (Enter Means)

Confidence Intervals for Cpk

Multiple-Comparison Procedures

Two-Sample T-Tests Allowing Unequal Variance (Enter Difference)

Probability Distributions

individualdifferences

One-Way Analysis of Variance

Summary of Formulas and Concepts. Descriptive Statistics (Ch. 1-4)

Testing Research and Statistical Hypotheses

Means, standard deviations and. and standard errors

Introduction to Analysis of Variance (ANOVA) Limitations of the t-test

Class 19: Two Way Tables, Conditional Distributions, Chi-Square (Text: Sections 2.5; 9.1)

Mean = (sum of the values / the number of the value) if probabilities are equal

Simple linear regression

Advanced Statistical Analysis of Mortality. Rhodes, Thomas E. and Freitas, Stephen A. MIB, Inc. 160 University Avenue. Westwood, MA 02090

Confidence Intervals for One Standard Deviation Using Standard Deviation

CURVE FITTING LEAST SQUARES APPROXIMATION

Unit 26 Estimation with Confidence Intervals

Need for Sampling. Very large populations Destructive testing Continuous production process

HYPOTHESIS TESTING (ONE SAMPLE) - CHAPTER 7 1. used confidence intervals to answer questions such as...

Simple Regression Theory II 2010 Samuel L. Baker

Calculating P-Values. Parkland College. Isela Guerra Parkland College. Recommended Citation

Estimation and Confidence Intervals

Characteristics of Binomial Distributions

Sample Paper for Research Methods. Daren H. Kaiser. Indiana University Purdue University Fort Wayne

Chapter 2. Hypothesis testing in one population

Chapter 5 Analysis of variance SPSS Analysis of variance

The correlation coefficient

Non-random/non-probability sampling designs in quantitative research

INTERNATIONAL STANDARD ON AUDITING 530 AUDIT SAMPLING

Having a coin come up heads or tails is a variable on a nominal scale. Heads is a different category from tails.

1. What is the critical value for this 95% confidence interval? CV = z.025 = invnorm(0.025) = 1.96

How Far is too Far? Statistical Outlier Detection

Final Exam Practice Problem Answers

HYPOTHESIS TESTING (ONE SAMPLE) - CHAPTER 7 1. used confidence intervals to answer questions such as...

Study Guide for the Final Exam

Regression Analysis: A Complete Example

WHERE DOES THE 10% CONDITION COME FROM?

MEASURES OF VARIATION

How To Write A Data Analysis

PowerScore Test Preparation (800)

Tests for One Proportion

Lesson 1: Comparison of Population Means Part c: Comparison of Two- Means

Recall this chart that showed how most of our course would be organized:

Curriculum Map Statistics and Probability Honors (348) Saugus High School Saugus Public Schools

2 GENETIC DATA ANALYSIS

Fairfield Public Schools

Tests for Two Proportions

Statistical estimation using confidence intervals

TImath.com. F Distributions. Statistics

IB Math Research Problem

Week 3&4: Z tables and the Sampling Distribution of X

A POPULATION MEAN, CONFIDENCE INTERVALS AND HYPOTHESIS TESTING

CHAPTER 11 CHI-SQUARE AND F DISTRIBUTIONS

1.5 Oneway Analysis of Variance

LAB 4 INSTRUCTIONS CONFIDENCE INTERVALS AND HYPOTHESIS TESTING

Confidence Intervals for Exponential Reliability

Variables Control Charts

CHI-SQUARE: TESTING FOR GOODNESS OF FIT

Factors affecting online sales

Using Stata for One Sample Tests

STRUTS: Statistical Rules of Thumb. Seattle, WA

CALCULATIONS & STATISTICS

EMPIRICAL FREQUENCY DISTRIBUTION

Stats Review Chapters 9-10

Independent t- Test (Comparing Two Means)

Confidence Intervals for Spearman s Rank Correlation

Regression with a Binary Dependent Variable

Chapter 7. Comparing Means in SPSS (t-tests) Compare Means analyses. Specifically, we demonstrate procedures for running Dependent-Sample (or

Solutions to Homework Problems for Basic Cost Behavior by David Albrecht

Two-sample inference: Continuous data

WEEK #23: Statistics for Spread; Binomial Distribution

Assignment 5 - Due Friday March 6

Statistics I for QBIC. Contents and Objectives. Chapters 1 7. Revised: August 2013

INTERNATIONAL STANDARD ON AUDITING 530 AUDIT SAMPLING AND OTHER MEANS OF TESTING CONTENTS

Confidence Intervals in Public Health

Transcription:

MAT140: Applied Statistical Methods Summary of Calculating Confidence Intervals and Sample Sizes for Estimating Parameters Inferences about a population parameter can be made using sample statistics for the following: 1. Proportion (percentage of population that possesses some characteristic or trait) 2. Mean (average value of whatever quantity is being measured for the population) 3. Variance (NOT standard deviation, although variance is used to work with standard deviation) A confidence interval (CI) for one of the parameters listed above is generally constructed through the following process: 1. Determine the corresponding statistic from a sample 2. Determine the range of values (upper and lower bounds) assumed to contain the true value of the population parameter at the stated level of confidence It should be noted that although following the above procedure is the general process for making inferences about a population parameter based on a sample statistic, each of the three parameters for which valid inferences can be made has its own unique formulas to use. Furthermore, obtaining the range of values that is hoped to contain the true value of the actual population parameter does not guarantee that the true value of the population parameter actually falls in that range. Related to confidence intervals is the concept of determining the minimum sample size necessary to ensure valid results, which is done simply by solving the pertinent formula for where applicable. The following variables and abbreviations are used at various times when performing calculations related to confidence intervals and, later on, hypothesis testing (which is covered in a future chapter): = population proportion ( is the complement of ; and ) = population mean = population variance = population standard deviation = sample proportion ( is the complement of ; and ) = sample mean = sample variance = sample standard deviation = sample size = confidence interval = margin of error (used for calculating for or ) = complement of confidence level associated with (for example, a confidence level means, which means ) = area in each tail for a confidence interval ( represents the middle range of values) = critical value in normal distribution for for or with known value of = critical value in distribution for for with unknown value of = degrees of freedom ( ) = critical value in distribution for lower bound of for (or ) = critical value in distribution for upper bound of for (or )

Procedure for Estimating a Population Proportion b. The conditions for binomial distribution are satisfied: i. Fixed number of trials ( is set) ii. Trials are independent (the outcome of any one trial has no effect on any other trial) iii. Exactly two categories of outcomes for each trial (success and failure) iv. Probabilities remain constant for each trial ( and do not change) c. There are at least successes and failures (equivalent to and ) 2. If not provided, calculate the value of the sample proportion : (Note: 4. Look up the value of in the table of values for the normal distribution 5. Calculate the margin of error : 6. Calculate the limits and state the for the population proportion in one of the following ways: a. Preferred method: b. c. ( of ( and margin of error, simply solve the equation for above for : [ ] Notes: 1. It is highly unlikely that there will be prior knowledge to provide a value for. In such instances, it is customary to use (and, therefore, ) in the calculation for. (If prior knowledge provides a value of to be used, then that should be used instead.) 2. Always round the value of up to the next highest integer if the value is not an integer.

Procedure for Estimating a Population Mean When Is Known Note: In general, this procedure is not used since it would be extremely unlikely that a value for would be known without also knowing the true value of since the calculation of depends on the value of, although rare cases may exist; the more practical approach for estimating is outlined in the next section of this packet. b. The value of the population standard deviation is known c. Either or both of the following conditions are met: i. The population is normally distributed ii. The sample size 2. If not provided, calculate the value of the sample mean 4. Look up the value of in the table of values for the normal distribution 5. Calculate the margin of error : 6. Calculate the limits and state the for the population mean in one of the following ways: a. Preferred method: b. c. ( of ( and margin of error, simply solve the equation for above for : [ ] Note: Always round the value of up to the next highest integer if the value is not an integer.

Procedure for Estimating a Population Mean When Is Not Known b. Either or both of the following conditions are met: i. The population is normally distributed ii. The sample size 2. If not provided, calculate the value of the sample mean 3. If not provided, calculate the value of the sample standard deviation 4. Determine the value of based on the stated confidence level: 5. Determine the number of degrees of freedom, : 6. Look up the value of in the table of values for the distribution 7. Calculate the margin of error : 8. Calculate the limits and state the for the population mean in one of the following ways: a. Preferred method: b. c. ( of ( and margin of error, it is generally acceptable to simply solve the equation for above for and use the value in the row labeled Large for degrees of freedom as the value of (this is equivalent to the value of used in the formula from the previous section in which the population standard deviation is known): [ ] Notes: 1. If statistics from a sample of known size are provided, the value of from the row for the corresponding number of degrees of freedom can be used, resulting in a slightly larger minimum necessary sample size which will theoretically provide more accurate results. 2. To obtain the greatest minimum necessary sample size using this approach, the preceding formula can be used with degree of freedom, although the resulting sample size will be significantly larger and may not be practical when formally gathering data. 3. If the population cannot be assumed to be at least reasonably close to normally distributed, calculating a minimum sample size becomes complex beyond the scope of this course. 4. Always round the value of up to the next highest integer if the value is not an integer.

Procedure for Estimating a Population Variance b. The population must be normally distributed regardless of sample size 2. If not provided, calculate the value of the sample standard deviation 4. Determine the number of degrees of freedom, : 5. Look up the values of and in the table of values for the distribution 6. Calculate the limits and state the for the population variance : ( ( 7. If the for the population standard deviation is desired, simply take square roots: ( ( Because the distribution depends on the number of degrees of freedom, and the number of degrees of freedom depends on the sample size, it is not possible to determine the minimum sample size necessary to guarantee valid results for a stated confidence level of ( and margin of error by simply solving the equation for above for. However, complex procedures do exist to determine such sample sizes. Since those procedures are beyond the scope of this course, it is sufficient to simply note that Table 7-2 on page 376 of the textbook provides required minimum sample sizes for many of the most common confidence levels and margins of error. When necessary throughout this course, it is sufficient to simply look up a required minimum sample size in that table.