How confident are we in the estimation of mean/proportion we have calculated?

Slides:



Advertisements
Similar presentations
EPIDEMIOLOGY AND BIOSTATISTICS DEPT Esimating Population Value with Hypothesis Testing.
Advertisements

Nemours Biomedical Research Statistics March 19, 2009 Tim Bunnell, Ph.D. & Jobayer Hossain, Ph.D. Nemours Bioinformatics Core Facility.
Section 7.1 Hypothesis Testing: Hypothesis: Null Hypothesis (H 0 ): Alternative Hypothesis (H 1 ): a statistical analysis used to decide which of two competing.
4-1 Statistical Inference The field of statistical inference consists of those methods used to make decisions or draw conclusions about a population.
IENG 486 Statistical Quality & Process Control
Chapter 9 Hypothesis Testing.
PY 427 Statistics 1Fall 2006 Kin Ching Kong, Ph.D Lecture 6 Chicago School of Professional Psychology.
BCOR 1020 Business Statistics
Statistical Analysis. Purpose of Statistical Analysis Determines whether the results found in an experiment are meaningful. Answers the question: –Does.
2 Accuracy and Precision Accuracy How close a measurement is to the actual or “true value” high accuracy true value low accuracy true value 3.
Statistical Inference Dr. Mona Hassan Ahmed Prof. of Biostatistics HIPH, Alexandria University.
1. Statistics: Learning from Samples about Populations Inference 1: Confidence Intervals What does the 95% CI really mean? Inference 2: Hypothesis Tests.
AM Recitation 2/10/11.
Hypothesis testing. Want to know something about a population Take a sample from that population Measure the sample What would you expect the sample to.
1/2555 สมศักดิ์ ศิวดำรงพงศ์
4-1 Statistical Inference The field of statistical inference consists of those methods used to make decisions or draw conclusions about a population.
Ch 10 Comparing Two Proportions Target Goal: I can determine the significance of a two sample proportion. 10.1b h.w: pg 623: 15, 17, 21, 23.
Statistical Analysis Statistical Analysis
14. Introduction to inference
Comparing Two Population Means
Jan 17,  Hypothesis, Null hypothesis Research question Null is the hypothesis of “no relationship”  Normal Distribution Bell curve Standard normal.
1 Power and Sample Size in Testing One Mean. 2 Type I & Type II Error Type I Error: reject the null hypothesis when it is true. The probability of a Type.
Populations, Samples, Standard errors, confidence intervals Dr. Omar Al Jadaan.
Topics: Statistics & Experimental Design The Human Visual System Color Science Light Sources: Radiometry/Photometry Geometric Optics Tone-transfer Function.
Education Research 250:205 Writing Chapter 3. Objectives Subjects Instrumentation Procedures Experimental Design Statistical Analysis  Displaying data.
Statistical Decision Making. Almost all problems in statistics can be formulated as a problem of making a decision. That is given some data observed from.
Maximum Likelihood Estimator of Proportion Let {s 1,s 2,…,s n } be a set of independent outcomes from a Bernoulli experiment with unknown probability.
Hypothesis Testing Hypothesis Testing Topic 11. Hypothesis Testing Another way of looking at statistical inference in which we want to ask a question.
Biostatistics Class 6 Hypothesis Testing: One-Sample Inference 2/29/2000.
1 Chapter 10: Introduction to Inference. 2 Inference Inference is the statistical process by which we use information collected from a sample to infer.
1 ConceptsDescriptionHypothesis TheoryLawsModel organizesurprise validate formalize The Scientific Method.
Lecture 17 Dustin Lueker.  A way of statistically testing a hypothesis by comparing the data to values predicted by the hypothesis ◦ Data that fall far.
Lecture 16 Section 8.1 Objectives: Testing Statistical Hypotheses − Stating hypotheses statements − Type I and II errors − Conducting a hypothesis test.
Essential Question:  How do scientists use statistical analyses to draw meaningful conclusions from experimental results?
통계적 추론 (Statistical Inference) 삼성생명과학연구소 통계지원팀 김선우 1.
2 Accuracy and Precision Accuracy How close a measurement is to the actual or “true value” high accuracy true value low accuracy true value 3.
McGraw-Hill/Irwin Copyright © 2007 by The McGraw-Hill Companies, Inc. All rights reserved. Chapter 8 Hypothesis Testing.
Statistics 101 Chapter 10 Section 2. How to run a significance test Step 1: Identify the population of interest and the parameter you want to draw conclusions.
1 Chapter 8 Introduction to Hypothesis Testing. 2 Name of the game… Hypothesis testing Statistical method that uses sample data to evaluate a hypothesis.
Chapter 20 Testing Hypothesis about proportions
Medical Statistics as a science
Introduction to Inference: Confidence Intervals and Hypothesis Testing Presentation 8 First Part.
Introduction to Inference: Confidence Intervals and Hypothesis Testing Presentation 4 First Part.
CHAPTER 15: Tests of Significance The Basics ESSENTIAL STATISTICS Second Edition David S. Moore, William I. Notz, and Michael A. Fligner Lecture Presentation.
Chapter 8 Parameter Estimates and Hypothesis Testing.
Fall 2002Biostat Statistical Inference - Confidence Intervals General (1 -  ) Confidence Intervals: a random interval that will include a fixed.
Lecture PowerPoint Slides Basic Practice of Statistics 7 th Edition.
Ex St 801 Statistical Methods Inference about a Single Population Mean.
Fall 2002Biostat Statistical Inference - Proportions One sample Confidence intervals Hypothesis tests Two Sample Confidence intervals Hypothesis.
Stats Lunch: Day 3 The Basis of Hypothesis Testing w/ Parametric Statistics.
1 URBDP 591 A Lecture 12: Statistical Inference Objectives Sampling Distribution Principles of Hypothesis Testing Statistical Significance.
Hypothesis Testing Errors. Hypothesis Testing Suppose we believe the average systolic blood pressure of healthy adults is normally distributed with mean.
Introduction to inference Tests of significance IPS chapter 6.2 © 2006 W.H. Freeman and Company.
Introduction Suppose that a pharmaceutical company is concerned that the mean potency  of an antibiotic meet the minimum government potency standards.
Statistical Analysis II Lan Kong Associate Professor Division of Biostatistics and Bioinformatics Department of Public Health Sciences December 15, 2015.
© Copyright McGraw-Hill 2004
Copyright © 2013, 2009, and 2007, Pearson Education, Inc. Chapter 10 Comparing Two Groups Section 10.1 Categorical Response: Comparing Two Proportions.
P-values and statistical inference Dr. Omar Aljadaan.
Statistical Inference Statistical inference is concerned with the use of sample data to make inferences about unknown population parameters. For example,
+ Unit 6: Comparing Two Populations or Groups Section 10.2 Comparing Two Means.
SAMPLING DISTRIBUTION OF MEANS & PROPORTIONS. SAMPLING AND SAMPLING VARIATION Sample Knowledge of students No. of red blood cells in a person Length of.
Learning Objectives After this section, you should be able to: The Practice of Statistics, 5 th Edition1 DESCRIBE the shape, center, and spread of the.
Uncertainty and confidence Although the sample mean,, is a unique number for any particular sample, if you pick a different sample you will probably get.
CHAPTER 15: Tests of Significance The Basics ESSENTIAL STATISTICS Second Edition David S. Moore, William I. Notz, and Michael A. Fligner Lecture Presentation.
Hypothesis Testing and Statistical Significance
Statistical Inference for the Mean Objectives: (Chapter 8&9, DeCoursey) -To understand the terms variance and standard error of a sample mean, Null Hypothesis,
Copyright © 2013, 2009, and 2007, Pearson Education, Inc. 1 FINAL EXAMINATION STUDY MATERIAL III A ADDITIONAL READING MATERIAL – INTRO STATS 3 RD EDITION.
Statistical Decision Making. Almost all problems in statistics can be formulated as a problem of making a decision. That is given some data observed from.
Chapter 9 Introduction to the t Statistic
Hypothesis Testing Summer 2017 Summer Institutes.
Presentation transcript:

How confident are we in the estimation of mean/proportion we have calculated?

2

3

Measures of precision: 1. Standard error of mean, SEM Standard error of proportion, SE(p) 2. Confidence interval for mean Confidence interval for proportion

Standard error of mean, SEM Number of patients Standard deviation, SD SEM is smaller (estimate is more precise): the larger is N (number of patients) the smaller is SD (dispersion of data)

7

95% confidence interval for mean, 95% CI  Together with SEM, 95% CI is also the measure of precision  Unlike SEM, 95% CI also estimates accuracy of the result ie. 95% is accurate that interval includes true (population) mean)

95% confidence interval for mean If we draw a 100 samples from our population we would find the true population value within 95% confidence interval in 95 samples samples

Critical values for 90%, 95% and 99% level of confidence 90% CI => mean ± 1.65 SEM 95% CI => mean ± 1.96 SEM 99% CI => mean ± 2.58 SEM Level of Confidence - Critical Value 0.75, or 75% , or 80% , or 85% , or 90% , or 95% , or 98% , or 99% 2.58

Example 1 The average systolic BP before treatment in study A, of a group of 100 hypertensive patients, was 170 mmHg. After treatment with the new drug the mean BP dropped by 20 mmHg. If the 95% CI is 15–25, this means: 11 we can be 95% confident that the true effect of treatment is to lower the BP by 15–25 mmHg.

Example 2 In study B 50 patients were treated with the same drug, also reducing their mean BP by 20 mmHg, but with a wider 95% CI of -5 to +45. This CI includes zero (no change). This means: 12 there is more than a 5% chance that there was no true change in BP, and that the drug was actually ineffective..

Example 3 – Meta analysis Fig. Plot of 5 studies of a new antihypertensive drug. 1.Which study showed the greatest change? 2.Did all the studies show change in favour of the intervention? 3.Were the changes statistically significant?

Watch out for... The size of a CI is related to the sample size of the study. Larger studies usually have a narrower CI. 14

Proportion 1. Standard error of proportion, SE(p) SE( p) = √(p(1 – p)/n) 2. Confidence interval for proportion

The standard deviation describes the variability of a sample; does not describe the sample The standard error of the mean (SEM) does not describe the sample but uncertainty describes the uncertainty of how the sample mean represents the population mean.

SD CI Standard deviation tells us about the variability (spread) in a sample. The CI tells us the range in which the true value (the mean if the sample were infinitely large) is likely to be.

Krebs NF, Westcott JE, Culbertson DL et. al. Comparison of complementary feeding strategies to meet zinc requirements of older breastfed infants. Am J Clin Nutr. 2012; 96:30-35 “Mean (±SEM) total absorbed zinc amounts were 0.80 ± 0.08, 0.71 ± 0.09, and 0.52 ± 0.05 mg/d for the: meat, iron-and-zinc-fortified infant cereal, and whole-grain, iron-only-fortified infant cereal groups of infants.” SEMCI Meat Fe&Zn Fe

TRUE or FALSE What does a small standard error tell us about the sample estimate of the mean? That it is highly variable That the population standard deviation may be small That the sample size is probably small That it is imprecise

TRUE or FALSE What will tend to make the standard error larger? A small variance A large standard deviation Imprecise data Inaccurate data 20

21

Statistics: Learning from Samples about Populations Inference 1: Confidence Intervals What does the 95% CI really mean? Inference 2: Hypothesis Tests What does a p-value really mean? When to use which test? Statistical Inference: Brief Overview

In epidemiological studies: Is there a relationship between a variable of interest and an outcome of interest? Ie. smoking and lung cancer Stress and thyroid cancer In clinical trails: Is experimental therapy more effective than standard therapy or placebo ? Examples of hypothesis testing in medical research

Hypothesis testing = testing of statistical hypothesis 24

Statistical hypothesis Statements about population parameter values. Null hypothesis (H 0 ) says a parameter is unchanged from a default, pre-specified value; and Alternative hypothesis (H 1 ) says parameter has a value incompatible with H 0 25

Make appropriate statistical hypotheses : Assumption: Mean cholesterol in hypertensive men is equal to mean cholesterol in male general population (20-74 years old). In the year old male population the mean serum cholesterol is 211 mg/ml with a standard deviation of 46 mg/ml Example: Hypertension and Cholesterol

no Null hypothesis => no difference between treatments  H 0 : μ hypertensive = μ general population  H 0 : μ hypertensive = 211 mg/ml ◦ μ = population mean of serum cholesterol ◦ Mean cholesterol for hypertensive men = mean for general male population Alternative hypothesis  H A : μ hypertensive ≠ μ general population  H A : μ hypertensive ≠ 211 mg/ml Example: Hypertension and Cholesterol

Null and alternative hypothesis 28 Two-sided tests One-sided tests

How to choose one or the other? 29

1.Assume H 0 is true i.e. believe results are a matter of chance 2.Quantify how far away are data from being consistent with H 0 by evaluating quantity called a test statistic 3. Assess probability of results at least this extreme - call this the p-value of the test 4. Reject H 0 (believe H 1 ) if this p-value is small or keep H 0 (do not believe H 1 ) otherwise

Interpretation of P-value (0.05) P>=0.05 Significant difference between the treatments Null hypothesis is rejected, alternative is accepted P<0.05 5% No difference between the treatments (observed difference having happened by chance) Null hypothesis is accepted

P-value The P value gives the probability of observed and more extreme difference having happened by chance. P = means that the probability of the difference having happened by chance is 0.5 in 1, or 1 in 2. P = 0.05 means that the probability of the difference having happened by chance is 0.05 in 1, i.e. 1 in

P-value The lower the P value, the less likely it is that the difference happened by chance and so the higher the significance of the finding. P = 0.01 is often considered to be “highly significant”. It means that the difference will only have happened by chance 1 in 100 times. This is unlikely, but still possible. 33

Chance rning/summerschools/lo_chanceSimulator/lo_chance Simulator.html rning/summerschools/lo_chanceSimulator/lo_chance Simulator.html 34

Example 1 Out of 50 new babies on average 25 will be girls, sometimes more, sometimes less. Say there is a new fertility treatment and we want to know whether it affects the chance of having a boy or a girl. Null hypothesis –the treatment does not alter the chance of having a girl. 35

Example 1 Null hypothesis –the treatment does not alter the chance of having a girl. Out of the first 50 babies resulting from the treatment, 15 are girls. We need to know the probability that this just happened by chance, i.e. did this happen by chance or has the treatment had an effect on the sex of the babies? P=

Example 1 The P value in this example is This means the result would only have happened by chance in in 1 (or 1 in 140) times if the treatment did not actually affect the sex of the baby. This is highly unlikely, so we can reject our hypothesis and conclude that the treatment probably does alter the chance of having a girl. 37

Example 2 Patients with minor illnesses were randomized to see either Dr Smith or Dr Jones. Dr Smith ended up seeing 176 patients in the study whereas Dr Jones saw 200 patients. 38

Example 2 Patients with minor illnesses were randomized to see either Dr Smith or Dr Jones. Dr Smith ended up seeing 176 patients in the study whereas Dr Jones saw 200 patients (Table 2). 39

1. Type of data (type of variable)? 2. Number of groups? 3. Related or independent groups? 4. Normal or asymmetric distribution? How to choose the appropriate statistical test?

41 Numerical

Make appropriate statistical hypotheses : Mean cholesterol in hypertensive men is 220 mg/ml with a standard deviation of 39 mg/ml. In the year old male population the mean serum cholesterol is estimated to 211 mg. Example: Hypertension and Cholesterol

Hypothesis vs Statictical Hypothesis Alcohol intake increases driver’s reaction time. Mean reaction time in examinees drinking alcohol is greater than in nondrinking controls. Research hypothesisStatistical hypothesis