2.4.10_Lec 8

2.4.10_Lec 8 - Lecture 8 First Quarter Review 1 Lecture 8 Outline 1st Quarter Review 1 The Scientific Method 2 Biostatistics paradigm paradigm

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Lecture 8 First Quarter Review 1 Lecture 8 Outline – 1st Quarter Review 1. The Scientific Method 2 Biostatistics paradigm 2. Biostatistics paradigm Variables, measurement Inter-relationships 3. Exploratory data analysis 4. Probability concepts 5. Probability distributions Binomial Poisson •N o r m a l 6. Sampling and Sampling distributions 2
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 The Scientific Method • The scientific method involves competing hypotheses about a natural phenomenon (the truth ”) • Data provide evidence in support of one or more hypothesis • Biostatistics uses data to draw inferences about the truth 3 TheRo leo fB ios ta t is t icsin Public Health 1. Generate hypotheses about the “truth” 2. Design a study; collect data 3. Descriptive statistics - Look at the data 4. Statistical inference • Discover patterns amidst variability • Make an inference about the unknown truth based on the observed data 4
Background image of page 2
3 Biostatistics Paradigm 1. Variable - a characteristic taking on different values • “Random” variable: values arise partly as a result of chance 2. Response variables vs. explanatory variables 3. Tendency for certain values of one variable to occur together with certain values of another variable variable • Conditional probabilities • Relative risk - “risk ratio” 5 Types of Variables 1. Quantitative : “amount” Discrete (gaps) vs. continuous 2. Qualitative : “attribute” Nominal (no “order”) vs. ordinal 6
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4 Bias and Variance 1. Variation - differences among measurements Natural” vs. “measurement” 2. Bias and Variance Bias : average measurement – truth Variance : variation about the average 7 Descriptive Statistics 1 Collecting data 1. Collecting data 2. Organizing and summarizing data 3. Analyzing data 4. Interpreting data 8
Background image of page 4
5 “Exploratory Data Analysis” Methods for organizing and visualizing data Stem and leaf display (distribution, shape) Box and whisker plots (distribution, quartiles, variability, outliers) 9 Stem and Leaf Display of Children’ s Weights (lbs) Stem Leaf 10-19 1 02 20-29 2 1223 3 2456 43 4 5 8 5 3459 60-69 6 04 40-49 30-39 50-59 Sample size n = 20 minimum = 10 maximum = 64 10
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
6 Example: Quartiles of Children’s Weights (lbs) •Q 2 = P 50 = median = middle observation = (36+43)/2 = 39.5 lbs 1 = P 25 = middle observation of lower 50% = (22+23)/2 = 22.5 lbs Q 3 = P 75 = middle observation of upper 50% = (53+54)/2 = 53.5 lbs 11 Boxplot of Children’ s Weights (lbs) max =64 Q 3 = 53.5 60 - 50 median = Q 2 = 39.5 Q 1 = 22.5 min= 10 50 - 40 - 30 - 20 - 10 - min 10 0 - 12
Background image of page 6
7 Boxplot of Children’ s Weights (lbs) (continued) Check for outliers: Upper fence = Q 3 + 1.5 (Q 3 - Q 1 ) = 53.5 + 1.5(53.5 - 22.5) = 100 Lower fence = Q 1 - 1.5 (Q 3 - Q 1 ) = 22.5 - 1.5(53.5 - 22.5) = -24 No outliers FENCES ARE NEVER SHOWN ON THE BOX PLOT UNLESS THEY ARE EQUALS
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 8
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/24/2010 for the course BIOS 600 taught by Professor Staff during the Spring '08 term at UNC.

Page1 / 22

2.4.10_Lec 8 - Lecture 8 First Quarter Review 1 Lecture 8 Outline 1st Quarter Review 1 The Scientific Method 2 Biostatistics paradigm paradigm

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online