PSCH 343; Statistical Methods In Behavior Science. Week Three Notes
PSCH 343; Statistical Methods In Behavior Science. Week Three Notes PSCH 343
Popular in Statistics Methods In Behavioral Science
Popular in Psychlogy
verified elite notetaker
This 9 page Class Notes was uploaded by Katie on Monday February 1, 2016. The Class Notes belongs to PSCH 343 at University of Illinois at Chicago taught by Liana Peter-Hagene in Spring 2016. Since its upload, it has received 29 views. For similar materials see Statistics Methods In Behavioral Science in Psychlogy at University of Illinois at Chicago.
Reviews for PSCH 343; Statistical Methods In Behavior Science. Week Three Notes
Report this Material
What is Karma?
Karma is the currency of StudySoup.
You can buy or earn more Karma at anytime and redeem it for class notes, study guides, flashcards, and more!
Date Created: 02/01/16
Instructor: Liana Peter-Hagene PSCH 343 Statistics Methods In Behavioral Science Week Three Notes Properties of the Normal Distribution (Z-scores) Inferential Statistics -We conduct studies on samples, but we draw conclusions about populations -Can we claim that the differences or relationships we found in our study represent differences or relationships in the “real world”? -Inferential statistics allow us to draw conclusions that go beyond data from a study Examples: 1. Is the enthusiasm for statistics experienced by people in this classroom representative of all UIC students? 2. A survey of 100 jurors shows more men than women voted guilty. Can we say these results represent all men and women jurors – even those who were not in the study? Population V. Sample Instructor: Liana Peter-Hagene -All people who go through CBT for anxiety versus 50 people in a clinical trial Sampling Methods Why Does Sampling Work? -We assume characteristics (data) are normally distributed in a population Normal curve: • Bell-shaped frequency distribution • Symmetrical, unimodal • Specific mathematical properties • Commonly found in nature Normal Distribution Properties -Specific mathematical properties Normal curve: Instructor: Liana Peter-Hagene -34% of scores between mean and 1 SD -14% of scores between 1 SD and 2 SDs -2% of scores beyond 2 SDs -The properties of normal distribution allow us to create standardized scores based on the raw scores, means, and SDs -These standardized scores are very informative and allow us to compare performance on different measures with different scales Z-Scores -A score tells little about how it relates to the whole distribution -David’s score on his stats exam was 45 -Linda’s score was 56 -Comparing a score to the mean tells whether it is above or below average -What if the mean of the test were 50? -David scored below the mean; Linda above the mean -What if the mean of the test were 60? -David and Linda scored below the mean -The SD helps determine how far below/above the mean a score is, compared to other scores M = 50, SD = 2 M = 50, SD = 5 Instructor: Liana Peter-Hagene -Z-scores tell us just that: How many standard deviations a score is below or above the mean • EXAM QUESTION: How can the exact same score get one student an A in one statistics class, and another student a C in another statistics class? Can this happen even if the two classes have the same mean? Z-scores help with comparing two people’s performance -Z-scores can also convert scores on different measure into the same metric so they can be compared. Instructor: Liana Peter-Hagene -Can literally allow us to compare apples and oranges Apple eating contest, apples eaten M = 27, SD = 5 Sam ate 35 apples Orange eating contest, oranges eaten M = 45, SD = 7 Maria ate 47 oranges Who did better – David in the apple eating contest or Alice in the orange eating contest? 1. Calculate Sam and Maria’s Z-scores based on their own distribution means and SDs 2. Compare the Z scores Answer, David did better. Z-Scores Help Compare One Person’s Scores On Two Measures Paula took a survey measuring life satisfaction. On the scale of job satisfaction, which had a mean of 25 and a standard deviation of 12, Sabrina scored 50. On the scale of personal life satisfaction, which had a mean of 55 and a standard deviation of 10, she scored 62. Is Paula more satisfied with her job, or her personal life? What % of scores will you find between – 1 SD and +1 SD in a Z distribution? Instructor: Liana Peter-Hagene Convert these scores to Z-scores and compute the M and SD of the Z-score distribution M = 5, SD = 2 1. Calculate Z scores 2. Calculate mean of Z scores. Is it 0? 3. Calculate deviation scores (Z-M ) –Zwhat do you notice? 4. Square and sum deviation scores 5. Divide by N = 5 6. You have the SD of the Z scores. Is it 1? Why We Use Z-Scores -The sign (+/-) tells us immediately whether a score is above or below the mean -The number tells us immediately how far the score is from the mean, in standard deviation units. We can use this information to assess % of scores above or below it -They are standardized scores that bring different scales to the same metric -Help us compare performance on different measures, for the same person or for different people Z-Scores Help Compare One Person’s Scores On Two Measures Paula took a survey measuring life satisfaction. On the scale of job satisfaction, which had a mean of 25 and a standard deviation of 12, Paula scored 50. On the scale of personal life satisfaction, which had a mean of 55 and a standard deviation of 10, she scored 62. Is Paula more satisfied with her job, or her personal life? Limitations Of Z-Scores 1. Because a person’s score is expressed relative to the group, the same person can have different z- scores when assessed in different samples Instructor: Liana Peter-Hagene If the absolute score is meaningful or of psychological interest, it will be obscured by transforming it to a relative metric. e.g., number of suicides/year in different countries number of correct responses on a math test Normal Distribution Properties And Z-Scores Normal Distribution And Probability -Probability: The expected relative frequency of an outcome; the proportion of successful outcomes to all outcomes Probability Example: Instructor: Liana Peter-Hagene How Does This Relate To The Normal Curve? -A test of knowledge about the environment is normally distributed. M = 50, SD = 10 Question: -If you were to pick a person completely at random, what is the probability you would pick someone with a score: Higher than 60? Instructor: Liana Peter-Hagene Higher than 40? Lower than 40? Normal Distribution Properties And Probability • M = 50, SD = 10 The same information can be expressed with Z-scores: What is the probability of randomly picking a someone with: a Z-score higher than +1? a Z-score higher than -1? a Z-score lower than -1?
Are you sure you want to buy this material for
You're already Subscribed!
Looks like you've already subscribed to StudySoup, you won't need to purchase another subscription to get this material. To access this material simply click 'View Full Document'