Lecture 7 Notes
Lecture 7 Notes 76884
Popular in PSYC4201W
verified elite notetaker
Popular in Psychlogy
This 6 page Class Notes was uploaded by Rachel Onefater on Friday February 5, 2016. The Class Notes belongs to 76884 at George Washington University taught by Dr. George Howe in Spring 2016. Since its upload, it has received 23 views. For similar materials see PSYC4201W in Psychlogy at George Washington University.
Reviews for Lecture 7 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: 02/05/16
Statistics for description and inference We find it easy to describe individuals… How do we describe groups or collections? Intuitively… People? Example : How do we describe them(i.e. a class, people who worship together at Mecca) People who aren’t part of some naturally occurring group? • All humans alive today • All children born in the same year in Dunedin, New Zealand • All people in the continental United States between the ages of 18 and 54 • All people in the US between the ages of 18 and 22 • The first 100 GWU students who sign up for and complete my online questionnaire as a requirement for their psychology course Statistics: a language for describing groups, collections, samples • Quantitative description on one or more dimensions Words in that language • Frequency Distribution → Frequency (def.) how often/how many → distribution (def.) How does that lay out across some metric/what we are testing : – The number (or percent) of people having the same score, distributed across all scores → Describes some sort of pattern when testing something. Words in that language (Cont’d) • Location of that distribution on a dimension: Words that you use when you describe sets of people – Range (056) – Midpoint of range (28.5) A.K.A Mode – Median (12) – Mean: μ = Σ(x)/n: (15.4) a. Average(def.) descriptor for a set or group, not for an individual's Example : every family has 1.5 children, I want to see that 1.5 childdoes not exist because avg. does not describe the individual Words in that language (Cont’d) • How variable the scores are: – Pick a point of reference (the mean μ ) – Calculate how far away every other score is Example : 15 and another person is 47, so there is a distance of 32 points, so you can calculate the average distance for the whole group away from the mean – Calculate the average distance from the mean → variance Words in that language • Variance: – Distance from mean: – Square it: – Compute the average: •Note: divide by n, not n1, for population variance • Standard deviation: square root of variance: Words in that language (Cont’d) • Mean: 15.4 • Variance: 167.44 • Standard deviation: 12.94 +1 SD +2 SD 1 SD 2 SD Response time data from our experiment Dot Probe task→ Hit a button when red circle pops up, and there will be a measure of how many times you are correct when you press that button! → Dr Howe’s reaction times on dot probe task response time: 491 726 274 410 597 469 572 520 767 534 Mean = 483 SD = 107 * A large percentage of the responses are within that 280 and 680, so there are only a few that are a bit slower! Using excel to calculate mean and standard deviation • Let’s jump to some data from our pending experiment Summarize steps 1. Make a copy to work on, as a full excel worksheet (xlsx) a. can save data in diff. formats, so make sure you save it in the right one (File→ Save as→ Excel Workbook) 2. Expand columns so names are visible a. highlight→ go to on of the borders→ open it up to be bigger 3. Delete practice trials **NOTE: Remember your assigned subject number so you can keep your results confidential, and you will be using your number throughout the semester. 4. Sort on correct, and delete error trials (correct = 0) 5. Sort on prob_threat *Delete all that say practice* → little triangle on the side of excel, click data, and sort so you can look at the mistakes, and you don’t want to analyze them, so you delete them! → Highlight all the neutral and threats and sort them all together! 6. Highlight response_time cells for neutral and name them Take all response time for neutral items and name entire set, and go to: formula→ define name→ Ex: Neutral 7. Highlight response_time cells for threat and name them Take all response time for neutral items and name entire set, and go to: formula→ define name→ Ex: Threat 8. Use options in Autosum icon to calculate mean, SD, N for the two probe types Mean→ Go to neutral→ click on box→ then go to autosum→ Click average/SD/N(things are highlighted)> in parenthesis put “(neutral)” 9. Repeat with other condition Mean→ Go to neutral→ click on box→ then go to autosum→ Click average/SD/N(things are highlighted)> in parenthesis put “(threat)” N:(def.) how many different trials we had, in Autosum, this is “Count Number” From description to inference • We describe something about a sample (mean, SD, difference in means) • How do we know whether that description fits the larger group or population? • A question ofinference (def.) taking information that is limited and expanding it to make conclusion more broadly Example : Do a study of GW students and generalize to all college students in the country • We need to take into account “fuzziness” introduced by using only a part of the population • More formally, sampling error (def.) fuzziness Measuring “fuzziness” in a mean • Standard deviation tells us something about this • Used to calculate the standard error of the mean – Defined as the standard deviation of the error in the sample mean with respect to the population mean – Calculated as the sample standard deviation divided by the square root of the sample size SEM :take the standard deviation and divide that by the square root of the mean *NOTE: sqrt square root on excel – Let’s look at this in my data How do we interpret this? • If we know the shape of the frequency distribution, we can use this to estimate the effects of fuzziness on our confidence that the sample mean is close to the population mean • Usually we assume a normal distribution: → we usually assume that the distribution of these errors is going to be normally distributed. • A common metric for this range: plus or minus 1.96 times the standard error (also known as 95% confidence interval) Measuring “fuzziness” in the differences between two means • Standard error of the difference between two means • Need to include information from the variances of both • We can calculate how large the mean difference is in comparison to that index of fuzziness • In this case, is the mean difference outside of the range of zero? • Formula: Calculating ttests in excel • Let’s jump back to our data again 24 Summarize steps • Calculate the square of the SD for the first group, divided by N (=sqrt(SD1*SD1/N) • Calculate the same quantity for the second group. • Sum these quantities, and calculate the square root (this gives you the standard error of the mean difference) • Calculate the mean difference plus or minus 1.96 times the standard error, for the confidence range • Calculate the t statistic by dividing the mean difference by the standard error • Use the ttest function to determine its probability =T.TEST(neut, threat,2,2) Summary • Means, mean differences, standard deviations describe aspects of a sample → in control, Dr. Howe is more likely to experience threat than nonthreat conditions • Standard errors and ttests are inferential statistics that tell us whether our findings hold even after we take into account the fuzziness of using only some out of the total population → tool for making statements, but cause can be helped by statistics, but not determined by statistics Meditation as attention training • Focused meditation (such as TM) • Mindfulness meditation 27 Training in TM – Transcendental Meditation techniques (Charles Alexander) • 1970’s – 1980’s • Focus on specific target (sound, image, sensation) • Continually return to that target as mind wanders • Methods for “calming the mind”, from Indian Vedic tradition • Programs involve training in meditation, establishing daily practice • Evidence for reduction in biological indexes of stress response • Much of the work here by proponents of TM, with few attempts to replicate in independent labs Training in mindfulness • Mindfulness Based Stress Reduction (MBSR: Jon KabatZinn) – Borrowing from Buddhist Vipassana meditation tradition • Uses concentration forms of meditation as initial stage to develop stable base for awareness (often the breath) • Second stage: rather than suppressing awareness of anything but focus, emphasizes awareness of sensations, thoughts, feelings • New goal: an attitude of “friendly curiosity, interest, and acceptance toward all observed phenomena • Emphasizes intention to refrain from evaluation and selfjudgment, and to observe nonjudgmentally when these occur MBSR Program • KabatZinn developed MBSR for patients with chronic pain and stressrelated conditions – 8 week class, 23 hours per week, plus a oneday intensive – Components involve • Body scan: exercise to increase awareness of body sensations • Hatha yoga: again, emphasizing awareness of sensation • Sitting meditation, practicing both concentration and awareness • Walking meditation MBSR Effectiveness • Evidence from controlled trials – Williams et al (2001): trained university staff in MBSR • MBSR group reported reductions in daily hassles, distress, and medical symptoms as compared to controls – Davidson et al (2003) trained biotech company employees in MBSR • Using electroencephalography (EEG), found greater activation in left anterior brain, and less asymmetry between left and right activation (associated in other studies with positive emotions or reduced depression) • Found stronger antibody response to administration of flu vaccine Summary • Stressful circumstances can shape attention – Severity of challenge, cognitive load • Attempts to suppress thoughts can make them worse • Expression/acceptance strategies seem to work better • Attention training methods (ABM, meditation) can be useful for stress reduction
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'