Psychology 242 Introduction to Research 1 Course Overview Module 5/1/14 This module is best used as a PowerPoint “Show”. Go to “slide show” and click “run show” Best way to print this: Click ‘File” “Print’; In the dialogue box click “print what?”. Select “Handouts (3 slides per page)” © Dr. David J. McKirnan, 2014 The University of Illinois Chicago McKirnanUIC@gmail.com Do not use or reproduce without permission Click anywhere Psychology 242 Introduction to Research Final Exam Review 2 This module is best used as a PowerPoint “Show”. Go to “slide show”, click “run show” Best way to print this: Click ‘File” “Print’; In the dialogue box click “print what?”. Select “Handouts (3 slides per page)” © Dr. David J. McKirnan, 2014 The University of Illinois Chicago McKirnanUIC@gmail.com Do not use or reproduce without permission Psychology 242, Dr. McKirnan Cranach, Tree of Knowledge [of Good and Evil] (1472) Psychology 242 Introduction to Research 3 What is science? What is science? Values Critical thought Theory: Why? or How? Evidence: How do you know? Discover the natural world Content Empirical findings: Facts Ways of classifying nature Well supported theories Methods Core empirical approach Basic experimental design Specific research procedures Statistical reasoning Psychology 242 Introduction to Research Irrational beliefs Critical thought – rational, empirical-based analysis – is cognitively effortful Our brains may be “hard wired” for irrational beliefs. Wish fulfilling, emotion-based beliefs: • …self-satisfying; confirmatory bias • …differentiating facts from opinions • …emotional responses precede thought Cognitive biases: • Spurious correlations • Evaluating evidence Rationalism & science have a tough row to hoe Psychology 242, Dr. McKirnan Week 12-13, quasi-experimental designs. 4 Psychology 242 Introduction to Research Four basic sources of knowledge or information: How do we know things? Authority: Credible / powerful people Social institutions Tradition Intuition: Emotionality or a “hunch” “Emotional IQ” Empiricism: Rationalism: Psychology 242, Dr. McKirnan Simple sensation / perception Direct observation; data Logical coherence Articulation with other ideas Most central to Science 5 Psychology 242 Introduction to Research What does science do? What does science do? Describe the world Initial approach to scientific study: “what is it” Leads to hypotheses Predict events Core feature of a hypothesis: if “X” then “Y”. Often still descriptive rather than experimental. Test theories Cause and effect questions involving hypothetical constructs. Often controlled experiments or complex correlation designs. Test applications of theories Using theory to model change Testing interventions or policy Psychology 242, Dr. McKirnan Week 2: Role & structure of science. 6 Psychology 242 Introduction to Research 7 Basic features of a research study Basic features of research; Theory Hypothetical construct Hypothesis Replication Operational definition Internal & external validity Confound Independent v. Dependent variables Click through and be sure you can define each of these. Which is the “cause” & which is the “effect”? Which is measured & which is manipulated? Measurement v. experimental studies Psychology 242, Dr. McKirnan Weeks 1 & 2; Introduction to science. Psychology 242 Introduction to Research Basic Elements of a Research Project Phenomenon Big picture / question Begin with the “big question” Core elements of a research study Theory Hypothetical Constructs Causal explanation Hypothesis Operational definition Specific prediction Methods Measurement v. experimental Data / Results • Descriptive data … articulate a clear theory …and derive concrete hypotheses. Then specific methods, the core of a scientific study. Then actual data & results… • Test hypothesis Discussion … implications for the theory Implications for theory Conclusions Future research? 8 …and larger issues. Psychology 242 Introduction to Research Core features of a research study: Theory Hypothesis Methods Data & Analysis Results Discussion Psychology 242, Dr. McKirnan Hypothetical constructs In important relationship More specific variables Falsifiable prediction Know these key terms & concepts. Operational definition Internal & external validity Numerical representation Normal distribution Probability Descriptive: Empirical question or exploration Hypothesis: Statistical significance Meaning of these results for the theory Study Limitations: Internal validity? External validity? 9 Psychology 242 Introduction to Research Section 1 study guide Core elements of the research flow Each component of the research flow corresponds to a later component… Psychology 242, Dr. McKirnan Weeks 1 & 2; Introduction to science. 10 Psychology 242 Introduction to Research Research process: The Big Picture Phenomenon Big picture question. Theory 1 Possible explanation, invoking one set of hypothetical constructs. Hypothesis 1 A prediction that logically flows from – and tests – the theory. Methods 1 Operationally define the variables & test the hypothesis. Psychology 242, Dr. McKirnan Theory 2 Alternate explanation, invoking other hypothetical constructs. Hypothesis 2 Another prediction that tests the same theory. Methods 2 An alternate operational definition & way of testing the hypothesis. Week 3; Experimental designs 11 Psychology 242 Introduction to Research Basics of Design: Internal Validity 12 Internal Validity: Can we validly determine what is causing the results of the experiment? General Research Hypothesis: the experimental outcome (values of the Dependent Variable) is caused only by the experiment itself (Independent Variable). Confound: a “3rd variable” (unmeasured variable other than the Independent Variable) actually led to the results. Core Design Issues: 1. Appropriate control group 2. Equivalent experimental & control groups (except for the Independent Variable). Psychology 242, Dr. McKirnan Psychology 242 Introduction to Research 13 External validity: summary External Is the sample Validity: typical of the Can we validly generalize from this experiment to the larger population? larger world? Is the outcome measure representative, valid & reliable? The research Sample: The Dependent Variable Is this typical of “real world” The study settings structure & The research Setting: where the context phenomenon The Independent Variable occurs? Does the experimental manipulation (or measured predictor) actually create (validly assess…) the phenomenon you are interested in? Psychology 242, Dr. McKirnan Psychology 242 Introduction to Research 14 Validity & Research approaches Observation or Measurement Simple Description Qualitative Quantitative Explore the actual process of a behavior. External Describe a behavioral or social trend. Experiments Correlational Studies Quasiexperiments “True” experiments Relate measured variables to each other to test hypotheses. Test hypotheses in naturally occurring events or field studies. Test specific hypotheses via controlled “lab” conditions. validity Internal validity Less control: More control: Observe / test phenomenon under natural conditions. Create the phenomenon in a controlled environment More accurate portrayal of how it works in nature Address specific questions or hypotheses Less able to interpret cause & effect Better interpret cause & effect Know what these research strategies represent & how they differ. Understand the trade-off of internal & external validity across them. Psychology 242, Dr. McKirnan Psychology 242 Introduction to Research 15 Quasi-experiments 1. Study naturally occurring events that could not be brought into a lab or a truedesigns experiment. Quasi-experimental Measurement studies Experimental designs for “studies in nature”. Retrospective designs 2. Evaluate existing groups or program(s) Simple survey of an intervention that already occurred Non-equivalent designs, due to Time series designs, often with archival data Understand these two forms of quasi-experiments. Understand these forms of nonequivalent designs. Psychology 242, Dr. McKirnan Self-selection Non-random assignment Use of existing groups Participants not blind Psychology 242 Introduction to Research True v. quasi-experimental designs, 3 True experiments: Quasi-experiments: Emphasize Internal Validity Assess cause & effect (in relatively artificial environment) Test clear, a priori hypotheses Emphasize External Validity Describe “real” / naturally occurring events Clear or exploratory hypotheses Groups Equivalent at baseline Random Assignment (or matching). Participants & experimenter Blind to assignment. Non-equivalent groups Control study procedures Create / manipulate the independent variable Control procedures & measures Non-random assignment Existing groups Self-selection Participants not blind. Complete Control not Possible May not be able to manipulate the independent variable Partial control of procedures & measures Know clearly how quasi-experiments differ from true experiments. In that light, know the core characteristics of an experiment and why those characteristics are important. Psychology 242, Dr. McKirnan 16 Week 12-13, quasi-experimental designs. 17 Introduction Quasi-experiments that do not have a control group: to Research Psychology 242 Group Observe1 Intervention or event Observe2 Observe1 Confound Observe2 Threats to internal validity (confounds): History Historical / cultural events occur between baseline & follow-up. Maturation Individual maturation or growth occurs between baseline & follow-up. Reactive measures People respond to being measured or being a measured a second time. Statistical regression Extreme scores at baseline “regress” to a more moderate level over time. Mortality / drop-out People leave the experiment non-randomly (i.e., for reasons that may affect the results…). Know these! What is a confound? Why is that important? Psychology 242, Dr. McKirnan Psychology 242 Introduction to Research 18 Non-equivalent (quasi-experimental) designs Two Group Pre- Post- Design Group Observe1 Intervention or event Observe2 Group Observe1 Contrast group Observe2 Non-equivalent groups Self-selection Non-random assignment Use of existing groups Participants not blind Understand this slide. Psychology 242, Dr. McKirnan Intervention & Assessments often controlled by researcher in these designs. Similar to true experimental design, except for nonequivalent groups 19 Sampling overview Psychology 242 Introduction to Research Who do you want to generalize to? Sampling Who is the target population? broad – external validity narrow – internal validity What does this mean? How do you decide who is a member? demographic / behavioral criteria? subjective / attitudinal? Why does this make a difference? What do you know about the population already – what is the “sampling frame”? Most externally valid & representative Will you use a: Assumes: • Clear sampling frame • Population is available Probability or random sample? Less valid for hidden groups. Non-probability or convenience Less externally valid sample Best when: targeted / multi-frame snowball… Psychology 242, Dr. McKirnan No clear sampling frame Hidden / avoidant population. Psychology 242 Introduction to Research 20 Ethics Research Ethics: The Tuskegee Study The Common Rule The Belmont Report Psychology 242, Dr. McKirnan Foundations of REsearch Tuskegee study begin as a potentially valuable trial of treatment outcomes Begun – and should have remained – a natural history of participants’ response to treatment. Became a wholly unethical no-treatment history. Tuskegee Study: Overview Based on spurious – and racist – scientific reasoning about differences between Africans and Caucasians Investigators took advantage of participants economic and social vulnerability to exploit and harm them. Note: Tuskegee participants were not actually given syphilis; they were not given treatment. Tuskegee led to many of our research norms and institutional controls. 21 Psychology 242 Introduction to Research Ethics procedures stemming from Tuskegee 22 Informed consent Non-coercive enrollment & retention Led to the 1979 Belmont Report Indirectly to core elements of the “Common Rule”. Ethical review & monitoring Led to establishment of the Federal Office for Human Research Protections (OHRP) Led to laws requiring Institutional Review Boards (IRBs) All Federally funded research must be reviewed and monitored by a local IRB Most institutions (e.g., UIC) require IRB approval of all research, federally funded or not. Have a general sense of why Tuskegee was unethical, and how it influenced our ethics decision making now Dr. David J McKirnan, McKirnanUIC@gmail.com Psychology 242 Introduction to Research The “Common Rule” criteria for Human Subjects Protection The Common Rule Minimize risks Risks must be reasonable Recruit participants equitably Informed consent Understand what each of these mean. Document consent Monitor for safety Protect vulnerable participants & maintain confidentiality Dr. David J McKirnan 23 Psychology 242 Introduction to Research Belmont Report (CITI training) 1. Respect For Persons Exercise autonomy & make informed choices. 2. Beneficence Minimize risk & maximize of social/individual benefit. 3. Justice Do not unduly involve groups who are unlikely to benefit. Include participants of all races & both genders Communicate results & develop programs/ interventions You know these from your CITI training. Generally understand them; be able to recognize these key values. Dr. David J McKirnan 24 Psychology 242 Introduction to Research 25 Descriptive research Quantitative Qualitative or Observational Existing data Describe an issue via valid & reliable numerical measures Study behavior “in nature” (high ecological validity). Use existing data for new quantitative (or qualitative) analyses Simple: frequency Qualitative Accretion Interviews Study “remnants” of behavior counts of key behavior “Blocking” by other variables Correlational research: “what relates to what” Focus groups Textual analysis Observational Direct Unobtrusive Wholly non-reactive Archival Use existing data to test new hypothesis Typically nonreactive What does it mean for research to be ‘reactive’? Psychology 242, Dr. McKirnan Descriptive Research. Psychology 242 Introduction to Research 26 Descriptive data Testing hypothesis with Archival, Time Series data Archival data: Already exist, collected for another reason Time series: “Snapshots” of a variable over time, sampling different people each time Longitudinal: Follow the same cohort of people over time. Quasi-independent variable: naturally occurring event, e.g. Magic Johnson testing positive for HIV HIV testing rates? See next slide: Psychology 242, Dr. McKirnan Descriptive Research. Psychology 242 Introduction to Research Psychology 242, Dr. McKirnan Archival, time series data example: Magic Johnson Descriptive Research. 27 Psychology 242 Introduction to Research 28 Correlation designs: Drawbacks & fixes Causality; a simple correlation may confuse cause & effect. ? Depression Alcohol consumption Confounds!; unmeasured 3rd variable problem General optimism Hemlines ? Stock market Dealing with confounds: Use complex measurements or samples to eliminate alternate hypotheses. This slide illustrated the “3rd variable problem” in interpreting correlational data. What does that refer to? Why is that important? Can you generate an example of that in a few words? Psychology 242, Dr. McKirnan Psychology 242 Introduction to Research 29 Descriptive Research: Overview Basic design issues: Reliability Time frame Cross sectional Longitudinal Case study Test – retest Split – half Alpha (internal) Validity Know what these terms mean. Go back to the lecture notes or your book for definitions & examples. Psychology 242, Dr. McKirnan Descriptive Research. Face Content Predictive Construct Ecological Psychology 242 Introduction to Research Statistics: an introduction Using numbers in science Number scales & frequency distributions Central Tendency: Mode, Median, Mean Variance: Standard Deviation The Z score and the normal distribution Using Z scores to evaluate data Testing hypotheses: critical ratio. 30 Psychology 242 Introduction to Research 31 Distributions Mode Normal distribution: mean = mode = Mean Median median at center of the distribution What are examples of data that might fall into these distributions? Median Mean Bimodal distribution Mean & median Mode are similar, at the center. Skewed distribution: Extreme scores in one direction make the median, and mean larger than the mode. Mode Median Mean Psychology 242, Dr. McKirnan Exam #3 study guide Psychology 242 Introduction to Research 32 Scales Types of numerical scales Psychology 242, Dr. McKirnan Week 12-13, quasi-experimental designs. Psychology 242 Introduction to Research 33 Types of numerical scales Ratio zero point grounded in physical property; values are “absolute” continuous & equal intervals Continuous scales (scores physical description: elapsed time, height on a continuum) Interval no zero point; scale values relative continuous with equal interval behavioral research, e.g., attitude or rating scales. Be able to provide or Ordinal rank order with non-equal intervals; no ‘0’ point Simple finish place, rank in organization... Categorical ‘values’ = categories only inherent categories: ethnic group, gender, zip code Psychology 242, Dr. McKirnan Exam #3 study guide recognize examples of these scale types Psychology 242 Introduction to Research 34 Scales and Central Tendency Measure of Central tendency Mode (most common score) Median (middle of distribution) Mean (average score) Typically used for: categorical variables often: bimodal distributions categorical or continuous variables highly skewed data continuous variables only more “normal” distributions use different measures of central tendency. Psychology 242, Dr. McKirnan Psychology 242 Introduction to Research Two measures of variance Measures of Dispersion or Variance 1. Range of the highest to the lowest score. Provides simple idea of where scores fall Very sensitive to any extreme score(s) (“outliers”). 2. Standard deviation of scores around the Mean Similar to “average” amount each score deviates from the M. “Standardizes” scores to a normal curve, allowing for basic statistics. More accurate & detailed than range You should know these by now Psychology 242, Dr. McKirnan Exam #3 study guide 35 Psychology 242 Introduction to Research z 36 Z You must know the Z score It is the core form of the critical ratio. It represents the: Strength of the experimental effect Adjusted by the amount of error variance Z= How far is your score (X) from the mean (M) How much variance is there among all the scores in the sample [standard deviation (S)] Psychology 242, Dr. McKirnan Week 12-13, quasi-experimental designs. = X–M S Psychology 242 Introduction to Research 37 Z and the normal distribution The normal distribution is a hypothetical distribution of cases in a sample It is segmented into standard deviation units. Each standard deviation unit (Z) represents a fixed % of cases We use Z scores & associated % of the normal distribution to make statistical decisions about whether a score might occur by chance. Remember approximations of these numbers Psychology 242, Dr. McKirnan If you do not fully understand this slide go back to the Statistics 1 lecture notes and figure it out!! Exam #3 study guide Psychology 242 Introduction to Research Normal distribution; Z scores Use Z to evaluate a score 1. Distance from M / (X) “error” variance Calculate how far the score is from the mean (M); X–M. 2. “Adjust” X–M by how much variance there is in the sample via standard deviation (S). 3. Z = X–M / S How “good” is a score of ‘6' in two groups? Table 1, high variance Table 2, low(er) variance Mean (M) = 4, Score (X) = 6 Mean (M) = 4, Score (X) = 6 Standard Deviation (S) = 1.15. (X-M = 6 - 4 = 2) Z (X-M/S) = 2/1.15 = 1.74 Standard Deviation (S) = 2.4. (X-M = 6 - 4 = 2) Z (X-M/S) = 2/2.4 = 0.88 Psychology 242, Dr. McKirnan Exam #3 study guide 38 Psychology 242 Introduction to Research 39 Evaluating scores using Z C. Criterion for a “significantly good” score X = 6, M = 4, S = 2.4, Z = .88 If your criterion for a “good” score is that it surpass 90% of all scores… X = 6, M = 4, S = 1.15, Z = 1.74 With high variance a ‘6’ is not “good”. With lower variance ‘6’ is good. 70% of cases I need you to understand the 90% of cases -3 -2 -1 0 +1 Z Scores logic of this approach. +2 (standard deviation units) Psychology 242, Dr. McKirnan Exam #3 study guide +3 Psychology 242 Introduction to Research Core research questions Data 40 Statistical Question One participant’s score Does this score differ from the M for the group by more than chance? Analyze with Z score Means for 2 or more groups Is the difference between these Means more than we would expect by chance? -- more than the M difference between any 2 randomly selected groups? Analyze with t score Scores on two measured variables Is the correlation (‘r’) between these variables more than we would expect by chance -- more than between any two randomly selected variables? Analyze with r Psychology 242, Dr. McKirnan Exam #3 study guide Psychology 242 Introduction to Research Summary Numbers are important for representing “reality” in science (and other fields). Different measures of central tendency are useful & accurate for different data; Mean is the most common. Median useful for skewed data Mode useful for simple categorical data Variance (around the mean) is key to characterizing a set of numbers. We understand a set of scores in terms of the: Central tendency – the average or Mean score The amount of variance in the scores, typically the Standard Deviation. Psychology 242, Dr. McKirnan Statistics introduction 1 41 Psychology 242 Introduction to Research 42 Summary Statistical decisions follow the critical ratio: Z is the prototype critical ratio: X–M S How far is your score (X) from the mean (M) Z= How much variance is there among all the scores in the sample [standard deviation (S)] = t is also a basic critical ratio used for comparing groups: How different are the two group Means t= How much variance is there within each the two groups; (“standard error of the mean”) = M1 – M2 Variance n grp1 grp1 Variance n grp2 grp2 You must understand what a critical ratio is. This slide needs to make Psychology 242, Dr. McKirnan Statistics introduction 1 perfect sense to you!! Psychology 242 Introduction to Research Revised 4/5/0943 Dr. McKirnan, Psychology 242 Introduction to statistics # 2 What can Plato’s Allegory of the Cave tell us about scientific reasoning? Was our hypothesis supported? The critical ratio and the logic of the t-test. The central limit theorem and sampling distributions Correlations and assessing shared variance Statistics Introduction 2. "The Allegory of the Cave" by Allison Leigh Cassel Psychology 242 Introduction to Research 44 Plato’s Cave, 6 What does Plato’s Allegory of the Cave tell us about scientific reasoning? We cannot observe “nature” directly, we only see its manifestations or images: We are trapped in a world of immediate sensation; Our senses routinely deceive us (they have error). We cannot get outside our limited sensations to see the underlying “form” of nature Statistics Introduction 2. Psychology 242 Introduction to Research 45 Plato’s Cave, 2 We study hypothetical constructs; basic “operating principles” of nature e.g., evolution, gravity, learning, motivation… Processes that we cannot “see” directly… …that underlie events that we can observe. We test hypotheses about what we can see and use rational analysis – theory – to deduce what the “form” of these processes must be, and how they work. Statistics Introduction 2. 46 Psychology 242 Introduction to Research Why can’t we just observe “nature” directly? 1. We can only observe the effects of hypothetical constructs, not the processes themselves. 2. We examine only a sample of the world; no sample is 100% representative of the entire population 3. Our theory helps us develop hypotheses about what we should observe if our theory is “correct”. 4. We test our hypotheses to infer how nature works. 5. Our inferences contain error: we must estimate the probability that our results are due to “real” effects versus chance. You must understand these basic concepts and terms! Statistics Introduction 2. Psychology 242 Introduction to Research 47 “Statistical significance” Testing statistical significance We assume that a score with less than 5% probability of occurring (i.e., higher or lower than 95% of the other scores) is not by chance alone … p < .05) Z > +1.98 occurs < 95% of the time (p <.05). If Z > 1.98 we consider the score to be “significantly” different from the mean To test if an effect is “statistically significant”… Compute a Z score for the effect Compare it to the critical value for p<.05; + 1.98 Really important Psychology 242, Dr. McKirnan Statistics introduction 1 Psychology 242 Introduction to Research 48 Statistical significance & Areas under the normal curve 95% of scores are between Z = -1.98 and Z = +1.98. Z = -1.98 Z = +1.98 2.4% of cases 2.4% of cases About 95% of cases -3 -2 -1 0 +1 +2 Z Scores (standard deviation units) Psychology 242, Dr. McKirnan Exam #3 study guide +3 Psychology 242 Introduction to Research With Z > +1.98 or < -1.98 we reject the null hypothesis & assume the results are not by chance alone. In a hypothetical distribution: 2.4% of cases are higher than Z = +1.98 2.4% of cases are lower than Z = -1.98 49 Statistical significance & Areas under the normal curve Thus, Z > +1.98 or < -1.98 will occur < 5% of the time by chance alone. 34.13% 34.13% of of cases cases Z = -1.98 of cases 2.25% of cases -3 -2 2.25% of cases -1 0 +1 +2 Z Scores +3 (standard deviation units) Psychology 242, Dr. McKirnan 2.4% of cases 95% of cases 13.59% 13.59% of cases 2.4% of cases Z = +1.98 Statistics introduction 1 50 Psychology 242 Introduction to Research Critical Ratio Psychology 242, Dr. McKirnan Exam #3 study guide Psychology 242 Introduction to Research 51 Critical ratio The strength of the results (our Critical ratio = direct observation of nature) Amount of error variance (the odds that our observation is due to chance) t= Difference between Ms for the two groups Variability within groups (error) Mgroup2 Mgroup1 Within-group variance, group1 control group Psychology 242, Dr. McKirnan Within-group variance, group2 experimental group Exam #3 study guide Psychology 242 Introduction to Research The Critical Ratio in action All three graphs have = difference between groups. They differ in variance within groups. The critical ratio helps us determine which one(s) represent a statistically significant difference. Be able to answer these: How do the between group variance & within group variance constitute the critical ratio. t represents the critical ratio for group comparisons: how does t vary for these three examples? Which might reflect a statistically significant difference? Low variance Medium variance High variance Statistics Introduction 2. 52 Psychology 242 Introduction to Research 53 The Central Limit Theorem; small samples Central limit theorem True Population M “True” normal distribution With few scores in the sample a few extreme or “deviant” values have a large effect. The distribution is “flat” or has high variance. Score Score Score Score Score Score <-- smaller Statistics Introduction 2. Score Score Score Score M larger ---> Score Psychology 242 Introduction to Research 54 The Central Limit Theorem; larger samples Central Limit Theorem True Population M “True” normal distribution With more scores the effect of extreme or “deviant” values is offset by other values. The distribution has less variance & is more normal. Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score <-- smaller Statistics Introduction 2. M larger ---> Psychology 242 Introduction to Research 55 The Central Limit Theorem; large samples Central Limit Theorem With many scores “deviant” values are completely offset by other values. The distribution is normal, with low(er) variance. The sampling distribution better approximates the population distribution Statistics Introduction 2. True Population M Score Score Score “True” normal distribution Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score Score <-- smaller Score M Score Score Score larger ---> Be able to apply the central limit theorem logic to evaluating t. Translate that to using the t table. Psychology 242 Introduction to Research Central limit theorem & evaluating t scores 1. Smaller samples (lower df) have more variance. 2. So, t must be larger for us to consider it statistically significant (< 5% likely to have occurred by chance alone). 3. Compare t to a sampling distribution based on df. 4. Critical value for t with p <.05 goes up or down depending upon sample size (df) Psychology 242, Dr. McKirnan Exam #3 study guide 56 Psychology 242 Introduction to Research A t-table specifies Critical Values: Alpha Levels df 8 9 10 11 12 13 14 15 18 20 25 30 40 60 120 0.10 0.05 0.02 0.01 0.001 1.860 1.833 1.812 1.796 1.782 1.771 1.761 1.753 1.734 1.725 1.708 1.697 1.684 1.671 1.658 1.645 2.306 2.262 2.228 2.201 2.179 2.160 2.145 2.131 2.101 2.086 2.060 2.042 2.021 2.000 1.980 1.960 2.896 2.821 2.764 2.718 2.681 2.650 2.624 2.602 2.552 2.528 2.485 2.457 2.423 2.390 2.358 2.326 3.355 3.250 3.169 3.106 3.055 3.012 2.977 2.947 2.878 2.845 2.787 2.750 2.704 2.660 2.617 2.576 5.041 4.781 4.587 4.437 4.318 4.221 4.140 4.073 3.922 3.850 3.725 3.646 3.551 3.460 3.373 3.291 Critical values for testing whether an effect is Statistically Significant Alpha = .05, df = 8 Alpha = .05, df = 18 Alpha = .05, df = 120 Alpha = .01, df = 40 Know how to use a t table. What is ‘Alpha’? What are Degrees of Freedom (df)? What is a ‘Critical Value’? 57 Psychology 242 Introduction to Research Central Limit Theorem; variations in sampling distributions df = 120, t > ±1.98, p<.05 As samples sizes ( df ) go down… df = 18, t > ± 2.10, p<.05 the estimated sampling distributions of t scores based on them have more variance, df = 8, This increases the critical value for p<.05. giving a more “flat” distribution. -2 t > ± 2.31, p<.05 -1 0 Z Score +1 (standard deviation units) Get this! -- Be able to go to a t table and apply this logic. Give yourself the Statistics Lectures 2 notes for details. +2 58 Psychology 242 Introduction to Research Taking a correlation approach Correlations t-test We create group differences on the Independent Variable. …and assess how the groups differ on the Dependent Var. Difference between groups standard error of M Correlation; We measure individual differences on the predictor variable… and see if they are associated with differences on the outcome. Σ (Z var1* Z var2) Df (n-1) Statistics Introduction 2. 59 Psychology 242 Introduction to Research 60 Statistics summary: correlation Pearson Correlation (r): measures how similar the variance is between two variables (“shared variance”) within a group of participants. Are people a given amount above (or below) the mean of one variable equally above (or below) the M of the 2nd variable? We measure distance from M using Z scores. r can range from -1.0 to +1.0 E.g., if participants who have Z = +1.5 on variable 1 also have Z = 1.5 on variable 2, etc., r = +1.0. r: For each participant multiply the Z scores for the two variables Sum across all participants Divide by df: Psychology 242, Dr. McKirnan Exam #3 study guide r= Σ (Z var1* Z var2) Df (n-1) 61 Psychology 242 Introduction to Research Type I and Type II errors Know what the Null Hypothesis is!* *Any effect is due to chance alone Psychology 242, Dr. McKirnan Week 12-13, quasi-experimental designs. Psychology 242 Introduction to Research 62 Type I v. Type II errors “Reality” Accept Ho Ho true Ho false [effect due to chance alone] [real experimental effect] Correct decision Type II error Type I error Correct decision Decision Reject Ho Statistics Introduction 2. Psychology 242 Introduction to Research Statistical Decision Making: Errors Type I error; Reject the null hypothesis [Ho] when it is actually true: Accept as ‘real’ an effect that is due to chance only Type I error rate determined by Alpha (.10, .05, .01…) More “liberal” alpha (e.g., .10) reject Ho more often. Worst form of error: statistical conventions are designed to prevent type I errors Statistics Introduction 2. 63 Psychology 242 Introduction to Research 64 Type I v. Type II errors “Reality” Accept Ho Ho true Ho false [effect due to chance alone] [real experimental effect] Correct decision Type II error Type I error Correct decision Decision Reject Ho Statistics Introduction 2. Psychology 242 Introduction to Research 65 Statistical Decision Making: Errors Type II error; Accept Ho when it is actually false; Assume as chance an effect that is actually real. Type II most strongly affected by statistical power (df): Central Limit Theorem: Smaller samples Assume more variance More conservative critical value* Too conservative a critical value Type II error Statistics Introduction 2. *within a given alpha… Psychology 242 Introduction to Research 66 Type I v. Type II errors “Reality” Accept Ho Ho true Ho false [effect due to chance alone] [real experimental effect] Correct decision Type II error Type I error Correct decision Decision Reject Ho Understand the logic of Type I & Type II errors. Be able to map these on to alpha levels and df in your study. Statistics Introduction 2. Psychology 242 Introduction to Research Inferential statistics: summary, Key terms Plato’s cave and the estimation of “reality” Hypothetical constructs actual observations Sample population Inferences about our observations: Deductive v. Inductive link of theory / hypothetical constructs & data Generalizing results beyond the experiment Critical ratio / Z You will be asked to produce and describe this. Variance, variability in different distributions Degrees of Freedom [df] Statistics Introduction 2. 67 Psychology 242 Introduction to Research Inferential statistics, cont. t-test, between versus within –group variance Sampling distribution, M of the sampling distribution Alpha (α), critical value t table, general logic of calculating a t-test “Shared variance”, positive / negative correlation General logic of calculating a correlation (mutual Z scores). Null hypothesis, Type I & Type II errors. Psychology 242, Dr. McKirnan Week 12-13, quasi-experimental designs. 68 69 Psychology 242 Introduction to Research Multiple independent variables Testing hypotheses about > 1 independent variable Factorial Designs: Main effects, Additive Effects, Interactions Psychology 242, Dr. McKirnan 4/14/09 Psychology 242 Introduction to Research > 1 independent variable Designs with > 1 Independent Variable Why have more than one IV? Include a ‘control’ variable Test 2 (or more) Independent variables Psychology 242, Dr. McKirnan Exam #3 study guide 70 Psychology 242 Introduction to Research > 1 independent variable 71 Include a ‘control’ variable as a second I.V. 1. Block the data by gender, age, race, attitudes, etc. 2. Test if the main Independent Variable has the same effect within both groups What is the effect of self-reflection on stress reduction? EXAMPLE Hypothesis: training in self-reflection helps buffer the stress of exams. 2nd Question: is that effect the same in women and men? [old v. young, etc…] Main effect: Self-reflection training less stress Interaction: training less stress worked for women, not men. Conclusion: Including a ‘control’ variable helped clarify the results. Psychology 242, Dr. McKirnan Exam #3 study guide Psychology 242 Introduction to Research > 1 independent variable 72 Testing more than one Independent Variable A. Test separate, ‘main effects’ of each I.V. (Do each of these variables significantly affect the outcome?) B. Test ‘additive’ effects of > 1 I.V.s simultaneously (What is the combined effect of these variables?) C. Test interaction of 2 or more I.V.s (Does the effect of one I.V. on the outcome depend upon a second variable...?) Know the difference between a main effect, an additive effect, and an interaction. Psychology 242, Dr. McKirnan Exam #3 study guide Psychology 242 Introduction to Research Interaction example: Genetics, stress and depression Participants’ genotype and level of childhood trauma interact in depression. There is a general (main) effect whereby more trauma leads to greater likelihood of adult depression Psychology 242, Dr. McKirnan Exam #3 study guide 73 Psychology 242 Introduction to Research Interaction example: Genetics, stress and depression, 2 However … the effect of trauma interacts with genetics Understand clearly why/how this is an interaction, not a main effect or additive effect. Also understand how the interaction tells us much more than the simple main effect. Childhood trauma has no effect in people who have no genetic vulnerability. With increasing vulnerability, increasing trauma increases the likelihood of depression Psychology 242, Dr. McKirnan Exam #3 study guide 74 Psychology 242 Introduction to Research Example of a 3-way interaction 75 Figure 3 Mean ratings of subjective stimulation and sedation on the BAES under 0.65 g/kg alcohol and placebo in women and men. Alcohol (v. placebo) made men much more stimulated. Psychology 242, Dr. McKirnan Alcohol made women much more sedated Multiple independent variables Psychology 242 Introduction to Research Alternate portrayal of 3-way mood interaction Placebo conditions do not show much effect The alcohol conditions show a classic “cross-over” effect for gender & mood; Why/how is this an interaction? 50 M BAES subscale scores 45 Men get aroused 40 35 Men, Alcohol Men, Placebo Women, Alcohol Women, Placebo 30 25 20 15 10 Women get sedated 5 0 Stimulation Psychology 242, Dr. McKirnan Sedation Multiple independent variables 76 Psychology 242 Introduction to Research Multiple IVs; summary 2 77 Multiple Independent Variables / Predictors: Are critical to theory development and testing: Stress or other environmental events can “switch on” genes that create psychological or other problems; genetic dispositions and environment are not separate processes. Establish key “boundary conditions” to theory: when and among whom does a basic psychological process operate? Alcohol makes it more difficult to inhibit behavior, but primarily among men. Psychology 242, Dr. McKirnan Multiple independent variables Psychology 242 Introduction to Research 78 Summary Key terms: Main effect Additive effect Interaction Cross-over interaction Factorial design Repeated measure Psychology 242, Dr. McKirnan Multiple independent variables Psychology 242 Introduction to Research Complex experiments: Within- subjects & blocking designs Own control Reversal designs Repeated measures & Randomized block designs Psychology 242, Dr. McKirnan 79 Psychology 242 Introduction to Research Basic forms of within-subjects designs, 1 Basic forms of within subjects designs; 1. Own control Each participant in control and experimental group. Optimally, order is counter-balanced 2. Reversal designs 3. Repeated measures & Randomized block designs Psychology 242, Dr. McKirnan Exam #3 study guide 80 Psychology 242 Introduction to Research Basic forms of within-subjects designs, 3 Basic forms of Within subjects designs; 1. Own control 2. Reversal designs Hypothesis: behavior controlled by clearly bounded condition Design: “A – B – A”; impose – withdraw – impose condition 3. Repeated measures & Randomized block designs Psychology 242, Dr. McKirnan Exam #3 study guide 81 Psychology 242 Introduction to Research Basic forms of within-subjects designs, 2 Basic forms of Within subjects designs; 1. Own control 2. Reversal designs 3. Repeated measures Multiple treatment conditions: each participant gets each treatment. Longitudinal / time sampling: each participant assessed over multiple time periods Randomized block designs: Repeated measure combined with between-groups variable. Psychology 242, Dr. McKirnan Exam #3 study guide 82 Psychology 242 Introduction to Research 83 Within subjects designs; own control, 2 1. Own Control Repeated Measures Design Single Group Control Condition Observe1 All participants get the Control Condition and measurement Experimental Condition Observe2 All participants then get the experimental intervention and measurement. Hypothesis tested by differences between conditions (Observation1 v. Observation2) within group. Internal validity: eliminate possible confound of group differences at baseline, since there is only one group. Psychology 242, Dr. McKirnan Exam #3 study guide 84 Psychology 242 Introduction to Research Reversal designs 2. “REVERSAL” DESIGNS Test at baseline in normal state, Test under temporary experimental condition Test again under normal state. Examples: Role of incentives in enhancing performance Impact of anti-depressant drug on mood Effect of self-awareness on following social norms Psychology 242, Dr. McKirnan Exam #3 study guide Psychology 242 Introduction to Research Basic forms of within-subjects designs, 4 Basic forms of Within subjects designs; 1. Own control 2. Reversal designs 3. Repeated measures & Randomized block designs Combine a blocking variable with repeated measures. Common for: Biomedical research Behavioral intervention evaluations Psychology 242, Dr. McKirnan Exam #3 study guide 85 Psychology 242 Introduction to Research Randomized block design Blocking Variable; between - subjects factor Groups may be formed around a “Person” variable; e.g., age or ethnic groups, groups based on an attitude measure… Person variables are not “true” IVs; people not randomly assigned. Or: Experimental condition; drug dose, treatment, etc. A “true” IV with random assignment Repeated measure: within-subjects factor Multiple treatment conditions: Each participant is observed after each treatment condition E.g., high v. low incentives, different instructional sets… Or: Longitudinal / time sampling: Measure D.V. over multiple time periods (Cohort studies). Here both the blocking variable and the repeated measures are considered IVs. Psychology 242, Dr. McKirnan 86 Psychology 242 Introduction to Research 87 Within subjects designs; own control, 3 Repeated measures / randomized block design Group 1 Baseline Measure Control Condition Measure2 M3 M4.. Group 2 Baseline Measure Experimental Condition Measure2 M3 M4.. Assignment Randomly or via natural “blocks” Treatment vs. Placebo. Primary Independent Variable. Baseline assessment prior to intervention or experimental condition. Psychology 242, Dr. McKirnan Follow-up. Repeated Measures assessment of the Dependent Variable. Time is a 2nd Independent Variable. Exam #3 study guide 88 Psychology 242 Introduction to Research There are two Independent Variables: Experimental treatment (e.g., drug dose v. placebo) Each IV may have a main effect on the outcome Time (Repeated measures of the outcome variable) If both IVs have main effects the two together would have an additive effect on the outcome Psychology 242, Dr. McKirnan The core hypothesis would be supported by an interaction effect of treatment group by time. Psychology 242 Introduction to Research 89 Main effect example Effect of drug treatment on systolic blood pressure: This shows a Main Effect. Imagine we are testing a new Statin drug for high blood pressure. 60 The treatment group has overall lower Bp, independent of time. Mean systolic Blood Pressure The study 200hypothesis is that drug treatment will help lower Bp, with 50180 stronger effects over time. Blocking variable M = 160 Here are 160 some (made up) randomized 40 block, repeated measures data. 140 PEP users Non users Treatment Placebo 30120 M = 106 100 20 80 1060 These data do not support the hypothesis that drug treatment helps lower Bp: 40 0 Baseline 0 1 6 2 3 The treatment 4 5 group 6 was lower at baseline treatment), and stayed lower over time. Month of study(before visit 12 18 24 30 36 These data would suggest a problem with the randomization: the groups were not equivalent at baseline. Psychology 242, Dr. McKirnan Psychology 242 Introduction to Research 90 Main effect example Effect of drug treatment on systolic blood pressure: This also shows a Main Effect. 60 Both the treatment and control groups show lower Bp over time. 200 Blocking variable Mean systolic Blood Pressure 50180 160 40 M = 147 140 30120 M = 105 100 PEP users Non users Treatment Placebo 20 80 1060 40 0 Baseline 0 1 6 2 3 4 also5do not6support the hypothesis: These data Month of study visit 12 18 Both groups over time. 24 got30better 36 Drug vs. placebo treatment made no difference. Psychology 242, Dr. McKirnan Psychology 242 Introduction to Research 91 Additive effect example Drug treatment & systolic blood pressure: Here is an example of an Additive Effect. 60 Both groups get better over time, 200 and the treatment group Blocking has overall lower variable Bp. Mean systolic Blood Pressure 50180 This ‘adds’ to a strong effect of treatment at the later study visits. 160 40 140 PEP users Non users Treatment Placebo 30120 100 20 80 These data also do not support the hypothesis: 1060 Both groups did get better, and the additive effect of group & time yielded the best outcome. 40 0 Baseline 0 1 6 2 However, 3 4 treatment 5 6 the group was lower at baseline, tovisit treatment. Month prior of study 12 18 24 30 36 These data suggest that people just get better over time, plus a problem with the randomization. Psychology 242, Dr. McKirnan Psychology 242 Introduction to Research 92 Interaction effect example Drug treatment & systolic blood pressure: Here is an Interaction Effect. 60 The treatment group gets better over time. 200 The control group stays Blocking stable. Mean systolic Blood Pressure 50180 variable 40160 PEP users Non users Treatment Placebo 140 30 120 20100 1080 The core hypothesis the this study is supported by this 60 0 Baseline 0 1 6 interaction effect. 2 3 4 5 The groups are equivalent at baseline. Month of study visit 18 group 24 shows 30 an effect 36 over time, the 12 The treatment control group does not. Psychology 242, Dr. McKirnan 6 Psychology 242 Introduction to Research Summary 93 Within – subjects designs are somewhat common in psychological research; Own control designs create a strong contrast for the Independent Variable. Since everyone gets all treatments, they eliminate problems in creating experimental v. control groups. Very common in biomedical or public health studies; Most clinical studies are longitudinal; participants are followed over time The intervention or experimental treatment is I.V. #1 (blocking or grouping variable). Stability or change over time is I.V. # 2 (repeated measure). Psychology 242, Dr. McKirnan