Research Methods REVISED.pdf

Research Methods ▪ Two Major Categories to Begin Research – Formulating an idea – Testing the idea 1  Research Methods ▪ Theory ▪ Concept of Determinism ▪ Hypothesis or Hypotheses 2  Research...

Research Methods ▪ Two Major Categories to Begin Research – Formulating an idea – Testing the idea 1  Research Methods ▪ Theory ▪ Concept of Determinism ▪ Hypothesis or Hypotheses 2  Research Methods ▪ Scientific Method – Set of procedures used for gathering and interpreting objective information 3  Research Methods ▪ Public Verifiability – All data and methods must be eventually open to others for review and scientific inspection 4  Research Methods ▪ Observer Bias – Distortion of evidence because of the personal motives and expectations of the viewer 5  Observer Bias Is this cup half empty or half-full? 6  Observer Bias A. 7  Observer Bias B. 8  Observer Bias: The Remedy ▪ Standardization – Uniform procedures for treating each participant ▪ Operational definition – Definition of a variable in terms of how it will be measured or manipulated in a study 9  Research Variables ▪ Independent Variable – A factor that is manipulated by the researcher – The causal part of the relationship ▪ Dependent Variable – A variable that the experimenter measures to assess the impact of the independent variable 10  Experimental Method ▪ Challenge to Objectivity – Overweighting hypothesized explanation – Alternative explanations must be ruled out 11  Experimental Method ▪ Confounding Variable – The effects of these variables may be confused for the effects of the IV ▪ Experimenter Bias – Example: Rosenthal & Fode (1963) 12  Experimental Method ▪ Placebo Effect – Participants’ expectations about what the manipulation will do to them lead to changes in the DV 13 Experimental Method: The Remedy ▪ Control Procedures – Holding all other variables constant except those being systematically varied 14 Experimental Method: The Remedy ▪ Double-blind Control ▪ Placebo Control 15 Experimental Method: The Remedy ▪ Between-subjects Design – Different groups of participants are randomly assigned to experimental conditions 16  Experimental Methods: The Remedy ▪ Within-subjects Design – Each participant is his or her own control ▪ Counterbalancing – Each condition must appear equally often in each position 17  Experimental Methods: Limitations ▪ Artificiality – Lab studies may oversimplify or distort behavior ▪ Participants may change responses when they know they’re being observed ▪ Ethical constraints 18  Correlational Research ▪ Determine to what extent two variables, traits, or attributes are related ▪ Correlational Coefficient (r) – Indicates the direction and magnitude of relationship between two variables 19  Correlational Methods ▪ Positive Correlation 20  Correlational Methods ▪ Negative Correlation 21 Correlational Methods 22  Psychological Measurement ▪ Reliability – Degree to which a test produces similar scores each time it is used – Stability, consistency ▪ Validity – Extent to which a test measures what it was intended to test 23  Psychological Measurement ▪ Self-report Measures – Behavior identified through a participant’s own observations and reports – Fixed-format or open-ended 24  Psychological Measurement ▪ Limits of Self-report Measures – Only for use with certain populations – Threat of reactivity 25  Psychological Measurement ▪ Behavioral Measures – Overt actions and reactions that are observed and recorded – Focus on process or products of behavior – Often physiological in nature (e.g., fMRI) – May involve naturalistic observation 26  Psychological Measurement ▪ Case Study – Intensive observation of a particular individual or subgroup 27  Ethical Issues in Research ▪ Informed Consent ▪ Risk/Gain Assessment ▪ Intentional Deception ▪ Debriefing 28  Ethical Issues in Research ▪ Should animals be used in psychological and medical research? 29 Understanding Research Results ▪ What did we find? Was our hypothesis supported? – Need to summarize data Graphical summaries Descriptive statistics 30  Bar Chart 12 10 8 6 4 2 African Asian Hispanic White ETHNICITY OF SAMPLE 31  Histogram 2.2 2.0 1.8 1.6 1.4 1.2 1.0.8 18.00 20.00 24.00 26.00 31.00 33.00 37.00 40.00 47.00 57.00 19.00 22.00 25.00 29.00 32.00 34.00 38.00 45.00 52.00 63.00 32 AGE  Descriptive Statistics ▪ Measures of Central Tendency – Mean (Average) – Median (Middle score) Avoids influence of outliers 33 2 3 4 5 6 7 10,000 34 2 3 4 5 6 7 10,000 35  Descriptive Statistics ▪ Measures of Central Tendency – Mean (Average) – Median (Middle score) Avoids influence of outliers – Mode (Most common score) Can be more than one 36  Descriptive Statistics Measures of Variability (Dispersion) - Range Highest minus lowest score - Standard How much do the scores Deviation vary, on average, from the (s) mean?  (x - x)2 N 37 A Linear Relationship F 2.9 38 Scatterplots of Different Correlations F 2.10 39 A Nonlinear Relationship F 2.11 40 Inferential Statistics: Distinguishing Chance From Significance ▪ Calculates the probability that results are due to chance ▪ Statistical significance is determined by statistical analyses performed on the data and found when an observed relation or difference between two variables is not due to chance 41 The “Bell Curve” 42 Inferential Statistics: Distinguishing Chance From Significance ▪ Normal curve allows us to determine likelihood of finding a given mean difference by chance alone ▪ If this probability is < 5%, the difference is considered “statistically significant” (assumedly not due to chance) ▪ Of course, assumption might be wrong! 43  How Statistics are Misused ▪ Outliers have undue influence in studies with low sample size (n) ▪ Small relationships found in studies with high sample size (n) are more likely to be significant ▪ Significant doesn’t mean important! 44