Understanding Research Methods in Psychology

Psychology 3301 Lecture 6

Recall Research? Methods? ? Philosophy? Of? Science? Research? Design? Statistics? Measurement? Data? Analysis? No? random? assignment? of? S s? to? conditions? Random? assignment? of? S s? to? conditions? Qualitative? Data? Quantitative? Data? Hypothesis? Testing? Estimation? ? Positivism? ? Popper? ? Sampling? Methods? Non-probability? Probability? ? Experiment? ? All? sorts? of? stuff? about? confounding,? blinding,? placebo? effects,? matching,? blocking,? etc.? *? ? ? Reduce? ? Summarize? ? Convey? meaning? ? Loss? functions? ? ? Decision? procedures? ? Point? hypotheses? ? Distribution? theory? ? Test? statistics? ? Theory? of? errors? ? No? room? but? we? don t? teach? much? of? this? stuff? anyway.? ? Operationism? ? CV? Theory? ? Kuhn? SRS? SYS? PPS? STR? Cluster? ? Content? ? Narrative? ? Discourse? ? Framework? ? Grounded? Theory? ? ? Univariate? ? Realism? ? T? constructs? ? Description? vs? explanation? vs? law? vs? prediction? vs? model? vs? theory? ? Determinism? vs? mechanism? vs? reductionism? vs? humanism? shape? location? spread? kurtosis? ? Reliability? ? Validity? ? CTT? ? IRT? ? ? Descriptive? Study? Case? study? Survey? Naturalistic? Interview? ? Quasi-Experiment? Pre-post? Pre-post-control? Time? series? Time? series? control? ? Other? Cohort? study? Guided? interview? Retrospective? Prospective? ? ? Bivariate? linear? correlation? non-lin? correl? ? Multivariate? MDS? PCA? FA? ? Metric? vs? Non-metric? ? Model? fitting? ? *? All? designed? to? attune? students? to? the? ways? in? which? our? methods? of? design? can? cause? our? research? to? mislead? us? about? the? way? in? which? the? world? really? is.? The? major? reason? for? research? methods? in? the? first? place.? ? The? reason? we? must? pay? attention? to? these? issues? is? that? most? of? these? principles? are? nothing? but? hard? learned? lessons? about? the? way? in? which? we? deceive? ourselves? by? the? methods? we? use? to? try? to? understand? the? world.? Although? they? are? listed? under? experiments,? these? are? principles? that? apply? to? ALL? methods? of? data? collection? and? analysis.?

Data Analysis: Distance The question of how far things are away from each other is fundamental to understanding the aims of a data analyst. Consider the gender income gap question. Even the way the question is phrased makes reference to a distance. That is, the size of a gap between two things. The concept of the distance between things is so fundamental that it is embedded deeply in to our ordinary language. Consider the questions i. ii. Is X a consistent player? iii. Are X and Y similar? iv. Is X normal? v. Are we the same? vi. Is X a reliable person? Do we agree?

Data Analysis: Distance Lets look at two techniques you already know about that we use as a mathematical paraphrase for the distance between things. Consider the standard deviation. Now let s consider the standard score.

Data Analysis: Distance The problem is that, in these methods, distance is measured in one dimension only. What if we want to measure distance in a two or three dimensional space? Watch the following videos: i. Euclidian distance one ii. Euclidian distance two So the distance between individuals or points in this two dimensional space is a measure of how similarly they responded to the two questions. Now, we use the idea of distance between points in space very widely throughout statistics and data analysis. One use is as a way to determine how well a model fits a set of data.

Data Analysis: Distance and Models In the following set of videos, let s look at the construction of a simple linear regression model and how we evaluate how well our models fit the data. Watch the following videos: i. ii. Linear regression video two iii. Linear regression video three iv. Linear regression video four Linear regression video one It s important to understand that no matter how complex models become, whether they be models constructed for the purpose of modeling the risk of exposure to or death from disease, or the future temperature of the globe, the principles are the same as they are for simple linear regression. Having said that, in most practical situations, we need models for data that is more complex than the one criterion, one predictor case.

Data Analysis: Distance and Models In the following set of videos, let s look at the construction of models for cases in which we have more than one predictor. So for instance, if we were trying to model risk of death from COVID- 19, we might want to use more than say just age; we might also like to use variables like number of people a subject is living with, density of the population in the surrounding area, whether the subject is diabetic or not, etc. To do this, we use a technique called multiple regression. In this technique we simultaneously use multiple predictors to model a single criterion such as risk of death. Watch the following videos: i. Multiple regression video one ii. Multiple regression video two iii. Multiple regression video three

Exercise 3 In this exercise, let s use multiple regression to model the gini coefficient for a given US State. Here are the steps i) ii) Explore the data file a bit by doing scatter plots of some of the variables with the criterion variable of interest the gini coefficient. iii) As part of the exploration, find out which states have the highest and lowest gini. Find out which variables have the strongest bivariate relationships with the gini. Identify states that are outliers that is, they don t follow the pattern of the other states. iv) Add a variable to the file. Go to the internet and determine whether a state voted for Biden or Trump in the last election and enter that data into the file. Open the US state data in SPSS.

Exercise 3 The steps continued v) Look at the relationship between who a state voted for and the gini. vi) Conduct an appropriate hypothesis test of the effect of who a state voted for on the gini and comment on the validity of the test you have conducted. vi) Now, develop a multiple regression model with gini as the criterion and the other variables as predictors. Find the best fitting model you can. vii) Note how well your model fits and whether or not the model is statistically efficient. viii) Identify the states that are not well represented by your model and the appropriateness of using the model to estimate the gini for those states. Watch a video on how to do exercise 3: here

Exercise 3: What to Hand In Go to the Discussion Board in the main menu on Blackboard. Go to Exercise 3. Report your multiple regression results and see how well your equation did in comparison to the equations produced by the other students in the class. Based on all of your analyses, comment on what you think might contribute to a high income inequality in a US state.