DOC PREVIEW
UMass Amherst PSYCH 241 - study guide for exam 2

This preview shows page 1 out of 4 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 4 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 4 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

241 Study Guide for Exam #2Example Questions:Be prepared to identify and sequence the seven overarching stages of theory driven research:1. Theory or general problem of interest (research question)2. Generate specific, testable hypothesis3. Design study and evaluate ethics4. Conduct study so as to achieve unambiguous results (evaluate internal & external validity)5. Collect and summarize data, descriptive statistics6. Draw conclusions from these analyses (inferential statistics)7. Reject/modify/support original hypothesisWhat are the three steps of data analysis and interpretation?1. Get to know the data (inspect data carefully, identify errors in data, consider whether the data makes sense or not); 2. Summarize the data (use descriptive statistics (central tendency, variability, effect size) and graphical displays of data); 3. Confirm what the data reveal (representative of the population mean, perform inferential statistics analysis)What does the use of statistical software packages mean for the researcher?Means researchers do few calculations, but need strong understanding of methods (Design & Analysis)What are the three things you should do in getting to know your data?Inspect data carefully, identify errors in data, consider whether the data makes sense or notBe prepared to describe the three measures of central tendency we discussed:Mean (sum of scores divided by number of scores)(arithmetic average); Median (middle point of frequency distribution)(score that splits the distribution in half); Mode (most frequent score in distribution)(can be more than one mode)Be prepared to describe the four measures of variability we discussed:Range of scores (difference between highest & lowest (max/min)); Variance (s^2)(sum ofthe squared differences between X1 and X divided by sample size n – 1); Standard Deviation (SD or s)(how far, on average, a score (x) is from the sample mean (X)); Measures of Effect Size(formula for Cohen’s d (d = X1 – X2 / SD)How is the standard error of the mean related to the standard deviation?Measures how well the sample mean estimates the population mean; standard deviation of theoretical sampling distribution of meansHow does increasing the sample size influence the standard error of the mean, specifically?Sample size produces tighter estimate of the standard error of the meanWhat does the standard error of the mean tell us about the population mean?Measures how well the sample mean estimates the population meanWhat are we assessing with effect size measures?Can compare across different studies (form of meta-analysis)What measure of effect size do we use for the comparison of two means?Cohen’s dWhat does a confidence interval tell us about the population mean?A range of values which we state (with a certain degree of confidence) includes the population meanHow does increasing the sample size influence the confidence interval, specifically?What are we trying to accomplish with the three stages of data analysis?Decide whether results support hypothesis or notWhat is the primary goal of a null hypothesis significance test (NHST)?To determine whether there are differences among conditionsWhat are the two steps of NHST? What does the probability value tell us?Step 1. Assume conditions do not differ; Step 2. Compute appropriate statistic to test for condition differences (t-test or ANOVA); probability value tells us if statistically significantWhen do we reject the null hypothesis? When do we accept the null hypothesis?Reject null hypothesis when the outcome has a small likelihood of occurring; never accept the null hypothesisIf the observed p value is > 0.5, why don’t we accept the null hypothesis?Researchers are tentative about conclusions, errors can occur & other hypotheses may exist, findings support the hypothesis but do not prove itWhat do we mean by Type 1 error? What do we mean by Type 2 error?Type 1 error = hypothesis rejected when actually true (no difference)Type 2 error = hypothesis not rejected when actually false (difference)What do we mean by experimental sensitivity and how can we increase this?Likelihood that an experiment will detect the effect of an independent variable when the independent variable had an effect (hypothesis is false); sensitivity increases with good research design and methodsWhat do we mean by power and what three factors affect the power of a statistical test?Power of statistical test; level of significance (alpha), size of effect for independent variable on dependent variable, sample sizeWhy do repeated measures designs often lead to greater experimental sensitivity?Minimize error variance, reduce noiseWhat is the logic of the ANOVA, and how does the true experimental design relate to this?Identify sources of variance in data (primary vs. error)When would you use the ANOVA approach rather than the t-test?When you have more than 2 levels of an independent variableBe prepared to present and describe the conceptual formula for the ANOVA:F = variation between groups / variation within groupsWhat do we mean by partitioning the variance and how is this used in ANOVA?Split total to “due to IVa and chance” and “due to chance”Be prepared to identify the four designs we discussed and to construct their skeleton tables:1-way Independent GroupsSource dfIVa (a – 1)Error a(n – 1)Total an - 11-way Repeated MeasuresSource dfIVa (a – 1)Subjects (n – 1)Error (residual)(a – 1) (n – 1)Total an - 12-way Independent Groups (Factorial)Source dfIVa (a – 1)IVb (b – 1)IVa * IVb (a – 1) (b – 1)Error ab(n – 1)Total abn - 12-way Mixed (Factorial)Source dfIVa (a – 1)Error (independent group factor) a(n – 1)IVb (b – 1)IVa * IVb (a – 1)(b – 1)Error (for Repeated Measures & Interaction)a(n – 1)(b – 1)Total abn - 1Be prepared to extract the important information from summary tables, for the four designs:AboveBe prepared to calculate the Mean Square values and F ratios in an ANOVA summary table:Mean Squares = sum of squares / degrees of freedomF-ratios = Mean Squares of IV / Mean Squares of error When would you use confidence intervals with the ANOVA approach?Can plot the means along the confidence intervals to judge where differences are likely toexistWhen would you use post-hoc test with the ANOVA approach? Why would you do this?To compare multiple pairs of means; repeated measures ANOVAWhat can you tell me about family-wise error and how to minimize it?The probability of making one or more false


View Full Document

UMass Amherst PSYCH 241 - study guide for exam 2

Download study guide for exam 2
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view study guide for exam 2 and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view study guide for exam 2 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?