Midterm 2 Study Guide

Midterm 2 Study Guide - Psychology 60, Spring 2010 ...

This preview shows page 1. Sign up to view the full content.

This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Psychology 60, Spring 2010  Midterm 2 Study Guide    This study guide is not intended to provide you with a comprehensive list of the topics you need to  know; rather, this guide is meant to guide you in your studying. Do not assume that you can study  only these topics and/or read only these sections in the book. This guide will not replace a thorough  reading of the book and review of your lecture notes.  The following is simply a list of topics and  formulas with which you should be most familiar.    ALSO: Statistics is inherently cumulative. That is, you need to know information from before the  first midterm in order to succeed on the second midterm (like how to calculate a mean, for  example). I won’t test you heavily or specifically on material from before the first midterm, but  understand that you still need to know this material. Accordingly, I have left those concepts on this  study guide.   • The differences between populations and samples  •  The difference between inferential and descriptive statistics  •  The differences between statistics and parameters  •  Sampling Error  •  Summation Notation  •  Scales of measurement, specifically the differences between the different scales  •  Characteristics of experimental research  o Manipulation  o Control  o Random Assignment  •  Differences between experimental studies and correlational studies  •  Constructs and Operational Definitions  •  Interpreting frequency graphs/histograms  •  Types of data appropriate for line graphs, bar graphs and scatter plots  •  Describing the shape of distributions using symmetry and skew  •  Differences between the different measures of central tendency  •  Computation of the standard deviation for both populations and samples  o Know how to use the formulas  o Know when to use each of the formulas  •  Z‐scores  o Computation of a z‐score for an individual score in a population  o Understand the meaning of a z‐score  o Be able to tell which of two z‐scores is more extreme  o Understand what extreme means in the statistical sense  o Converting from raw scores to z‐score  o Converting from z‐scores to raw scores  o Be able to find the proportion of a normal distribution between two z‐scores  o Be able to find the proportion of a normal distribution beyond a z‐score  o Be able to find the z‐score corresponding to where a certain proportion of a  distribution is beyond that score  • Know the basic definition of probability    Material Presented Since First Midterm:     • Distribution of sample means  o Understand what the distribution of sample means represents  o Be able to locate the z‐score for a particular sample mean in the distribution of  sample means  o Be able to calculate the standard deviation for the distribution of sample means for  populations, and from sample data  o Understand the difference between the standard error and the estimated standard  error  o Understand when the distribution of sample means will be normal  o Understand how the shape of the distribution of sample means changes with sample  size  o Understand whyit is important for the distribution of sample means to be normal  o Understand what the central limit theorem tells us tells us about sampling  distributions     •  Hypothesis testing in general  o Understand the basic logic of a hypothesis test  Understand what critical regions are in a hypothesis test  Understand what alpha is  o Be able to perform hypothesis tests at alphas other than .05; what changes?  o Be able to use the z and t tables (will be provided)   o Know what changes in a one‐tailed hypothesis test  o Know some of the issues with using a one‐tailed hypothesis test  o Know how to correctly interpret the result of a hypothesis test  o Know what a Type I error is  Understand why the probability of a false alarm is alpha ONLY when the null  hypothesis is true  o Know what a Type II error is  Understand why the probability of a miss is beta ONLY when the alternative  hypothesis is true  o Know why we never “accept” the null hypothesis  o Know the difference between statistical significance and practical significance  o Be able to calculate Cohen’s d, and understand what it shows  o Know the differences between the t and z distributions  o Understand the concept of degrees of freedom, and know how to calculate degrees of  freedom for a t‐test  o Understand the concept of power  Know what factors can influence the power for a test  Know how to compute power for a z test  o Understand what p‐values tell us  o Understand why the p‐value is not the probability that the null hypothesis is true    • Hypothesis Testing: Tests to know  o Be able to perform a hypothesis test from raw data, or from summary statistics (for  example, if I were to give you the mean and standard deviation of a sample, and μ for  a population, be able to compute the correct hypothesis test)  o Know how to perform a hypothesis test when σ and μ are known, z‐test  o Know how to perform a hypothesis test when σ is unknown but μ is known, one  sample t‐test  o Know how to perform a hypothesis test when σ and μ are unknown, independent or  dependent sample t‐tests depending on study design  o Know which tests are applicable for which experimental situations, especially when  to use a dependent vs. independent samples t‐test      Some Important Formulas from Before Midterm 1    Mean  Sum of squares for sample                        Standard deviation for population  From SS          Standard deviation for sample  From SS          Sum of squares for population,   Definition form          Sum of squares for population  Computational Form                Sum of squares for sample  Computational Form          Z­score to raw score      Raw score to z­score                        Some Important Formulas from After Midterm 1          Single Sample z­test:  test statistic  Single Sample t­test:  sample variance    X−µ zX = σX SS s= df   2         Single Sample z­test:  standard error  σ2 σX = n Estimated Cohen's d = X−µ tX = sX Single Sample t­test:   estimated standard error  sX =     X−µ s Dependent samples t­test:   test statistic:  t XD XD = sXD   Dependent samples t­test:  estimated standard error  sXD = 2 s n     Single Sample t­test:   test statistic      Single Sample t­test:  estimated Cohen’s d     2 D s n           Dependent samples t­test:   sample variance:  Independent samples t­test:   Pooled variance    SSD s= df 2 D SS1 + SS2 s= df1 + df2 2 p   Independent samples t­test: estimated  standard error  SSD = Σ( X Di − X D )2   Dependent samples t­test:   sample SS computational formula  2 SSD = ΣX   Estimated Cohen's d = XD 2 sD Independent samples t­test:   test statistic    (X1 − X2 ) = s(X1 − X2 )     n2   X1 − X2 s2 p       Power Calculation Formulas for z­tests    Critical value of the mean:        t(X1 − X2 ) s2 p Independent samples: estimated Cohen’s d       Dependent samples:   estimated Cohen’s d     Estimated Cohen's d = n1 +       Di n s2 p s( X1 − X2 ) =   ( ΣX ) −     Dependent samples t­test:   sample SS definitional formula    2 Di     Xcritical = µnull + zcriticalσ X       z relative to distribution of z under the  alternative hypothesis:    Xcritical − µalternative z= σX         ...
View Full Document

This note was uploaded on 10/16/2011 for the course PSYCH 60 taught by Professor Parris during the Spring '11 term at UCSD.

Ask a homework question - tutors are online