Cheatography

# Data Analysis in Psychological Research Cheat Sheet by Sana_H

data analysis techniques and methods in psychological research

### Analysis

 Data Analysis means examinig, sorting, catego­rising, comparing and evaluating the coded data Types of Analysis Descri­ptive Statistics-techn­iques used to summarize and display numerical data.This provides a general unders­tanding of trends in the data These include: central tendency,variabilityskewness,ANOVA/MANOVA,correlation,regression,canonical analysis Processing of Data Preparing data for analysis Editin­g-p­roc­essing raw data, detect errorsCoding-assigning symbols to responses to be put into categoriesClassification- reduce to groupsTabulation-arranging in logical orderUsing percen­tages Infere­ntial Statistics or Statis­tical Analysis- draw conclu­sions, generalize results from sample to the popula­tion, find meaningful relati­onship from data, and reduce possib­ility of error These include: hypothesis testing (param­etric, nonpar­ametric tests),estimaition of parameter values

### Measures of Central Tendency

 Mean arithmetic average of distri­bution of numbers Median middle score in an ordered distri­bution Mode most frequently occuring score ina distri­bution

### Distri­bution of Data

 Normal Probab­ility Curve (NPC/NDC) special type of density curve that is bell shapeddescribes tendency of most data to normally cluster around the middle Skewness non symmet­rical datacollection of data on either side of the curve Kurtosis peaked or flat distri­bution of data

### Measures of Relati­onship

 Univariate (one variable( Bivariate (two variables) Multiv­ariate (more than two variables) one way ANOVA- analysis of variance which is one direct­ional, x - yIndex Number - measure of relative change in magnitude of a variable (change in price of commodity in the span of a year)Time series analysis - observ­ationof a phenomenon over a period of time (trend analysis) Simple Correl­ation- determine the strength and direction of relati­onship between two variablesSimple Regression-study cause and effect relati­onship, determ­ination of statis­tical relati­onship between two/more variables, used for prediction of future valuesTwo way ANOVA Multiple Regression and Multiple correl­ationMultiple discri­minant analysis-tech to distin­guish datasets obf particular characMANOVACanonical Analysis-deter­mining relati­onship between two sets of variables simult­ane­ously The strength of the relati­onship will always range between +1.00 and -1.00 If the number is closer to +1.00 or -1.00, it indicates a strong correl­ation between the variable. The closer the number is to 0, the weaker the relati­onship becomes bivariate contd.Coeffi­cient of Associ­ation- indicates strength of relati­onship between variablesCoeffi­cient of Contin­gency- indicates whether the IV and DV are dependent or indepe­ndent of each other mulitv­ariate contd.Factor Analysis-data reduction systemCluster Analysis-used to classify objects into groups where objects in one group are more similar to each other and different from objects in other groups correl­ation does not prove causation correl­ation can be studied through: Charles Spearman's coeffi­cient OR Karl Pearson's coeffi­cient

### Statis­tical Signif­icance

 Used to determine whether the differ­ences in the data set are signif­icant or not, i.e whether the differ­ences are real and not caused due to random variations of the experi­ment. It gives us a probab­ility that the results were caused by chance and not by experi­mental manipu­lation Type I error-we accept Ho when it is falseType II error- we reject Ho when it is true Probab­ility is denoted by p indicating the difference due to chanceFor ex. If p < 0.05, it means that there is a 5 out of 100 probab­ility of result being due to chance OR 95% certain that results were real and not due to chance

### Measures of Variab­ili­ty/­Dis­persion

 Variance measure of how much values in a dataset differ from the meanthe amount of dispersion of scores Range difference between values of extreme items(­highest and lowest scores) Standard Deviation average distance between the scores and the mean ORavergae squared deviations from the mean scores in a distri­bution

### Infere­ntial Statistics

 Point estimate- a single value, best estimate of a parameterInterval estimate-a range of plausible values of a parameter Parametric test-specifies certain conditions about parameter of popula­tion, stronger than nonpar­ametric testsnormally distri­buted dataex. z test, t test, F test Nonpar­ametric tests-does not specify any condit­ions, distri­bution free statistics, data does not fall under NPCex. Man Whitney U test, Kendall's tau, chi-square test