Chapter 10 - Criminal Justice and Criminology Research Methods, 2nd Edition

Chapter 10 Analysis of Quantitative Data 1 Vocabulary of Coding Coding - the systemic reorganization of raw data into a format that is computer readable. Coding Procedure - a set of rules stating that certain numbers are assigned to variable attributes. Codebook - a document describing the coding procedure and the location of data for variables in a format that computers can use. Precoding - the act of writing the code categories directly on the questionnaire; survey researchers often precode questionnaires before collecting data. 2 Entering Data Data Field - a column or set of columns assigned to a variable. Code Sheets - a sheet with grids in which the researcher writes the code numbers in squares that correspond to a row and column location, and then uses this to type it into the computer. Direct Entry Method - a method of data entry where the researcher manually types in the data. Optical Scan Sheets - a machine that can read information from questionnaire sheets and insert them directly into a computer file. 3 Cleaning Data Accuracy is extremely important when coding data. Errors made when coding or entering data into a computer threaten the validity of measures and cause misleading results. After careful coding, the researcher checks the accuracy of coding, or “cleans” the data. 4 Results With One Variable Statistics - ways to manipulate and summarize numbers that represent data from a research project. Descriptive Statistics - a description of phenomena using numbers. Univariate Statistics - statistics describe one variable. Frequency Distribution - a table that shows the distribution of cases into categories of one variable, that is, the number or percent of cases in each category. Visually, this uses: Histogram Frequency Polygon 5 Results With One Variable Measures of Central Tendency Mode - the most common or frequently occurring number in a distribution of scores. Median - the middle point of a distribution of scores (half the scores fall below the median and half the scores fall above the median). Mean - the arithmetic average of a distribution of scores. 6 Results With One Variable Measures of Variation Another characteristic of a distribution is its spread, dispersion or variability around the center. Researchers measure variation in three ways: Range - the largest and smallest scores within a distribution of scores; the simplest way of measuring variation. Percentile - indicate the score at a specific place within a distribution of scores. Standard Deviation - a statistic based on the mean and gives an average distance between all scores and the mean. 7 Results With Two Variables Bivariate Relationship - Considers two variables together and their relationship. Bivariate Statistics - statistics which describe the relationship between two variables. Statistical Relationship - when variables appear together and are associated (they co-vary). Statistical relationships are based on two ideas: Covariation Independence 8 Results With Two Variables Bivariate Tables - The bivariate percentaged table presents the same information as a scattergram in tables that are based on cross tabulation and usually contain percentages. Bivariate Percentaged Table - a statistical table based on cross- tabulation; that is, the cases are organized in the table on the basis of two variables at the same time. Bivariate tables usually contain percentages. Cross Tabulation - the technique of intersecting two or more variables so that the cases are organized in the same table at the same time. 9 Results With Two Variables Measure of Association - a single number that expresses the strength, and often the direction, of a relationship. Proportionate Reduction in Error (PRE) - the logic which underlies most measures of association. It asks the question: How much does knowledge of one variable reduce the errors that are made when guessing the values of the other variable? 10 Inferential Statistics Inferential Statistics A genre of statistics that uses probability theory to test hypotheses formally, permit inferences from a sample to a population, and test whether descriptive results are likely to be due to random factors of to a real relationship. 11 Statistical Significance Statistical Significance - the foundation of inferential statistics. It means that results are not likely to be due to chance factors. It indicates the probability of finding a relationship in the sample when there is none in the population. Level of Statistical Significance - a way of talking about the likelihood that statistical analysis results are due to chance factors (a relationship appears in the sample when there is none in the population). 12 Type I and Type II Errors Type I Error Occurs when the researcher says that a relationship exists when in fact none exists. It means falsely rejecting a null hypothesis. Type II Error Occurs when a researcher says that relationship does not exist, when in fact it does. 13