1 Empirical research usually uses some type of analysis CHAPTER 11 INTERPRETING DATA 2 Empirical research is first and foremost a rather than a operation a Statistical a Logical mathematical 3 statistics are used to summarize and otherwise describe date in manageable forms 4 Descriptive statistics are used to data under study 5 statistics help researchers form conclusions from their observations typically that involves forming conclusions about a population from the study of a sample drawn from it 6 Inferential statistics allow researchers to use to make about populations a Sample data statements 7 What is the purpose of Univariate analysis 8 What is the purpose of bivariate analysis and multivariate analysis a Descriptive a Summarize a Inferential a To DESCRIBE a To EXPLAIN 9 What is a type of univariate description a Frequency distribution 10 What are types of measures of central tendency a Mean median mode 11 Descriptive statistics represent a method for presenting descriptions in a manageable form 12 The simplest statistics describe some type of average and dispersion for a single variable known 13 analysis refers to descriptions of two variables and analysis examines relationships among three or more variables a Bivariate analysis multivariate analysis 14 analysis explain subjects scores on one variable by referencing their scores on another a Quantitative as analysis a Univariate variable a Bivariate 15 In a the values of the dependent variable depend on the values of the independent variable a Contingency table 16 What are the 3 steps in constructing a contingency table a 1 Divide cases into groups based on IV and make a column for each group b 2 Make a row for each possible score on the DV c 3 Enter the percentage of cases in each column that fall in each row 17 How do you read a contingency table a Take ROW score of the DV and compare of different IV groups in that ROW 18 Researchers can assess the because the causes must be associated with their effects a Statistical conclusion validity 19 In your sample X and Y may be associated by CHANGE because of what 20 The distribution is a description of the number of times the various attributes of a variable are 21 Measures of are statistical measures that express how observations are clustered in a a Sampling error observed in a sample a Frequency distribution a Central tendency 22 Measure of central tendency data to an easily manageable form but they do not covey the of the original data a Reduce details a Mode observations a Mean a Median a Dispersion a Range b Standard deviation a Distribution average values a Range a Variability a Standard deviation you would have more a Larger variability 23 The is the most frequent attribute either grouped or ungrouped 24 The arithmetic is the sum of values for all observations divided by the number of 25 The is the middle attribute in the ranked distribution of observed attributes 26 is the distribution of values around some central values such as an average 27 What are the types of measures of dispersion 28 Measures of dispersive give a summary indication of the of cases around an value 29 The simplest measure of dispersion is the the distance separating the highest from the lowest 30 When describing the range the bigger the number the more 31 can be described as the average amount of variation about the mean 32 If the numbers scores are more spread out you would have a standard deviation meaning 33 The standard deviation measure of dispersion is based on the Deviations from the mean 34 The sum of squared deviations from the mean divided by the number of cases is called the 35 Taking the square root of the produces the standard deviation 36 When the numerical value of the standard deviation is high and that for the mean is low the is not a good measure of central tendency 37 Medians should be calculated for only data Means should be calculated for only data 38 If the variable in question is gender what are appropriate measures to use a Raw numbers or percentage marginal 39 are descriptive statistics that standardize some measure for comparative purposes 40 When must researchers standardize measures in order to draw comparisons a When population sizes differ 41 What is the purpose of subgroup descriptions a Comparative to imply some causal connections 42 If the table is percentaged down read If the table is percentaged across read 43 analysis is a method of analyzing the simultaneous relationships among several variables and may be used to more fully understand the relationship between two variables a Squared a Variance a Variance a Mean a Interval ratio a Rates a Across down a Multivariate 44 When we generalize from samples to larger populations we use statistics to test the significance of an observed relationship a Inferential 45 statistics are used to estimate the generalizability of findings arrived at in the analysis of a sample to the larger population from which the sample has been selected a Inferential 46 Inferences about a characteristic of a population must contain what two things a Confidence interval range within which the value is expected to be b Confidence level likelihood that the values does actually fall within the range 47 During inferential statistics the must be drawn from the population about which inferences are being made it must assume sampling apply to only a Sample simple random sampling error 48 estimate the likelihood that an association as large as the observed one could result from normal sampling error if no such association exists between the variables in the larger population a Tests of statistical significance 49 The is the unlikeliness that relationships observed in a sample could be attributed to 50 The statistical significance of a relationship observed in a set of sample data then is always 51 0 05 level of P the probability of a relationship as strong as the observed one being attributable to sampling error alone is no more than sampling error alone a Statistical significance expressed in terms of a Probabilities i 05 5 in 100 ii 0 01 1 in 100 iii 001 1 in 1 000 a Substantive variables in a population a Null hypothesis relationship a Empirically expect a Inverse function smaller a Whole populations 52 significance means that an observed association is strong important or meaningful 53 Chi square is based on the the assumption that there is no relationship between two 54 Chi square compares what you get with what you given a null hypothesis of
View Full Document
Unlocking...