Chapter 16

Statistical Analysis

DR. JOE NJOROGE

 

Chapter Outline

}  Descriptive Statistics

}  Inferential Statistics

}  Other Multivariate Techniques

}  Quick Quiz

 

Descriptive Statistics

}  Descriptive Statistics – statistical computations describing either the characteristics of a sample or the relationship among variables in a sample.

}  Data Reduction

 

}  Measures of Association

 

}  Proportionate Reduction of Error (PRE) – a logical model for assessing the strength of a relationship by asking how much knowing values on one variable would reduce our errors in guessing values on another variable.

 

Descriptive Statistics

}  Nominal Variables

}  Lambda (λ)

 

}  Ordinal Variables

}  Gamma (γ)

 

}  Interval and Ratio Variables

}  Pearson (r)

 

 

 

Descriptive Statistics

}  Regression Analysis – a method of data analysis in which the relationships among variables are represented in the form of an equation, called a regression equation.

 

}  Linear Regression Analysis – a form of statistical analysis that seeks the equation for the straight line that best describes the relationship between two ratio variables.

 

}  Multiple Regression Analysis – a form of statistical analysis that seeks the equation representing the impact of two or more independent variables on a single dependent variable.

Descriptive Statistics

Descriptive Statistics

}  Linear Regression

 

}  Regression Line

 

}  Unexplained Variation

 

}  Explained Variation

Descriptive Statistics

}  Multiple Regression

}  Partial Regression Analysis – a form of regression analysis in which the effects of one or more variables are held constant, similar to the  logic of the elaboration model.

 

}  Curvilinear Regression Analysis – a form of regression analysis that allows relationships among variables to be expressed with curved geometric lines instead of straight ones.

Inferential Statistics

}  Inferential Statistics – the body of statistical computations relevant to making inferences from findings based on sample observations to some larger population.

 

Inferential Statistics

}  Univariate Inferences

}  Cautions about Making Inferences

              The sample must be drawn from the population about which inferences are being made.

              The inferential statistics assume several things: (a) simple random sampling, (b) sampling with replacement, (c) 100 percent completion rate

              Inferential statistics are addressed to sampling error only, not nonsampling error.

}  Tests of Statistical Significance

}  Statistical Significance – a general term referring to the likelihood that the relationship observed in a sample could be attributed to sampling error alone.

 

}  Tests of Statistical Significance – a class of statistical computations that indicate the likelihood that the relationship observed between variables in a sample can be attributed to sampling error alone.

}  The Logic of Statistical Significance

              Assumptions regarding the independence of two variables in the population study

              Assumptions regarding the representativeness of samples selected through conventional probability-sampling procedures

              The observed joint distribution of sample elements in terms of the two variables

}  Level of Significance – in the context of tests of statistical significance, the degree of likelihood that an observed, empirical relationship could be attributed to sampling error.

}  A relationship is significant at the .05 level if the likelihood of its being only a function of sampling error is no greater than 5 out of 100.

}  Chi-Square

}  Based on the null hypothesis.

 

}  Computation:

}  For each cell in the table, subtract the expected frequency for that cell from the observed frequency.

}  Square the quantity.

}  Divide the squared difference by the expected frequency.

 

}  Chi-Square Table

 

Inferential Statistics

}  t-Test

}  Measure for judging the statistical significance of differences in group means.

 

}  Logic:

}  The value of t will increase with the size of the differences between means.

}  The value of t will also increase with the size of the sample involved.

}  The value of t will be larger when variations of values within each group are smaller.

}  Caution…

}  There are no objective tests of substantive significance (only objective significance).

}  Statistical significance is only appropriate for samples, and not for whole populations.

}  Tests of significance are based on the same sampling assumptions used to computer confidence intervals.

Other Multivariate Techniques

}  Path Analysis – a form of multivariate analysis in which the causal relationship among variables are presented in a graphic format.

 

}  Time-Series Analysis – an analysis of changes in a variable over time.

 

}  Factor Analysis – a complex algebraic method for determining the general dimensions of factors that exist within a set of concrete observations.

 

}  Analysis of Variance (ANOVA) – method of analysis in which cases under study are combined into groups representing an independent variable, and the extent to which the groups diff from one another is analyzed in terms of some dependent variable. Then, the extent to which the groups differ is compared with the standard of random distribution.

 

}  Discriminant Analysis – method of analysis similar to multiple regression, except that the dependent variable can be nominal.

 

}  Log-Linear Models – data analysis technique based on specifying models that describe the interrelationships among variables and then comparing expected and observed table-cell frequencies.

}  Geographic Information Systems (GIS) – analytic technique in which researchers map quantitative data that describe geographic units for a graphic display.