Statistics Descriptive and Inferential Data is numerical Statistics

  • Slides: 18
Download presentation
Statistics: Descriptive and Inferential

Statistics: Descriptive and Inferential

Data is numerical

Data is numerical

Statistics n A set of mathematical techniques used by social scientists to organize and

Statistics n A set of mathematical techniques used by social scientists to organize and manipulate data for the purpose of answering questions and testing theories

Variable n Any trait that can change values from case to case

Variable n Any trait that can change values from case to case

Independent Variable Dependent Variable

Independent Variable Dependent Variable

Descriptive Statistics 1) 2) When the researcher needs to summarize or describe the distribution

Descriptive Statistics 1) 2) When the researcher needs to summarize or describe the distribution of a single variable When the researcher wishes to understand the relationship between two or more variables

Data Reduction n n Process of allowing a few numbers to summarize many numbers

Data Reduction n n Process of allowing a few numbers to summarize many numbers Is the basic goal of single-variable (or univariate) descriptive statistical procedures

Measures of Association n n Understand the relationship between two or more variables Allow

Measures of Association n n Understand the relationship between two or more variables Allow to quantify the strength and direction of a relationship

Inferential Statistics n n n Wish to generalize findings from a sample to a

Inferential Statistics n n n Wish to generalize findings from a sample to a population Population – total collection of all cases that the researcher wishes to understand better Involves using information from samples (carefully chosen subsets of the defined populations) to make inferences about populations

Discrete Variable n n It has a basic unit of measurement that cannot be

Discrete Variable n n It has a basic unit of measurement that cannot be subdivided Eg. # of people per household

Continuous Variable n n If the measurement can be subdivided infinitely Eg. time Always

Continuous Variable n n If the measurement can be subdivided infinitely Eg. time Always approximating and rounding off the scores Reported as discrete

Level of Measurement n n n Nominal Ordinal Interval-ratio (I/R)

Level of Measurement n n n Nominal Ordinal Interval-ratio (I/R)

Nominal n n n Classification into categories is the only measurement procedure permitted Not

Nominal n n n Classification into categories is the only measurement procedure permitted Not numerical Compared to each other only in terms of the number of cases classified in them

Nominal n n Categories not higher or lower along some numerical scale Eg. gender,

Nominal n n Categories not higher or lower along some numerical scale Eg. gender, religious affiliation Mutually exclusive and exhaustive Categories are relatively homogeneous

Ordinal n n Classify into categories Allow categories to be ranked High to low,

Ordinal n n Classify into categories Allow categories to be ranked High to low, more or less than another Eg. SES: upper class, middle class, working class, lower class

Ordinal n n n Represents only a position The distance between the scores cannot

Ordinal n n n Represents only a position The distance between the scores cannot be described in precise terms Averages cannot be used

Interval-Ratio (I/R) n n n They are measured in units that have equal intevals

Interval-Ratio (I/R) n n n They are measured in units that have equal intevals Eg. age, # of siblings Have a true zero n n Zero indicates the absence or complete lack of whatever is being measured Eg. education, income

Levels of measurement is the first guideline to use in selecting a statistic

Levels of measurement is the first guideline to use in selecting a statistic