Assigning numbers or scores to the attributes or traits of an individual 

• need clear and consistent basis asigning numbers to applicants 
• numbers provide a convenient means for characterizing and diferentiationg among job applicants 

We don't measure the person but rather their attributes or traits 

• psychological- personality intelligence 
• physical-upper body strengths, cardiovascular enduranced 

a measure of an employee attribute identified through a job analysis as being important for job success 

• personality test, interviews, biographical data questionnaires, applicantion blanks, and assessment centers 

Use measures of job performance to validate predictors and verify that the predictors are job related.

• Organizational issues: absenteeism, turnover, citizenship behaviors (OCB), trainability
• Work-related outcomes: error rates, productivity counts, total sales, speed, supervisory ratings (e.g.,1 – 5 pt scale)

Precision of Measurement

Determined by the number of distinct scores permitted by the predictor and criterion used

Greater precision allows the use of more sophisticated statistical analyses

Scales of Measurement

Provide a means by which individuals can be distinguished from one another on a variable of interest

• Classification of success v. degree of success
• Classification: Pass / Fail a training program
• Degree: Performance on a training performance test

Nominal Scale

Allows individuals or objects to be assigned to a group/category

• All individuals having a common characteristic are assigned to the same category
• Gender: Female = 0; Male = 1
• Race: Caucasian = 1, African American = 2, Hispanic = 3 

• Individuals can belong to only one category or class
• Numbers carry no numerical meaning
• Only stats possible are frequency counts and percentages
• Mean of race = .75?

• Nominal
• Ordinal
• Interval
• Ratio

Scales get progressively more sophisticated in terms of what you can do statistically

Ordinal Scale

• Ranks objects, such as individuals, from “high” to “low” on some variable of interest.
• Individuals are assigned a number and differences between the numbers indicate the relative position of individuals for the variable on which they are ranked
• Does not provide information on the magnitude of the differences among the rankings
• Can only draw “greater than” or “less than” (> or <) inferences from ordinal data

Interval Scale

• Uses constant (equal interval) units of measurement that represent meaningful rank-order differences
• Difference between 40 and 60 is same as difference between 60 and 80 on math test
• Has an arbitrary zero point
• Someone who scores 80 does not have twice as much math ability as someone who scores 40
• Can’t say that someone who scores 0 has 0 math ability
• Frequently used scale for predictors and criteria
• Likert-scales are on an interval scale (1 – 5 point)
• Helpful for measuring psychological traits
• Can perform statistical procedures such as mean, standard deviation, and correlation

Ratio Scale

• Has an absolute zero point
• Zero means zero
• Has numerical values that can be added, subtracted, multiplied, and divided (can do any math operation on a ratio scale)
• Is not often encountered in HR selection because KSAs are more often psychological rather than physical in nature
• Widgets produced : EE 1: 50 widgets; EE 2: 100 widgets
• May see a ratio scale on the criterion side (productivity counts or sales)

All persons assessed are measured by the same information or content

• Format - e.g., multiple choice, essay, interview /
• Medium – e.g., paper and pencil v. computer
• ADA accommodations
• standardization of selection measurement 

Administration

Information is collected the same way in all locations and across all administrators

• standardization of selection Measurement 

Scoring

Rules for scoring are specified before administering the test and are applied the same way with each application

• standardization of selection measurement 

Predictors 

Measure used in Hr Selection 

Tests designed to measure important KSAs for the job

• Background information - previous life and work experience
• Application forms
• Reference checks
• Biographical data questionnaires

Interviews – KSAs, Person/Organization fit

• Tests – assessing specific KSAs
• Aptitude/ability – e.g., intellectual, mechanical, motor
• Achievement – e.g., job knowledge
• Personality – identify who will work harder or cope better on     the job

criteria 

Mearues of used in Hr selection 

Measures of behavior or performance on the job that are used to evaluate the predictors used to forecast performance.

• Objective production data
• Personnel data
• Absenteeism, voluntary turnover
• Judgmental data
• Performance appraisal ratings
• Job or work sample data
• Performance on a sample of the work – e.g., typing test
• Training proficiency data
• Success in a training program