5.Creating_Quality_Selection_Measures

5.Creating_Quality_Selection_Measures - Creating Quality...

Info iconThis preview shows pages 1–14. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Creating Quality Selection Measures MGT 315 Scott Class Agenda p Judging the quality of selection measures n Reliability n Validity n Generalizability n Legality p Spotlight on causal inference Organizing Model Selection p The process by which companies decide who will or will not be allowed into the organization p Takes the pool of applicants delivered by recruitment and selects a subset Selection p Hopefully we recruited people with the KSAOs needed for the job. Now we measure people on them by assigning each a number (good or bad): n Ex: 4.5 out of 7 on a creativity scale n Ex: 75 out of 100 on an intelligence measure n To get that number we use various measures, tests, and instruments p How do we create “good” measures or know that the measures we are using are good? Selection p “Good” selection measures must be: n Reliable n Valid n Generalizable n Legal Reliability p The degree to which a measure is free of random error n A score on any measure has two components: the “true score” – random error. Sources of random error: p Interviews: unusual circumstances, distractions p Tests: poorly worded questions, scoring mistakes p Surveys: item ambiguity, judgment calls p References: mood of reference giver Reliability p Reliability is calculated by correlating “measurement repetitions” n Repetition in Items p Example: Give an applicant a survey that asks the same kinds of items multiple times; correlate the answers to the items – are they the same? n Repetition in Times p Example: Give a test to an applicant multiple times, correlate the results – are the scores similar? n Repetition in Raters p Example: Interview applicants with multiple interviewers; correlate their scores – do they agree on each applicant? p What does “correlate” mean, exactly? The Correlation Coefficient (r) p A perfect positive relationship is 1 p A perfect negative relationship is –1 p The strength of the correlation is inferred by judging the compactness of a scatterplot of the X and Y values p More compact=stronger correlation p Less compact=weaker correlation Correlation: r = 1 2 4 6 8 10 12 2 4 6 8 10 Variable X Variable Y Correlation: r = .70 2 4 6 8 10 12 2 4 6 8 10 Variable X Variable Y Correlation: r = .30 2 4 6 8 10 12 2 4 6 8 10 Variable X Variable Y Correlation: r = 0 2 4 6 8 10 12 2 4 6 8 10 Variable X Variable Y p...
View Full Document

This note was uploaded on 10/17/2011 for the course ECON 101 taught by Professor Thompson during the Spring '11 term at Michigan State University.

Page1 / 42

5.Creating_Quality_Selection_Measures - Creating Quality...

This preview shows document pages 1 - 14. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online