MULTIPLE-REGRESSION ANALYSIS OF HOUSEHOLD TRIP GENERATION-A CRITIQUE

Abstract

MULTIPLE-REGRESSION ANALYSIS OF TRIP GENERATION BASED ON DATA AGGREGATED TO THE ZONAL-AVERAGE LEVEL IS DISCUSSED WITH RESPECT TO ITS DESCRIPTIVE AND PREDICTIVE ACCURACY. THE VALIDITY OF THE MAJOR ASSUMPTIONS UNDERLYING THIS METHODOLOGY IS EXAMINED. CERTAIN STATISTICAL CHARACTERISTICS OF THE ZONE SAMPLING DISTRIBUTIONS ARE EXAMINED IN ORDER TO DETERMINE: (1) THE ACCURACY AND RELIABILITY OF THE MEAN AS A REPRESENTATIVE MEASURE OF THE INDIVIDUAL HOUSEHOLD TRIP- GENERATION RATES AND SOCIOECONOMIC CHARACTERISTICS, AND (2) THE RELATIVE HOMOGENEITY OF ANALYSIS ZONES WITH RESPECT TO HOUSEHOLD TRIP-GENERATION RATES AND SOCIOECONOMIC CHARACTERISTICS. SOURCES OF VARIATION IN HOUSEHOLD TRIP- GENERATION RATES AND SOCIOECONOMIC CHARACTERISTICS ARE ANALYZED TO EVALUATE THE EFFECT OF DATA AGGREGATION ON THE EXPLANATIVE ABILITY OF TRIP-GENERATION EQUATIONS. THE ZONE- SAMPLING DISTRIBUTIONS EXHIBITED A CONSIDERABLE DEGREE OF DISPERSION AND SKEWNESS, RATHER THAN NORMALITY, IMPLYING THAT ZONAL AVERAGES ARE NOT TRULY REPRESENTATIVE OF THE INDIVIDUAL HOUSEHOLD TRAITS. THE MAJORITY OF THE RESIDENTIAL ZONES WERE RELATIVELY HETEROGENEOUS WITH RESPECT TO HOUSEHOLD TRIP-GENERATION RATES AND SOCIOECONOMIC CHARACTERISTICS. THIS FINDING REFUTES THE VALIDITY OF THE COMMONLY ACCEPTED ASSUMPTION OF ZONAL HOMOGENEITY. THE AGGREGATION OF INDIVIDUAL HOUSEHOLD TRIP-GENERATION RATES TO ZONAL AVERAGES LEFT ONLY A SMALL PERCENTAGE OF VARIATION FOR USE IN FITTING THE REGRESSION EQUATION, THEREBY REDUCING THE EXPLANATIVE ABILITY OF THE RESULTING EQUATION. WHEN MULTIPLE -REGRESSION ANALYSIS PRECEDED AGGREGATION OF THE DATA, THE RESULTING TRIP-GENERATION EQUATION EXPLAINED A GREATER PERCENTAGE OF THE TOTAL VARIATION IN THE DEPENDENT VARIABLE WITHOUT SACRIFICING ANY SIGNIFICANT DEGREE OF ACCURACY IN DESCRIBING EXISTING DATA. /AUTHOR/

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 23 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.