1977
DOI: 10.1080/768370956
|View full text |Cite
|
Sign up to set email alerts
|

Some comments on the need for mathematics in estimating bias

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2003
2003
2018
2018

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(3 citation statements)
references
References 0 publications
0
3
0
Order By: Relevance
“…Among all three firm classes over the entire study period, the analysis of variance shows significant variation in persistence rates (F ϭ 191.57, p Ͻ 0.001). The persistence rates among firm size classes do not strictly conform to the equal variances assumption, however minor departures are permitted when sample numbers are large enough and groups are of equal size, as is the case here (Clark & Hosking, 1986;Norcliffe, 1977). The residuals show moderate negative skewness, owing to three low outliers amongst the small firm size class.…”
Section: Firm Size Business Cycles and Transience In Ontariomentioning
confidence: 68%
“…Among all three firm classes over the entire study period, the analysis of variance shows significant variation in persistence rates (F ϭ 191.57, p Ͻ 0.001). The persistence rates among firm size classes do not strictly conform to the equal variances assumption, however minor departures are permitted when sample numbers are large enough and groups are of equal size, as is the case here (Clark & Hosking, 1986;Norcliffe, 1977). The residuals show moderate negative skewness, owing to three low outliers amongst the small firm size class.…”
Section: Firm Size Business Cycles and Transience In Ontariomentioning
confidence: 68%
“…In the construction of frequency distribution tables, Norcliffe [35] method was used to determine the number of classes.…”
Section: Discussionmentioning
confidence: 99%
“…Table 4 shows that household sizes in the study area were grouped into three, according to Norcliffe [35] method of classification, namely 1-5, 6-10, 11 & above with 14%, 26% and 60% of the total respondents respectively. The result indicates that the third group (11 & above) with more than 10 persons per household has the highest number of respondents.…”
Section: Household Size Of the Respondents In The Study Areamentioning
confidence: 99%