document resume mccall, chester h.; walters, lauren e ... · document resume. ed 419 839 tm 028...
TRANSCRIPT
DOCUMENT RESUME
ED 419 839 TM 028 415
AUTHOR McCall, Chester H.; Walters, Lauren E.TITLE Words and Their Value to the Survey Researcher.PUB DATE 1998-04-00NOTE 27p.; Paper presented at the Annual Meeting of the American
Educational Research Association (San Diego, CA, April13-17, 1998).
PUB TYPE Reports - Research (143) -- Speeches/Meeting Papers (150)EDRS PRICE MF01/PCO2 Plus Postage.DESCRIPTORS Administrators; *Definitions; Engineers; *Graduate Students;
Higher Education; *Research Methodology; Responses;*Surveys; Tables (Data); *Test Construction; Test Items;*Undergraduate Students
IDENTIFIERS *Quantifiers
ABSTRACTIn May 1972, 2,900 copies of a survey were distributed
eliciting opinions about the meaning of some qualifying adjectives andphrases commonly used in "verbal communications." These same adjectivephrases are commonly used in survey research. They include phrases such as "afew," "a majority," "nearly all," and other quantifiers. The 1972 survey hada 40% response rate, indicative of interest in the study. This study updatesthat 1972 study, reporting findings from different groups of subjects. Ninegroups (graduate students in several disciplines, including education,undergraduates, and engineers and administrators) ranging in size from 3 to20 members were surveyed. Results made it clear that individuals withindifferent groups give different interpretations to quantifying phrases, andthat differences also exist among groups. It is suggested that there is aneed to study item reliability in surveys in more detail if words andphrases, such as the 22 identified in this study, are to be included inresponse options, narrative instructions in a survey, or reporting on thesurvey findings. Appendix A is the report from the 1972 survey, and AppendixB contains a copy of the original survey form. (Contains five tables, eightfigures, and three references.) (SLD)
********************************************************************************* Reproductions supplied by EDRS are the best that can be made *
* from the original document. *
********************************************************************************
00
WORDS AND THEIR VALUE
TO THE
SURVEY RESEARCHER
Chester H. McCallGraduate School of Education and Psychology
Pepperdine UniversityCulver City, CA 90230
Lauren E. WaltersTeacher
Los Angeles Unified School District
U.S. DEPARTMENT OF EDUCATIONOffice of Educational Research and Improvement
ED ATIONAL RESOURCES INFORMATIONCENTER (ERIC)
This document has been reproduced asreceived from the person or organizationoriginating it.
Minor changes have been made toimprove reproduction quality.
Points of view or opinions stated in thisdocument do not necessarily representofficial OERI position or policy. 1
American Educational Research AssociationLO 1998 Annual Meetingd. San Diego, CACO
April 13-17, 1998
I
AERA\1998.doc
PERMISSION TO REPRODUCE ANDDISSEMINATE THIS MATERIAL HAS
BEEN GRANTED BY
C. mcCQ I I
TO THE EDUCATIONAL RESOURCESINFORMATION CENTER (ERIC)
[email protected] 4/3/98
WORDS AND THEIR VALUE TOTHE SURVEY RESEARCHER
DESCRIPTORS:Survey research, research methodology, validity/reliability, instruments
Background
In May of 1972, 2,900 copies of a survey were distributed eliciting opinions regarding the meaning ofsome qualifying adjectives/phrases commonly used in "verbal communications." These sameadjectives/phrases are commonly used in survey research. John Hoyt (1972) in his report emphasizes theproblems which arise when using some of these words and/or phrases, particularly when decisions mightbe made based upon an interpretation of what these qualifying adjectives/phrases might mean. In the 1972paper, the author does not identify how the 2,900 initial sample was selected. He indicates that withinthree weeks a 40% response was obtained, "demonstrating that there was 'rather considerable' interest inthe subject." Stanley Payne (1951) in his provocative book points out how important it is in developinganinstrument with questions that the meanings of the allowable responses be as clear as possible. PaulScipione (1995) in his timely article includes the following introductory comments:
"Those of us who design and direct research studies spend so much time with numbers that weoften forget that words also represent values (in the minds of the writer as well as the readers;authors comments). Yet both the questionnaires we use to elicit information from respondentsand the reports we use to communicate research findings and recommendations to clients dependsignificantly on language."
He goes on to make several additional points which, independently, have been raised after more than 15years of survey research involvement by the author of this paper:
We speak of a substantial change rather than indicating the numerical amount of the change;We convert descriptive words to numerical values and develop descriptive statistics, such asaverages, to discuss the findings; and,We make considerable use of descriptive words and phrases, such as a lot, many, orfrequently, in providing a report on the findings of a survey.
The descriptive results of the 1972 study appear as Appendix A to this paper. A copy of the initial surveyform appears as Appendix B. It is important to note that these two appendices are exactly as reported byJohn Hoyt in 1972.
Objectives/Purposes
Believing strongly that the 1972 results have probably not changed much and, because of the author'sinterest in using surveys to collect useful information in educational research and for makingmanagementdecisions both within education and elsewhere, the author received release time from his educationalinstitution to collect additional data using the same survey and the same set of instructions. Had the authorbeen aware of the Scipione (1995) study at the time of his research, the items used on the instrument mighthave been slightly modified; although, from a research perspective, a replication of the exact instrumentand instructions (Hoyt, 1972) seemed most appropriate.
The purpose of this study was to update the 1972 study and to report findings from groups of differentsubjects. It was hypothesized that individuals who might become subjects for surveys would continue toattach different meanings or interpretations to the words and phrases in the original study, creating a needfor an awareness on the part of those using the survey results about the possible differences ininterpretation of the words and phrases, not only as instruments are developed but also as the results arereported.
AERA\PAPER-98.DOC PAGE - 1 3 4/6/98
Perspectives/Theoretical Framework
Of considerable concern in survey research is assessing the reliability and validity ofan instrument andalso items on the instrument. In the context of this paper, reliability of an item is the extent to which theitem means the same thing to all respondents at a given time and the same thing to an individual respondentat different points in time. It is generally agreed that survey results may be, essentially, worthless if theindividual items on the instrument are unreliable and invalid. This paper addresses the reliability issue interms of the way in which words or phrases used in assessing opinions or perceptions may be interpretedby the respondent and, hence, interpreted and reported by the researcher. The instrument used in the 1972study and again in this study contains 22 items.
Methods. Techniques. Modes of Inquiry
Unlike the 1972 study in which the sampling procedure was not clearly identified, the intent of thisreplication was to utilize individuals from nine different groups to address two questions:
Do those responding today produce similar results (in terms of averages, medians, modes,ranges, and distributions) to those obtained in 1972?Is there a difference in the response patterns among nine different groups?
The instrument was administered in a group setting by the author and by three other faculty members at asingle institution. Because of the ambiguity of the 1972 instrument (Appendix B), faculty explained whatwas expected in assigning numerical values to the verbal descriptions. Data were coded, entered onto anEXCEL spread sheet and imported into NCSS 97© 6.0 for Windows, a statistical analysis softwarepackage.
Data Sources or Evidence
The nine groups from which data were collected were:
1. A research class at the doctoral level, fail 1995.2. A special class of doctoral students studying "organization change," fall 1995.3. A research class at the doctoral level, winter 1996.4. Undergraduate students in a communications major, fall 1995.5. An education faculty associated with graduate programs, winter 1996.6. A third research class at the doctoral level, winter 1996.7. A masters class majoring in educational administration, winter 1996.8. A masters class in research with students primarily in teacher training education, spring 1996.9. A group of engineers and administrators in the management construction business during a
seminar on survey methods, summer 1996.
The nine groups above ranged in size from nine to twenty three individuals. After data were coded andsummary statistics obtained, individual responses were reviewed for logic and consistency. In three casesthe results were discarded because the respondent apparently did not understand the directions.
AERA\PAPER-98.DOC PAGE - 2 4/6/98
4
Results and/or Conclusions/Point of View
Summary statistics for the 1972 data appear as Appendix C. Appendix D (Tables 1 through 5) indicate foreach of the nine groups and each of the 22 quantifying phrases, the following statistics:
Arithmetic mean (average)MedianModeThe range of reported valuesThe minimum and maximum reported values
It is interesting to note, for selected quantifying phrases and the arithmetic mean, median, and minimumand maximum values, comparisons among the nine groups and the Hoyt (1972) study:
ARITHMETIC MEANHoyt 1 2 3 4 5 6 82 9
A few 8.31 7.4 17.1 9.8 3.9 17.4 8.2 10.1 6.4Many 31-40' 54.3 45.7 51.7 30.4 50.3 49.9 45.8 44.9A majority 51-55 59.8 56.7 56.9 57.9 56.6 66.4 68.7 56.8Nearly all 86-90 95.4 87.8 94.7 85.8 84 95.5 88.1 85.6
MODE'A few 10 3 3 3 3 5 3 3Many 40 50 80 60 40 25A majority 51 51 51 51 51 51 51 51 51Nearly all 90 98 90 95 95 90
MAXIMUM AND MINIMUMA few N /A' 0-25 3-80 3-50 2-12 3-80 2-25 3-60 0-30Many N/A 20-100 15-80 10-100 4-80 20-90 20-99 6-90 5-100A majority N/A 51-90 51-90 10-90 10-99 51-90 51-100 40-98 25-100Nearly all N/A 90-99 20-98 85-99 20-99 0-99 89-99 5-99 25-99
1 - For some reason, Hoyt reported, for some phrases, the arithmetic mean as a range of values.2 - Data from Group 7 in Appendix D appear to be entered in error and have not been included in this table.3 - Due to small samples the mode did not exist in some of the groups.4 - Hoyt did not report ranges.
Detail for the other phrases and groups are reported in Appendix D.
To give a flavor of the specific relative frequency of responses, Appendix E contains histograms for thefollowing phrases:
A coupleA fewA majorityA substantial majorityNumerousLotsA large proportion ofVirtually all
AERA\PAPER-98.DOC PAGE - 3 4/6/98
5
Even if we assume that some of the respondents may not have understood the directions or were "jokingaround," the results still are unnerving and suggest the need for great caution in using quantifying phrasesin both the body of surveys and reporting the findings of surveys.
It is quite clear that individuals within groups give different interpretations to quantifying phrases andamong groups differences also exist. It is suggested, although not necessarily supported by the data in thisstudy, that different professions might exhibit differences in not only location statistics but also ranges.
Educational or Scientific Importance of the Study
It is clear to the author that the diverse opinions with respect to the meaning of many of the "quantifying"words and phrases are pause for reflection on how we are analyzing and reporting survey results. It issuggested that there is a need to pursue further the issue of item reliability if words and phrases, such as the22 identified in this study, are to be included in response options, in narrative instructions in a survey, or inreporting on the survey findings.
REFERENCES
Hoyt, J. S. (1972). Do quantifying adjectives mean the same thing to all people? AgriculturalExtension Services: University of Minnesota.
Scipione, P. A. (1995). The value of words: numerical perceptions associated with descriptive wordsand phrases in market research reports. Journal of Advertising Research, May/June 1995.
Payne, S. L. (1951). The art of asking questions. Princeton, NJ: Princeton University Press.
NOTE: Scipione's paper includes 17 excellent references related to both verbal and visual presentations ofitems associated with questionnaires and their analyses.
ARRA\PAPER-98.DOC PAGE - 4 4/6/98
RESULTS OF THE SURVEY
General
APPENDIX A
The first, and probably strongest, point to be made in looking at the surveyresults is that, despite the large number of valid responses (1180) and thelarge rate of return (40%) to the survey, no claim is made for the precisionof the results. Indeed, the most valid single conclusion that can be drawnis that the quantifying adjectives used in the survey represent to the sampleof respondents surveyed a broad range of numbers. It is also clear that thecontext in which the adjective is used may be as relevant to the quantity impliedas is the quantifying phrase itself. In addition; the results suggest to all whoverbalize quantitative data that they ought to be as precise as possible and, tothose of us who listen to verbalized data, to insist that the speaker injectprecision into his verbalizations.
The meanings of the quantifying adjectives are summarized briefly in figure 1and graphically in figures 2 through 25. In addition, for those who are con-cerned with additional statistical analysis a printout of the 1180 valid responsesfor each of the quantifying adjectives is available from MAPS.
The graphical representations, in addition to presenting the distribution of theresponses, also show three statistics for each response. First, the "mode"which is simply the discrete number that appeared most often for each adjective.Second, the "median" which is the number in the series of responses that representsa point such that half of the numerical responses fall on one side of it and halfon the other side. Third, the "mean" which is the sum of all of the responsesdivided by the number of responses. The mean is also frequently referred to as
. the "average" response. To illustrate, if a group of 9 numerical responses were:1,1,2,2,3,4,4,4,6 --then the mode would be 4 (the most frequent response); themedian would be 3 (there are as many responses below 3 as there are above 3);and the mean would be 3 (the sum of all the responses, 29, divided by the numberof responses, 9).
Another general observation about the responses is that, with the exception ofquantifying adjectives which represent numbers less than 10 or numbers greaterthan 90, the most frequent responses fell on numbers divisible by 5. There are
. two other exceptions to this observation; the phrase 'a minority' and the phrasea majority' are subject to rather precise statistical definition and the responses
were, as one would expect, most frequently given as these two single numbers.For responses where the quantifying adjective has a mode of 90 or above therewere relatively frequent usages of the numbers 95, 98, and 99 and a relativelyinfrequent choice of the other discrete numbers between 90 and 100.
APPENDIX B
Out of a total of 100 items (votes, apples, dollars, opinions, or what haveyou) place a number in the right hand column that represents your under-standing of each of the following descriptors. (Please use only one wholenumber as your "best" answer; no decimals, fractions, or ranges). -Remember,enter the whole number out of 100(%) for each description.
Descriptor Number it Represents
"A few"
"Damn few"
"A couple"
"Lots"
"A majority"
"Several"
"Many"
"Most"
"Almost all"
"Hardly-any"
"A substantial majority"
"A significant number of . . ."
"Virtually all"
"Almost none"
"A small number of"
"Numerous"
"Nearly all"
"A minority of"
"A consensus of"
"Not very man of"
"A large proportion of"
"A clear mandate" (i.e. votes outof the 100)
Quantifying Phrase
SUMMARY OF SURVEY RESPONSES APPENDIX
Statistic
C
Mean*(Average)
ResponseMode
(Most Frequent)Median*
(Mid-Point)
Almost None 1 2.19. 2.84
A Couple 2 2.04 2.21
Damn Few 3 3.17 3.81
Several 3 7.47 11.94
Hardly Any 5 4.52 4.84
Few 10 7.08 8.31
Small Number of 10 8.16 9.02
Not Very Many 10 6 - 10 6 - 10
Lots 40 41 - 50 41 - 50
Many 40 31 - 40 31 7 40
Significant Number of 40. 31 - 40 31 - 40
Considerable Number of 40 31 - 40 31 - 40
Numerous 40 31 - 40 31 - 40
Minority 49 21 - 30 21 - 30
Majority 51. 51 - 55 51 - 55
Consensus 60 51- 60 51 - 60
Substantial Majority 75 66 - 70 66-- 70
Large Proportion 75 61 - 70 51 - 60
Clear Mandate 75 61 - 70 61 - 70
Most 90 71 - 80 61 - 70
Nearly All 90 86 - 90 86 - 90
Almost All 95 86 - 90 86 - 90
Virtually All 95 95.25 94.04
.
* In order to make the statistics of general usefulness medians and means arereported as ranges in those cases when appropriate.
9
TA
BL
E 1
. Ari
thm
etic
Mea
n fo
r N
ine
Gro
ups
on T
wen
ty T
wo
Item
s
ME
AN
Ave
rage
17,
Qua
ntify
ing
Phr
ase
Gro
up 1
Gro
up 2
Gro
up 3
Gro
up 4
Gro
up 5
'G
roup
6 -
Gro
up 7
',
Gro
up 8
',..
Gro
up 9
Age
4142
21.6
5340
.329
.329
.345
.2A
Few
7.4
17.1
9.8
3.9
17.4
8.2
10.1
10.1
6.4
A D
amn
Few
3.3
12.7
4.5
3.9
4.3
4.7
3.2
3.2
8.4
A C
oupl
e2
142.
92
10.5
10.9
6.4
6.4
7.1
Lots
60.2
63.7
58.7
34.9
46.6
62.6
46.1
46.1
48.9
A M
ajor
ity59
.856
.756
.957
.956
.666
.468
.768
.756
.8S
ever
al23
.317
.315
13.1
21.1
16.5
22.9
22.9
13.9
Man
y54
.345
.751
.7-,
30.4
50.3
49.9
45.8
45.8
44.9
Mos
t81
76.7
85.4
67.9
7881
.281
.781
.775
.6A
lmos
t All
95.8
93.3
94.4
81.4
92.4
85.5
86.3
86.3
88.2
Har
dly
Any
4.6
14.1
9.1
6.2
2.8
8.6
8.5
8.5
10.2
A S
ubst
antia
l Maj
ori
76.5
69.5
77.2
72.8
61.5
74.4
71.5
71.5
68.7
A S
igni
fican
t Num
b(57
.446
.760
.649
.354
.354
.258
.358
.350
.2V
irtua
lly A
ll87
.9_
94.8
9590
.785
.795
.889
.489
.487
.9A
lmos
t Non
e2.
410
.45.
92.
82.
21.
86.
96.
88.
3A
Sm
all N
umbe
r of
6.4
16.6
11.1
9.6
7.7
98.
78.
711
.6N
umer
ous
44.6
50.7
51.2
42.3
39.5
39.4
41.6
41.6
39.3
Nea
rly A
ll95
.487
.894
.785
.884
95.5
55.1
88.1
85.6
A M
inor
ity o
f24
.442
.333
.921
.141
.649
.126
.626
.630
.4A
Con
sens
us o
f73
.574
.773
.159
.484
.581
.568
.368
.370
.9N
ot V
ery
Man
y of
12.9
1519
10.5
8.3
15.5
12.5
12.5
13
A L
arge
Pro
port
ion
174
7071
.570
.570
.568
.466
.266
.256
.9A
Cle
ar M
anda
te84
.468
.777
.381
.969
.182
59.5
59.5
67.7
AE
RA
\ M
EA
N.X
LS
10P
age
1
113/
31 /9
8
TA
BL
E 2
. Med
ian
for
Nin
eG
roup
s on
Tw
enty
Tw
o It
ems
ME
DIA
N
Gro
up 5
:56
Gro
up 6
41.5
Gro
up 7
27G
roup
827
.. G
roup
944
Qua
ntify
ing
Phr
ase
Gro
up 1
,G
roup
.2G
roup
3G
roup
4A
ge41
4120
A F
ew6
76
312
55
53
A D
amn
Few
35
33
2.5
33
33
A C
oupl
e2
22
22
22
22
Lots
7075
6120
55.5
7540
4050
A M
ajor
ity51
5151
5151
6070
7051
Sev
eral
9.5
79
9.5
1210
1010
6.5
Man
y50
4052
.525
47.5
4540
4035
Mos
t85
8090
82.5
8085
9090
80A
lmos
t All
9695
9590
9095
9595
90H
ardl
y A
ny3
53
4.5
2.5
33
34.
5A
Sub
stan
tial M
ajor
'79
7575
7570
7577
7775
A S
igni
fican
t Num
b(60
4065
5065
5160
6055
Virt
ually
All
9898
9895
9598
9898
96A
lmos
t Non
e1
21.
51.
82
21
13
A S
mal
l Num
ber
of5
107.
510
97
66
7N
umer
ous
4850
47.5
3035
3735
3530
Nea
rly A
ll97
9095
9495
9895
9590
A M
inor
ity o
f20
4036
.522
.547
4025
2531
.5A
Con
sens
us o
f71
8075
5588
8570
7066
Not
Ver
y M
any
of10
1212
.510
415
1010
10A
Lar
ge P
ropo
rtio
n72
.570
7578
7570
7575
66A
Cle
ar M
anda
te82
.570
8085
68.5
8575
7570
AE
RA
WE
DIA
N.X
LS
12
Pag
e 1
J3/
31/9
8
TA
BL
E 3
. Mod
e fo
r N
ine
Gro
ups
on T
wen
ty T
wo
Item
s
MO
DE
-Q
uant
ifyin
g P
hrci
se..
Gro
Up:
1..
.Gro
up 2
,;G
roup
3G
roup
4G
roU
p 5
.,G
roU
p 6
Gro
up 7
Gro
up 8
Gro
up 9
Age
4135
2057
2323
A F
ew3
33
35
33
3A
Dam
n F
ew3
33
32
33
33
A C
oupl
e2
22
22
22
22
Lots
7030
2075
50A
Maj
ority
5151
5151
5151
5151
51S
ever
al3
155
55
Man
y50
8060
4040
25M
ost
9090
9090
9090
Alm
ost A
ll99
9599
9095
9590
Har
dly
Any
21
22
1
A S
ubst
antia
l Maj
orl
8075
7575
7085
8575
A S
igni
fican
t Num
b(60
4075
5060
6070
Virt
ually
All
9998
9995
9599
9999
98A
lmos
t Non
e1
11
11
11
A S
mal
l Num
ber
of10
610
1010
55
5N
umer
ous
6035
3015
3030
30N
early
All
9890
9595
;90
90A
Min
ority
of
2049
.49
3049
4010
10A
Con
sens
us o
f10
010
010
010
010
010
0N
ot V
ery
Man
y of
1010
10-3
1010
10A
Lar
ge P
ropo
rtio
n of
7075
8070
70A
Cle
ar M
anda
teI
7575
8010
067
8080
75
AE
RA
\ M
OD
E.X
LS
1 4
Pag
e 1
3/31/98
15
TA
BL
E 4
. Ran
ge V
alue
for
Nin
e G
roup
s on
Tw
enty
Tw
o It
ems
RA
NG
E V
ALU
E(T
he D
iffer
ence
Bet
wee
n th
e M
inim
um a
nd M
axim
um V
alue
s)Q
uant
ifyin
g P
hras
e,
Gro
Llp
1G
roup
:21G
toup
3G
roup
4G
roup
5G
roup
6G
roup
7G
roup
8G
roup
9A
ge19
2210
3529
2121
16A
Few
2577
4710
7723
5757
30A
Dam
n F
ew10
8822
815
119
974
A C
oupl
e0
8818
078
9888
8878
Lots
100
9085
8370
8595
9695
A M
ajor
ity39
3980
8939
4958
5875
Sev
eral
8877
9746
8768
8686
67M
any
8065
9076
7079
8484
95M
ost
4844
4069
2549
9090
94A
lmos
t All
,.9
1920
949
9098
9874
Har
dly
Any
2088
9929
568
7474
79A
Sub
stan
tial M
ajor
i48
7038
9075
5390
9075
A S
igni
fican
t Num
b(95
6575
5555
8693
9385
Virt
ually
All
9919
2479
100
990
9074
Alm
ost N
one
1069
749
54
9090
80A
Sm
all N
umbe
r of
1268
7918
1224
2323
27N
umer
ous
8157
7066
8068
7979
99N
early
All
978
1479
9910
9494
74A
Min
ority
of
4965
7946
7790
7373
45A
Con
sens
us o
f49
6595
8049
4999
9970
Not
Ver
y M
any
of30
3388
2130
3228
4725
A L
arge
Pro
port
ion
4040
6070
6576
8150
80A
Cle
ar M
anda
te33
6052
5010
040
9949
60
16A
ER
A \
RA
NG
E.X
LSP
age
13/
31/9
8
TA
BL
E 5
. Ran
ge o
f V
alue
s fo
r N
ine
Gro
ups
on T
wen
ty T
wo
Item
s
AB
CD
El
FG
I-I
IJ
K1 2
RA
NG
E O
F V
ALU
ES
3,
4-:
CIL
iarif
ifyin
g P
hras
e-,
:Gro
Up
1'.
Gro
iip 2
-.%
.:`G
roup
3'G
roU
P 4
,.G
roup
5 '
' Gro
Up
6". G
roup
7 .
Gro
Up
8G
roup
95
Age
30 to
49
35 to
57
20 to
30
31 to
66
25 to
54
22 to
43
22 to
43
38 to
54
6A
Few
0 to
25
3 to
80
3 to
50
2 to
12
3 to
80
2 to
25
3 to
60
3 to
60
0 to
30
7A
Dam
n F
ew0
to 1
02
to 9
02
to 2
42
to 1
00
to 1
52
to 1
31
to 1
01
to 1
01
to 7
58
A C
oupl
e2
to 2
2 to
90
2 to
20
2 to
22
to 8
02
to 1
002
to 9
02
to 9
02
to 8
09
Lots
0 to
100
10 to
100
15 to
100
4 to
87
0 to
70
15 to
100
4 to
100
4 to
100
5 to
100
10A
Maj
ority
51 to
90
51 to
90
10 to
90
10 to
99
51 to
90
51 b
100
40 to
98
40 to
98
25 to
100
11S
ever
al2
to 9
03
to 8
03
to 1
004
to 5
03
to 9
02
to 7
04
to 9
04
to 9
03
to 7
012
Man
y20
to 1
0015
to 8
010
to 1
004
to 8
020
to 9
020
b 9
96
to 9
06
to 9
05
to 1
0013
Mos
t51
to 9
951
to 9
560
to 1
0010
to 9
965
to 9
051
to 1
0010
to 1
0010
to 1
005
to 9
914
Alm
ost A
ll90
to 9
980
to 9
980
to 1
005
to 9
990
to 9
99
to 9
91
to 9
91
to 9
925
to 9
915
Har
dly
Any
0 to
20
2 to
90
1to
100
1to
30
0 to
51
to 6
91
to 7
51
to 7
51
to 8
016
A S
ubst
antia
l Maj
ority
51 to
99
20 to
90
60 to
98
10 to
100
0 to
75
45 to
98
8 to
98
8 to
98
20 to
95
17A
Sig
nific
ant N
umbe
r of
0 to
95
15 to
80
20 to
95
20 to
75
25 to
80
10 to
96
5 to
98
5 to
98
10 to
95
18V
irtua
lly A
ll0
to 9
980
to 9
975
to 9
920
to 9
90
to 1
0090
to 9
910
to 1
0010
to 1
0025
to 9
919
Alm
ost N
one
0 to
10
1to
70
1to
75
1to
10
0 to
51
to 5
0 to
90
0 to
90
0 to
80
20A
Sm
all N
umbe
r of
0 to
12
2 to
70
1to
80
2 to
20
0 to
12
2 to
26
2 to
25
2 to
25
3 to
30
21N
umer
ous
0 to
81
23 to
80
20 to
90
20 to
86
0 to
80
7 to
75
10 to
89
10 to
89
0 to
99
2 2
Nea
rly A
ll90
to 9
920
to 9
885
to 9
920
to 9
90
to 9
989
b 9
95
to 9
95
to 9
925
to 9
92
3A
Min
ority
of
0 to
49
15 to
80
1to
80
3 to
49
3 to
90
10 to
100
2 to
75
2 to
75
4 to
49
24A
Con
sens
us o
f51
to 1
0035
to 1
005
to 1
0020
to 1
0051
to 1
0051
to 1
001
to 1
001
to 1
0030
to 1
0025
Not
Ver
y M
any
of0
to 3
07
to 4
02
to 9
02
to 2
30
to 3
03
to 3
52
to 3
03
to 5
05
to 3
026
A L
arge
Pro
port
ion
of60
to 1
0045
to 8
530
to 9
020
to 9
025
to 9
020
to 9
63
to 9
045
to 9
55
to 8
527
A C
lear
Man
date
67 to
100
30 to
90
48 to
100
50 to
100
0 to
100
60 to
100
1to
100
51 to
100
30 to
90
9/4/
961
8P
age
111
:46
AM
19
Page/Date/Time 1 03-31-1998 12:37:31Database DAAERA\QualDB.S0
Histogram Section
150.0-
100.0-
50.0
APPENDIX E
0.0 r0 0 40.0 80.0
A_CoupleFIGURE 1. HISTOGRAM FOR "A COUPLE"
120.0
20
Page /Date/Time 1 03-31-1998 13:29:41Database D:\AERA \QuaIDB.S0
Histogram Section
100.0-
66.7-
Percent
33.3-
0.0-20.0
I 1 1
20.0 60.0 100.0
A_Few
FIGURE 2. HISTOGRAM FOR "A FEW"
Page/Date/Time 1 03-31-1998 12:54:55Database DAAERA\OualDB.S0
Histogram Section
6.wV
60.0-
40.0-
20.0-
0.00.0 40.0.0 80.0 120.0
A_MajorityFIGURE 3. HISTOGRAM FOR "A MAJORITY"
Page/Date/Time 1 03-31-1998 12:57:33Database D:\AERA \QuaIDB.S0
Histogram Section
"E'a)
12a)a.
60.0-
40.0-
20.0-
d----, t--.710.0-20.0
, I ,I I
73.3 120.026.7 7d.3
A_Substantial_Majority
FIGURE 4. HISTOGRAM FOR"A SUBSTANTIAL MAJORITY"
Page /Date/Time 1 03-31-1998 13:02:35Database D:\AERA \QuaIDB.S0
Histogram Section
30.0-
20.0-
Percent
10.0-
0.0-20.0 26.7 73.3
I 2
Numerous
FIGURE 5. HISTOGRAM FOR "NUMEROUS"
I 1
120.0
Page/Date/Time 1 03-31-1998 12:44:58Database D:\AERA \QuaIDB.S0
Histogram Section
30.0,
20.0-
Percent
10.0-
0.0 ,
-20.0 26.7 73.31 I 1
120.0Lots
FIGURE 6. HISTOGRAM FOR "LOTS"
25
Page/Date/TimeDatabase DAAERA
Histogram Section
50.0-
33.3-Za)Ua)o.
16.7-
0.0
1
\QuaIDB.S003-31-1998 13:04:42
00 40.0 80.0 120.0
A_Large_Proportion_of
FIGURE 7. HISTOGRAM FOR"A LARGE PROPORTION OF"
26
Page/Date/Time 1 03-31-1998 12:59:52Database D:\AERA \QuaIDB.S0
Histogram Section
120.0-
80.0-
Percent
40.0_
0.0 ,
-20.0
.. 1,'
26.7 73.3
Virtually_All
FIGURE 8. HISTOGRAM FOR"VIRTUALLY ALL"
1
120.0
U.S. Department of EducationOffice of Educational Research and Improvement (OERI)
National Library of Education (NLE)Educational Resources Information Center (ERIC)
REPRODUCTION RELEASE(Specific Document)
I. DOCUMENT IDENTIFICATION:
ERICTM028415
Title: W ORAS 4-A/ L T1, 6zR V A e- To r H 6- Sol? viryRESEVIRO#7?
Author(s): c'eAu i,i9v-REiti E. WALTel?SCorporate Source:prppE-Roive O., C.SEP. Aos / iv GEC ES ibt)IF-1-Er>
III:ST*RZC
Publication Date:
04 /6 -5'8
II. REPRODUCTION RELEASE:In order to disseminate as widely as possible timely and significant materials of interest to the educational community, documents announced in the
monthly abstract journal of the ERIC system, Resources in Education (RIE), are usually made available to users in microfiche, reproduced paper copy,and electronic media, and sold through the ERIC Document Reproduction Service (EDRS). Credit is given to the source of each document, and, ifreproduction release is granted, one of the following notices Is affixed to the document.
If permission is granted to reproduce and disseminate the identified document, please CHECK ONE of the following three options and sign at the bottomof the page.
The sample slicker shown below will beaffixed to all Level 1 documents
1
PERMISSION TO REPRODUCE ANDDISSEMINATE THIS MATERIAL HAS
BEEN GRANTED BY
Sa
TO THE EDUCATIONAL RESOURCESINFORMATION CENTER (ERIC)
Level 1
Check here for Level 1 release, perrnitdng reproductionand dissemination in microfiche or other ERIC archival
media (e.g., electronic) endpaper copy.
The sample sticker shown below will beaffixed to all Level 2A documents
PERMISSION TO REPRODUCE ANDDISSEMINATE THIS MATERIAL IN
MICROFICHE, AND IN ELECTRONIC MEDIAFOR ERIC COLLECTION SUBSCRIBERS ONLY,
HAS BEEN GRANTED BY
2A
TO THE EDUCATIONAL RESOURCESINFORMATION CENTER (ERIC)
Level 2A
Check here for Level 2A release, permltdng reproductionand dissemination in microfiche and in electronic media
for ERIC archival collection subscribers only
The sample sticker shown below will beaffixed to all Level 28 documents
PERMISSION TO REPRODUCE ANDDISSEMINATE THIS MATERIAL IN
MICROFICHE ONLY HAS BEEN GRANTED BY
2B
TO THE EDUCATIONAL RESOURCESINFORMATION CENTER (ERIC)
Level 2B
Check here for Level 2B release, permittingreproduction and dissemination in microfiche only
Documents will be processed as Indicated provided reproduction quality permits.If permission to reproduce Is granted, but no box Is checked, documents will be processed at Level 1.
I hereby grant to the Educational Resources Information Center (ERIC) nonexclusive permission to reproduce and disseminate this documentas indicated above. Reproduction from the ERIC microfiche or electronic media by persons other than ERIC employees and its systemcontractors requires permission from the copyright holder. Exception is made for non-profit reproduction by libraries and other service agenciesto satisfy information needs of educators in response to discrete inquiries.
here,-) 131- 4-Sign Sig
Organizatplease
d
cseT/F7tl7on
74. RecIAl L:ao
Chet McCall31 Pepperdine Univ., GSEP400 Corporate PointeCulver City, CA 90230
Telephone:3/0-'568* 2323 Fi'xio -54 8-5 9Ss-
E-Mail Address: 085iti-1i-ifiri ('cti 076.PI) NF. EDU (over)
III. DOCUMENT AVAILABILITY INFORMArTION (FROM NON-ERIC SOURCE):
If permission to reproduce is not granted to ERIC, or; if you wish ERIC to cite the availability of the document from another source, pleaseprovide the following information regarding the availability of the document. (ERIC will not announce a document unless it is publiclyavailable, and a dependable source can be specified. Contributors should also be aware that ERIC selection criteria are significantly morestringent for documents that cannot be made available through EDRS.)
Publisher/Distributor:
Address:
Price:
IV. REFERRAL OF ERIC TO COPYRIGHT/REPRODUCTION RIGHTS HOLDER:
If the right to grant this reproduction release is held by someone other than the addressee, please provide the appropriate name andaddress:
Name:
Address:
V. WHERE TO SEND THIS FORM:
Send this form to the following ERIC Clearinghouse:THE UNIVERSITY OF MARYLAND
ERIC CLEARINGHOUSE ON ASSESSMENT AND EVALUATION1129 SHRIVER LAB, CAMPUS DRIVE
COLLEGE PARK, MD 20742-5701Attn: Acquisitions
However, if solicited by the ERIC Facility, or if making an unsolicited contribution to ERIC, return this form (and the document beingcontributed) to:
ERIC Processing and Reference Facility1100 West Street, 2" Floor
Laurel, Maryland 20707-3598
Telephone: 301-497-4080Toll Free: 800-799-3742
FAX: 301-953-0263e -mail: [email protected]
WWW: http://ericfac.piccard.csc.com
EFF-088 (Rev. 9/97)PREVIOUS VERSIONS OF THIS FORM ARE OBSOLETE.