Access

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

If You Use a Screen Reader

This content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.

SIZE OF POPULATION AND VARIABILITY OF DEMOGRAPHIC DATA 17th and 18th Centuries

BARBARA SPENCER
Genus
Vol. 32, No. 3/4 (1976), pp. 11-42
Stable URL: http://www.jstor.org/stable/29788128
Page Count: 32
  • Read Online (Free)
  • Subscribe ($19.50)
  • Cite this Item
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
SIZE OF POPULATION AND VARIABILITY OF DEMOGRAPHIC DATA 17th and 18th Centuries
Preview not available

Abstract

This study of the variability of births and marriages is an attempt to examine some of the possible consequences of basing economic and demographic analysis on small populations. Small populations have not been extensively used because of the fear that the variability of the data may be too high for reliable estimates. Using mostly Belgium birth and marriage data from villages and parishes in the 17th and 18th centuries, we show that the coefficient of variation decreases with increased sample size but at a decreasing rate. In fact the advantage of increased sample size in reducing the variability of the data becomes rather insignificant at relatively low numbers of births and marriages per year. Furthermore since the functional form fitted is based on theoretical considerations arising from the binomial distribution, we have reason to believe that similar results will be found with other data. This would seem to indicate that relationships obtained from relatively small villages and parishes may be just as reliable as those from larger populations for the purpose of inferring the existence of the relationships in other populations experiencing similar economic circumstances. Questo studio della variabilità delle nascite e dei matrimoni si propone di valutare alcune delle possibili conseguenze che scaturiscono dall'analisi economica e demografica quando questa venga condotta su piccoli gruppi. Le ricerche su piccoli gruppi non sono, generalmente, molto utilizzate per il timore che l'elevata variabilità dei dati pregiudichi l'attendibilità delle valutazioni. Ricorrendo soprattutto a dati su nascite e matrimoni di comuni e parrocchie belghe nel XVII e XVIII secolo, si constata che il coefficiente di variazione tende a diminuire quando aumenta l'ampiezza del campione, ma in misura decrescente. Infatti il vantaggio derivante dall'adozione di campioni più grandi al fine della riduzione della variabilità dei dati, diviene presto piuttosto trascurabile, anche in corrispondenza di un numero annuo di nascite e matrimoni ancora relativamente basso. Inoltre, dal momento che la forma di relazione funzionale prescelta si basa su presupposti teorici collegati alla distribuzione binomiale, si è portati a credere che i risultati ottenuti su dati di villaggi e parrocchie relativamente piccoli, possano avere la medesima attendibilità di quelli stimati su popolazioni più ampie, allorché ci si prefigga di inferire l'esistenza delle stesse relazioni in altre popolazioni che sperimentano analoghe condizioni economiche. Cette étude de la variabilité des naissances et des mariages est un effort pour examiner certaines des conséquences d'une analyse économique et démographique basée sur des petites populations. Des petites populations n'ont pas été beaucoup utilisées par crainte que la variabilité des données soit trop grande pour des évaluations sûres. Employant principalement des dates de naissances et de mariages des villages et des paroisses belges aux dix-septième et dix-huitième siècles, on montre que le coéfficient de variation diminue quand on augmente le nombre d'observations mais il diminue à un taux décroissant. En effet, l'avantage d'un plus grand échantillon pour réduire la variabilité des données devient assez minime quand le nombre de naissances et de mariages enregistré par an est relativement bas. En outre, puisque la forme fonctionnelle employée est basée sur des considérations théorétiques provenant de la distribution binomiale, on a lieu de croire que des résultats obtenus dans des villages et paroisses relativement petits pourraient être tout aussi sûrs que ceux obtenus dans des populations plus grandes quand on a l'intention d'inférer l'existence de relations dans d'autres populations ayant des conditions économiques pareilles.

Page Thumbnails

  • Thumbnail: Page 
11
    11
  • Thumbnail: Page 
12
    12
  • Thumbnail: Page 
13
    13
  • Thumbnail: Page 
14
    14
  • Thumbnail: Page 
15
    15
  • Thumbnail: Page 
16
    16
  • Thumbnail: Page 
17
    17
  • Thumbnail: Page 
18
    18
  • Thumbnail: Page 
19
    19
  • Thumbnail: Page 
20
    20
  • Thumbnail: Page 
21
    21
  • Thumbnail: Page 
22
    22
  • Thumbnail: Page 
23
    23
  • Thumbnail: Page 
24
    24
  • Thumbnail: Page 
25
    25
  • Thumbnail: Page 
26
    26
  • Thumbnail: Page 
27
    27
  • Thumbnail: Page 
28
    28
  • Thumbnail: Page 
29
    29
  • Thumbnail: Page 
30
    30
  • Thumbnail: Page 
31
    31
  • Thumbnail: Page 
32
    32
  • Thumbnail: Page 
33
    33
  • Thumbnail: Page 
34
    34
  • Thumbnail: Page 
35
    35
  • Thumbnail: Page 
36
    36
  • Thumbnail: Page 
37
    37
  • Thumbnail: Page 
38
    38
  • Thumbnail: Page 
39
    39
  • Thumbnail: Page 
40
    40
  • Thumbnail: Page 
41
    41
  • Thumbnail: Page 
42
    42