Background to the Parental Behaviour Data

The perception of parental behaviour by parents and their children was the central concern of the study from which the Parental Behaviour data have been drawn (Kojima, 1975). Kojima wanted to validate the component (or factorial) structure of the questionnaires used to measure parental behaviour. He argued that this could be done by comparing the reactions of parents and their children to parallel versions of the same instrument, more specifically he used two versions of the Children's Report of Parent Behaviour Inventory (Schaefer, 1965), one for the parents and one for the children.

• Boys data analysed in Kroonenberg (2008)
• Girls data analysed in Kroonenberg, Harshman, & Murakami (2009).

References

• Kojima, H. (1975). Inter-battery factor analysis of parents' and children's reports of parental behavior. Japanese Psychological Bulletin, 17, 33-48 (in Japanese).
• Kroonenberg, P. M. (2008). Applied multiway data analysis. Hoboken NJ: Wiley.
• Kroonenberg, P. M., Harshman, R. A, & Murakami, T. (2009). Analysing three-way profile data using the Parafac and Tucker3 models illustrated with views on parenting. Applied Multivariate Research, 13, 5-41. PDF: https://www.phaenex.uwindsor.ca/ojs/leddy/index.php/AMR/article/viewFile/2833/2271
• Schaefer, E. S. (1965). Children's reports of parental behavior: An inventory. Child Development, 36, 413-424.

Data description

The Japanese version of the Children's Report of Parent Behavior Inventory (CRPBI) was used for this study. In order to have parents judge their own behaviour Kojima (1975) developed a strictly parallel version of this inventory for them, the PRPBI. The CRPBI is a three-point Likert-type questionnaire designed to assess children's perceptions with respect to parental acceptance, permitted psychological autonomy, and level of parental control. The scales were unidirectional and the respondents were asked whether each statement was ``Not like'', ``Somewhat like'', and ``Like'' the parental behaviour. The original English versions are nearly identical in indicating behaviours of mothers and fathers, but the structure of the Japanese language made it possible to make a single version suitable for both parents. The substantive questions to be addressed in our analysis are (1) to what extent the structures of the questionnaire subscales are independent of who judges parental behaviour, (2) whether individual differences between judges exist, and (3) how such differences, if they exist, can be modeled and presented.

The boys data are ratings expressing the judgments of parents with respect to their own behaviour toward their sons, and the judgments of their sons with respect to their parents. Thus, there are four conditions: both parents assessing their own behaviour with respect to their sons --- Father-Own behaviour (F-F), Mother-Own behaviour (M-M); and the sons' judgment of their parents' behaviour --- Son-Father (B-F), Son-Mother (B-M). The judgments involved 150 middle-class Japanese eighth-grade boys on the 18 subscales of the inventory. Thus, the three-way profile data set consists of a 150 (Sons) x 18 (scales) x 4 (judgment combinations) data array.

The girls data are ratings expressing the judgments of parents with respect to their own behaviour toward their daughters, and the judgments of their daughters with respect to their parents. Thus, there are four conditions: both parents assessing their own behaviour with respect to their daughters --- Father-Own behaviour (F-F), Mother-Own behaviour (M-M); and the daughters' judgment of their parents' behaviour --- Daughter-Father (G-F), Daughter-Mother (G-M). The judgments involved 150 middle-class Japanese eighth-grade girls on the 18 subscales of the inventory. Thus, the three-way profile data set consists of a 153 (Daughters) x 18 (scales) x 4 (judgment combinations) data array.

Rows (1st mode): Sons/Daughters

Columns (2nd mode): Scales

Slices (3rd mode): Judges

Boys

Girls

Data arrangement for boys (girls similar)

A three-way data array X = (x(i,j,k)) has the following form

                        |-----|i=1
                   |-----|    |i=2
              |-----|    |    |..
              |     |    |    |..
              |     |    |____|i=I=150    k=K=4
              |     |____|            k=2
              |_____|              k=1
            j=1,.,J=18

The actual data file has the following form:

          j=1,.,J=18
            |-----|i=1
            |     |i=2
            |     |..     k= 1
            |     |..
            |_____|i=I=150
            |-----|i=1
            |     |i=2
            |     |..     k= 2
            |     |..
            |_____|i=I=150
            |-----|i=1
            |     |i=2
            |     |..     k=4
            |     |..
            |_____|i=I=150
      

Thus the first mode (i) is nested in the third mode (k) and there are 150 (Sons) times 4 (Judges) rows and 18 (Scales) columns.

Data handling

Given that the data are three-way profile data they are treated in the standard manner by centring per occasion-variable combination and by normalising the data after centring per lateral slice i.e. per scale over all sons/daughters x judges combinations. For details see Kroonenberg (2008). Applied multiway data analysis. Hoboken NJ: Wiley (Chapter 13).

Permissions

[Download the zipped Parental Behaviour Data for sons]

[Download the zipped Parental Behaviour Data for daughters]