论文部分内容阅读
目的:探讨中华成人智力量表事前智商的估计方法。方法:中华成人智力量表(ISCA)标准化样本被随机分成人数大致相等的两组,分别用于建立智商估计公式和效度检验。公式建立经由一系列以全量表智商为因变量、保持测验成绩和人口统计学变量为自变量的分层线性回归而实现,效度检验时比较估计值和实际值的分布、平均数差异、相关性和等级一致程度。结果:两组的人口统计学特征和测验成绩无显著差异。十个估计公式调整R2为38.3%-86.6%,估计标准误为11.84-5.47。估计智商平均数与实际智商无显著差异,全距较实际智商有程度不同的缩窄。估计值与实际值相关系数为0.62-0.93,相同等级比率为49.9%-67.8%。联合分测验成绩能大幅提高估计效度,增加联合的分测验项数能提高估计精确度,但项目的平均贡献下降。结论:基于ISCA常模数据建立了10个ISCA智商的估计公式,在正常成人中使用具有满意的估计效度。
Objective: To explore the method of estimating the IQ of Chinese Adult Intelligence Scale. Methods: Standardized samples of Chinese Adult Intelligence Scale (ISCA) were randomly divided into two groups of approximately equal numbers, which were used to establish IQ estimation formula and validity test respectively. The formula is established through a series of stratified linear regression with full scale IQ as the dependent variable, test scores and demographic variables as independent variables. The validity test compares the distribution of the estimated and actual values, the mean difference, the correlation Sex and level of consistency. Results: There was no significant difference between the two groups in demographic characteristics and test scores. The adjustment of the ten estimation formulas is 38.3% -86.6% for R2, with an estimated standard error of 11.84-5.47. There is no significant difference between the estimated IQ and the actual IQ, and the full range is narrower than the actual IQ. The correlation coefficient between estimated value and actual value is 0.62-0.93, and the same rank ratio is 49.9% -67.8%. Joint sub-test score can greatly improve the validity of the test, increase the number of sub-test joint can improve the accuracy of the estimate, but the average contribution of the project decreased. CONCLUSIONS: Estimates of 10 ISCA IQs based on ISCA norm data were constructed and used in normal adults with satisfactory estimates of validity.