结构方程模型统计检验力分析：原理与方法

结构方程模型是心理学、管理学、社会学等学科中重要的统计工具之一。然而, 大量使用结构方程模型的研究忽视了对该方法的统计检验力进行必要的分析和报告, 在一定程度上降低了这些研究的结果的证明效力。结构方程模型的统计检验力分析方法主要有Satorra-Saris法、MacCallum法与Monte Carlo法三类。其中Satorra-Saris法适用于备择模型清晰、检验对象相对简单、检验方法基于χ²分布的情形; MacCallum法适用于基于χ²分布的模型拟合检验且备择模型不明的情形; Monte Carlo法适用于检验对象相对复杂、采用模拟或重抽样方法进行检验的情形。在实际应用中, 研究者应当首先判断检验的目的、方法以及是否有明确的备择模型, 并根据这些信息选择具体的分析方法。     

Agency, authorship, and illusion

Daniel Wegner argues that conscious will is an illusion. I examine the adequacy of his theory of apparent mental causation and whether, if accurate, it suggests that our experience of agency and authorship should be considered illusory. I examine various interpretations of this claim and raise problems for each interpretation. I also distinguish between the experiences of agency and authorship.     

Free Will in the Block Universe

Carl Hoefer has argued that determinism in block universes does not privilege any particular time slice as the fundamental determiner of other time slices. He concludes from this that our actions are free, insofar as they are pieces of time slices we may legitimately regard as fundamental determiners. However, I argue that Hoefer does not adequately deal with certain remaining problems. For one, there remain pervasive asymmetries in causation and the macroscopic efficacy of our actions. I suggest that what Hoefer may have shown us is that causation, not determinism, was the threat to free will all along. Additionally, Hoefer might avoid the problem of the asymmetry of macroscopic efficacy by noting we have a very small region of space-time completely determined by our choices. However, this move implies our freedom to act is freedom to do very little, given that the region is trivial. I suggest that Hoefer should instead claim that we do have pervasive macroscopic efficacy toward the past, though I am unsure of how well this thesis works. Regardless, there remains a problem that the inside-out perspective requires us to see our choices as brute facts or random occurrences. Attempts to resolve this problem seem to require either a theory of agent causation or a traditional compatibilist argument, making Hoefer’s thesis extraneous, unless he can show us that these require the inside-out perspective. However, Hoefer has not yet shown us this, so there is work to be done.

Compatibilism,Evil, and the Free-Will Defense

It is widely believed that (1) if theological determinism were true, in virtue of God’s role in determining created agents to perform evil actions, created agents would be neither free nor morally responsible for their evil actions and God would not be perfectly good; (2) if metaphysical compatibilism were true, the free-will defense against the deductive problem of evil would fail; and (3) on the assumption of metaphysical compatibilism, God could have actualized just any one of those myriad possible worlds that are populated only by compatibilist free creatures. The primary thesis of this essay is that none of these propositions is true. This thesis is defended by appealing to a recently proposed novel, acausal, composite, unified theory of free action – the Theory of Middle Freedom – that evades the central problems plaguing traditional theories of metaphysical compatibilism.

Voluntary response selection in free association

Reaction time (RT) in free association (FA) is assumed to consist of three components: stimulus word encoding, response selection, and response generation. The RT of word naming contains the first and third components only. If response selection is a serial voluntary search it can be manipulated by rewarding response speeding. This would lead the subject to terminate the search sooner. Thus, greater speeding will be achieved for delayed responses, for which search was long, than for undelayed ones. This differential speeding effect was observed in Experriment 1 ( N =17), in which the task was FA. Speeding effect was not differential in Experiment 2, in which the subjects ( N =16) were given a word naming task. Both of these experiments employed a between-subjects design. Their results were replicated in Experiment 3 ( N =13), which employed a within-subject design. The results, taken together, suggest that differential speeding is specific to response selection, in accordance with Flekkoy's (1973 a , 1981) voluntary selection model. However, they are inconsistent with the traditional associonistic models.     

Relations Between Continuous Performance Test Performance Measures and ADHD Behaviors

The Conners' Continuous Performance Test (CPT) is a neuropsychological task that has repeatedly been shown to differentiate ADHD from normal groups. Several variables may be derived from the Conners' CPT including errors of omission and commission, mean hit reaction time(RT), mean hit RT standard error, d', and . What each CPT parameter actually assesses has largely been based upon clinical assumptions and the face validity of each measure (e.g., omission errors measure inattention, commission errors measure impulsivity). This study attempts to examine relations between various CPT variables and phenotypic behaviors so as to better understand the various CPT variables. An epidemiological sample of 817 children was administered the Conners' CPT. Diagnostic interviews were conducted with parents to determine ADHD symptom profiles for all children. Children diagnosed with ADHD had more variable RTs, made more errors of commission and omission, and demonstrated poorer perceptual sensitivity than nondiagnosed children. Regarding specific symptoms, generalized estimating equations (GEE) and ANCOVAs were conducted to determine specific relationships between the 18 DSM-IV ADHD symptoms and 6 CPT parameters. CPT performance measures demonstrated significant relationships to ADHD symptoms but did not demonstrate symptom domain specificity according to a priori assumptions. Overall performance on the two signal detection measures, d' and , was highly related to all ADHD symptoms across symptom domains. Further, increased variability in RTs over time was related to most ADHD symptoms. Finally, it appears that at least 1 CPT variable, mean hit RT, is minimally related to ADHD symptoms as a whole, but does demonstrate some specificity in its link with symptoms of hyperactivity.     

Age-related differences in the von Restorff isolation effect

When one item is made distinct from the other items in a list, memory for the distinctive item is improved, a finding known as the isolation or von Restorff effect (after von Restorff, 1933). Although demonstrated numerous times with younger adults and children, this effect has not been found with older adults (Cimbalo & Brink, 1982). In contrast to the earlier study, we obtained a significant von Restorff effect for both younger and older adults using a physical manipulation of font colour. The effect size for older adults was smaller than that obtained for younger adults, confirming a prediction of Naveh-Benjamin's (2000) associative deficit hypothesis, which attributes age-related differences in memory performance to older adults' reduced ability to form associations. The findings are consistent with related research in which older adults demonstrate similar—but smaller—benefits for distinctive information to those for younger adults.     

Age-related differences in the von restorff isolation effect

When one item is made distinct from the other items in a list, memory for the distinctive item is improved, a finding known as the isolation or von Restorff effect (after von Restorff, 1933). Although demonstrated numerous times with younger adults and children, this effect has not been found with older adults (Cimbalo & Brink, 1982). In contrast to the earlier study, we obtained a significant von Restorff effect for both younger and older adults using a physical manipulation of font colour. The effect size for older adults was smaller than that obtained for younger adults, confirming a prediction of Naveh-Benjamin's (2000) associative deficit hypothesis, which attributes age-related differences in memory performance to older adults' reduced ability to form associations. The findings are consistent with related research in which older adults demonstrate similar—but smaller—benefits for distinctive information to those for younger adults.     

What can we learn about immediate memory from the development of children's free recall?

We ask the question: Which aspects of immediate memory performance improve with age? In two studies, we reexamine the widely held view that primary memory capacity estimates derived from children's immediate free recall are age invariant. This was done by assessing children's immediate free-recall accuracy while also measuring the order in which they elected to recall items (Experiment 1) and by encouraging children to begin free recall with items from towards the end of the presented list (Experiment 2). Across samples aged between 5 and 8 years we replicated the previously reported age-related changes in free-recall serial position functions when aggregated across all trials of the standard task, including an absence of age differences in the recency portion of this curve. However, we also show that this does not reflect the fact that primary memory capacity is constant across age. Instead, when we incorporate order of report information, clear age differences are evident in the recall of list-final items that are output at the start of a participant's response. In addition, the total amount that individuals recalled varied little across different types of free-recall tasks. These findings have clear implications for the use of immediate free recall as a means of providing potential indices of primary memory capacity and in the study of the development of immediate memory.